Computer Vision and Pattern Recognition (cs.CV)

Abstract: Scale variation is a deep-rooted problem in object counting, which has not been effectively addressed by existing scale-aware algorithms. An important factor is that they typically involve cooperative learning across multi-resolutions, which could be suboptimal for learning the most discriminative features from each scale. In this paper, we propose a novel method termed STEERER (\textbf{S}elec\textbf{T}iv\textbf{E} inh\textbf{ER}itance l\textbf{E}a\textbf{R}ning) that addresses the issue of scale variations in object counting. STEERER selects the most suitable scale for patch objects to boost feature extraction and only inherits discriminative features from lower to higher resolution progressively. The main insights of STEERER are a dedicated Feature Selection and Inheritance Adaptor (FSIA), which selectively forwards scale-customized features at each scale, and a Masked Selection and Inheritance Loss (MSIL) that helps to achieve high-quality density maps across all scales. Our experimental results on nine datasets with counting and localization tasks demonstrate the unprecedented scale generalization ability of STEERER. Code is available at \url{https://github.com/taohan10200/STEERER}.

Abstract: In this paper, we revisit the limitations of anchor-based lane detection methods, which have predominantly focused on fixed anchors that stem from the edges of the image, disregarding their versatility and quality. To overcome the inflexibility of anchors, we decompose them into learning the heat map of starting points and their associated directions. This decomposition removes the limitations on the starting point of anchors, making our algorithm adaptable to different lane types in various datasets. To enhance the quality of anchors, we introduce the Large Kernel Attention (LKA) for Feature Pyramid Network (FPN). This significantly increases the receptive field, which is crucial in capturing the sufficient context as lane lines typically run throughout the entire image. We have named our proposed system the Anchor Decomposition Network (ADNet). Additionally, we propose the General Lane IoU (GLIoU) loss, which significantly improves the performance of ADNet in complex scenarios. Experimental results on three widely used lane detection benchmarks, VIL-100, CULane, and TuSimple, demonstrate that our approach outperforms the state-of-the-art methods on VIL-100 and exhibits competitive accuracy on CULane and TuSimple. Code and models will be released on https://github.com/ Sephirex-X/ADNet.

Abstract: In this work, we focus on synthesizing high-quality textures on 3D meshes. We present Point-UV diffusion, a coarse-to-fine pipeline that marries the denoising diffusion model with UV mapping to generate 3D consistent and high-quality texture images in UV space. We start with introducing a point diffusion model to synthesize low-frequency texture components with our tailored style guidance to tackle the biased color distribution. The derived coarse texture offers global consistency and serves as a condition for the subsequent UV diffusion stage, aiding in regularizing the model to generate a 3D consistent UV texture image. Then, a UV diffusion model with hybrid conditions is developed to enhance the texture fidelity in the 2D UV space. Our method can process meshes of any genus, generating diversified, geometry-compatible, and high-fidelity textures. Code is available at https://cvmi-lab.github.io/Point-UV-Diffusion

Abstract: The development of computer vision algorithms for Unmanned Aerial Vehicles (UAVs) imagery heavily relies on the availability of annotated high-resolution aerial data. However, the scarcity of large-scale real datasets with pixel-level annotations poses a significant challenge to researchers as the limited number of images in existing datasets hinders the effectiveness of deep learning models that require a large amount of training data. In this paper, we propose a multimodal synthetic dataset containing both images and 3D data taken at multiple flying heights to address these limitations. In addition to object-level annotations, the provided data also include pixel-level labeling in 28 classes, enabling exploration of the potential advantages in tasks like semantic segmentation. In total, our dataset contains 72k labeled samples that allow for effective training of deep architectures showing promising results in synthetic-to-real adaptation. The dataset will be made publicly available to support the development of novel computer vision methods targeting UAV applications.

Abstract: Handwritten mathematical expression recognition (HMER) has attracted extensive attention recently. However, current methods cannot explicitly study the interactions between different symbols, which may fail when faced similar symbols. To alleviate this issue, we propose a simple but efficient method to enhance semantic interaction learning (SIL). Specifically, we firstly construct a semantic graph based on the statistical symbol co-occurrence probabilities. Then we design a semantic aware module (SAM), which projects the visual and classification feature into semantic space. The cosine distance between different projected vectors indicates the correlation between symbols. And jointly optimizing HMER and SIL can explicitly enhances the model's understanding of symbol relationships. In addition, SAM can be easily plugged into existing attention-based models for HMER and consistently bring improvement. Extensive experiments on public benchmark datasets demonstrate that our proposed module can effectively enhance the recognition performance. Our method achieves better recognition performance than prior arts on both CROHME and HME100K datasets.

Abstract: Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, we consider a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, we find that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is non-trivial. The spectral bias of deep networks hinders the higher frequency modes in Gaussian vectors from being learned and hence impairs the reconstruction of image details. To tackle this issue, we design a network unit, named Frequency Compensation block (FCB), with a bank of filters that jointly emphasize the mid-to-high frequencies of an input signal. We demonstrate that diffusion models with FCB achieve significant gains in both perceptual and distortion metrics. Second, to further boost the generalization performance, we propose a novel data synthesis pipeline, HazeAug, to augment haze in terms of degree and diversity. Within the framework, a solid baseline for blind dehazing is set up where models are trained on synthetic hazy-clean pairs, and directly generalize to real data. Extensive evaluations show that the proposed dehazing diffusion model significantly outperforms state-of-the-art methods on real-world images.

Abstract: Understanding digital documents is like solving a puzzle, especially historical ones. Document Layout Analysis (DLA) helps with this puzzle by dividing documents into sections like paragraphs, images, and tables. This is crucial for machines to read and understand these documents.In the DL Sprint 2.0 competition, we worked on understanding Bangla documents. We used a dataset called BaDLAD with lots of examples. We trained a special model called Mask R-CNN to help with this understanding. We made this model better by step-by-step hyperparameter tuning, and we achieved a good dice score of 0.889.However, not everything went perfectly. We tried using a model trained for English documents, but it didn't fit well with Bangla. This showed us that each language has its own challenges. Our solution for the DL Sprint 2.0 is publicly available at https://www.kaggle.com/competitions/dlsprint2/discussion/432201 along with notebooks, weights, and inference notebook.

Abstract: Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will affect the real-time perception of streaming applications. Despite the wide application of quantization to lighten models, we show in our paper that directly applying quantization in BEV tasks will 1) make the training unstable, and 2) lead to intolerable performance degradation. To solve these issues, our method QD-BEV enables a novel view-guided distillation (VGD) objective, which can stabilize the quantization-aware training (QAT) while enhancing the model performance by leveraging both image features and BEV features. Our experiments show that QD-BEV achieves similar or even better accuracy than previous methods with significant efficiency gains. On the nuScenes datasets, the 4-bit weight and 6-bit activation quantized QD-BEV-Tiny model achieves 37.2% NDS with only 15.8 MB model size, outperforming BevFormer-Tiny by 1.8% with an 8x model compression. On the Small and Base variants, QD-BEV models also perform superbly and achieve 47.9% NDS (28.2 MB) and 50.9% NDS (32.9 MB), respectively.

Abstract: Intracerebral hemorrhage is one of the diseases with the highest mortality and poorest prognosis worldwide. Spontaneous intracerebral hemorrhage (SICH) typically presents acutely, prompt and expedited radiological examination is crucial for diagnosis, localization, and quantification of the hemorrhage. Early detection and accurate segmentation of perihematomal edema (PHE) play a critical role in guiding appropriate clinical intervention and enhancing patient prognosis. However, the progress and assessment of computer-aided diagnostic methods for PHE segmentation and detection face challenges due to the scarcity of publicly accessible brain CT image datasets. This study establishes a publicly available CT dataset named PHE-SICH-CT-IDS for perihematomal edema in spontaneous intracerebral hemorrhage. The dataset comprises 120 brain CT scans and 7,022 CT images, along with corresponding medical information of the patients. To demonstrate its effectiveness, classical algorithms for semantic segmentation, object detection, and radiomic feature extraction are evaluated. The experimental results confirm the suitability of PHE-SICH-CT-IDS for assessing the performance of segmentation, detection and radiomic feature extraction methods. To the best of our knowledge, this is the first publicly available dataset for PHE in SICH, comprising various data formats suitable for applications across diverse medical scenarios. We believe that PHE-SICH-CT-IDS will allure researchers to explore novel algorithms, providing valuable support for clinicians and patients in the clinical setting. PHE-SICH-CT-IDS is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/PHE-SICH-CT-IDS/23957937.

Abstract: Multi-view representation learning aims to capture comprehensive information from multiple views of a shared context. Recent works intuitively apply contrastive learning to different views in a pairwise manner, which is still scalable: view-specific noise is not filtered in learning view-shared representations; the fake negative pairs, where the negative terms are actually within the same class as the positive, and the real negative pairs are coequally treated; evenly measuring the similarities between terms might interfere with optimization. Importantly, few works study the theoretical framework of generalized self-supervised multi-view learning, especially for more than two views. To this end, we rethink the existing multi-view learning paradigm from the perspective of information theory and then propose a novel information theoretical framework for generalized multi-view learning. Guided by it, we build a multi-view coding method with a three-tier progressive architecture, namely Information theory-guided hierarchical Progressive Multi-view Coding (IPMC). In the distribution-tier, IPMC aligns the distribution between views to reduce view-specific noise. In the set-tier, IPMC constructs self-adjusted contrasting pools, which are adaptively modified by a view filter. Lastly, in the instance-tier, we adopt a designed unified loss to learn representations and reduce the gradient interference. Theoretically and empirically, we demonstrate the superiority of IPMC over state-of-the-art methods.

Abstract: State-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them on limited hardware resources, especially for recent popular large language models (LLM) and computer vision models (CV). Recent popular dataset distillation methods are thus developed, aiming to reduce the number of training samples via synthesizing small-scale datasets via gradient matching. However, as the gradient calculation is coupled with the specific network architecture, the synthesized dataset is biased and performs poorly when used for training unseen architectures. To address these limitations, we present dataset quantization (DQ), a new framework to compress large-scale datasets into small subsets which can be used for training any neural network architectures. Extensive experiments demonstrate that DQ is able to generate condensed small datasets for training unseen network architectures with state-of-the-art compression ratios for lossless model training. To the best of our knowledge, DQ is the first method that can successfully distill large-scale datasets such as ImageNet-1k with a state-of-the-art compression ratio. Notably, with 60% data from ImageNet and 20% data from Alpaca's instruction tuning data, the models can be trained with negligible or no performance drop for both vision tasks (including classification, semantic segmentation, and object detection) as well as language tasks (including instruction tuning tasks such as BBH and DROP).

Abstract: Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained. In such cases, multi-view self-supervision and synthetic-to-real transfer serve as alternative approaches, however, with a considerable performance reduction in comparison to supervised case. Instead, we propose a single-view self-supervised method that achieves a performance similar to the supervised case. In some medical devices, such as endoscopes, the camera and light sources are co-located at a small distance from the target surfaces. Thus, we can exploit that, for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance to the surface, providing a strong single-view self-supervisory signal. In our experiments, our self-supervised models deliver accuracies comparable to those of fully supervised ones, while being applicable without depth ground-truth data.

Abstract: Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based methods and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate post-processing, leading to high computational overhead. Regression-based methods undertake instance-aware prediction but face limitations in robustness and data efficiency due to their reliance on high-level representations. In our academic pursuit, we propose SRFormer, a unified DETR-based model with amalgamated Segmentation and Regression, aiming at the synergistic harnessing of the inherent robustness in segmentation representations, along with the straightforward post-processing of instance-level regression. Our empirical analysis indicates that favorable segmentation predictions can be obtained at the initial decoder layers. In light of this, we constrain the incorporation of segmentation branches to the first few decoder layers and employ progressive regression refinement in subsequent layers, achieving performance gains while minimizing additional computational load from the mask. Furthermore, we propose a Mask-informed Query Enhancement module. We take the segmentation result as a natural soft-ROI to pool and extract robust pixel representations, which are then employed to enhance and diversify instance queries. Extensive experimentation across multiple benchmarks has yielded compelling findings, highlighting our method's exceptional robustness, superior training and data efficiency, as well as its state-of-the-art performance.

Abstract: In this study, we propose a method for jointly learning of images and videos using a single model. In general, images and videos are often trained by separate models. We propose in this paper a method that takes a batch of images as input to Vision Transformer IV-ViT, and also a set of video frames with temporal aggregation by late fusion. Experimental results on two image datasets and two action recognition datasets are presented.

Abstract: Training deep generative models usually requires a large amount of data. To alleviate the data collection cost, the task of zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain without any further training samples. Due to the data absence, the textual description of the target domain and the vision-language models, e.g., CLIP, are utilized to effectively guide the generator. However, with only a single representative text feature instead of real images, the synthesized images gradually lose diversity as the model is optimized, which is also known as mode collapse. To tackle the problem, we propose a novel method to find semantic variations of the target text in the CLIP space. Specifically, we explore diverse semantic variations based on the informative text feature of the target domain while regularizing the uncontrolled deviation of the semantic information. With the obtained variations, we design a novel directional moment loss that matches the first and second moments of image and text direction distributions. Moreover, we introduce elastic weight consolidation and a relation consistency loss to effectively preserve valuable content information from the source domain, e.g., appearances. Through extensive experiments, we demonstrate the efficacy of the proposed methods in ensuring sample diversity in various scenarios of zero-shot GAN adaptation. We also conduct ablation studies to validate the effect of each proposed component. Notably, our model achieves a new state-of-the-art on zero-shot GAN adaptation in terms of both diversity and quality.

Abstract: Hand action recognition is essential. Communication, human-robot interactions, and gesture control are dependent on it. Skeleton-based action recognition traditionally includes hands, which belong to the classes which remain challenging to correctly recognize to date. We propose a method specifically designed for hand action recognition which uses relative angular embeddings and local Spherical Harmonics to create novel hand representations. The use of Spherical Harmonics creates rotation-invariant representations which make hand action recognition even more robust against inter-subject differences and viewpoint changes. We conduct extensive experiments on the hand joints in the First-Person Hand Action Benchmark with RGB-D Videos and 3D Hand Pose Annotations, and on the NTU RGB+D 120 dataset, demonstrating the benefit of using Local Spherical Harmonics Representations. Our code is available at https://github.com/KathPra/LSHR_LSHT.

Abstract: Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of spatial invariance in the data-forwarding process. In this study, we present a novel approach, termed Spatial Transform Decoupling (STD), providing a simple-yet-effective solution for oriented object detection with ViTs. Built upon stacked ViT blocks, STD utilizes separate network branches to predict the position, size, and angle of bounding boxes, effectively harnessing the spatial transform potential of ViTs in a divide-and-conquer fashion. Moreover, by aggregating cascaded activation masks (CAMs) computed upon the regressed parameters, STD gradually enhances features within regions of interest (RoIs), which complements the self-attention mechanism. Without bells and whistles, STD achieves state-of-the-art performance on the benchmark datasets including DOTA-v1.0 (82.24% mAP) and HRSC2016 (98.55% mAP), which demonstrates the effectiveness of the proposed method. Source code is available at https://github.com/yuhongtian17/Spatial-Transform-Decoupling.

Abstract: The field of Computer Vision (CV) was born with the single grand goal of complete image understanding: providing a complete semantic interpretation of an input image. What exactly this goal entails is not immediately straightforward, but theoretical hierarchies of visual understanding point towards a top level of full semantics, within which sits the most complex and subjective information humans can detect from visual data. In particular, non-concrete concepts including emotions, social values and ideologies seem to be protagonists of this "high-level" visual semantic understanding. While such "abstract concepts" are critical tools for image management and retrieval, their automatic recognition is still a challenge, exactly because they rest at the top of the "semantic pyramid": the well-known semantic gap problem is worsened given their lack of unique perceptual referents, and their reliance on more unspecific features than concrete concepts. Given that there seems to be very scarce explicit work within CV on the task of abstract social concept (ASC) detection, and that many recent works seem to discuss similar non-concrete entities by using different terminology, in this survey we provide a systematic review of CV work that explicitly or implicitly approaches the problem of abstract (specifically social) concept detection from still images. Specifically, this survey performs and provides: (1) A study and clustering of high level visual understanding semantic elements from a multidisciplinary perspective (computer science, visual studies, and cognitive perspectives); (2) A study and clustering of high level visual understanding computer vision tasks dealing with the identified semantic elements, so as to identify current CV work that implicitly deals with AC detection.

Abstract: Depth sensing is a crucial function of unmanned aerial vehicles and autonomous vehicles. Due to the small size and simple structure of monocular cameras, there has been a growing interest in depth estimation from a single RGB image. However, state-of-the-art monocular CNN-based depth estimation methods using fairly complex deep neural networks are too slow for real-time inference on embedded platforms. This paper addresses the problem of real-time depth estimation on embedded systems. We propose two efficient and lightweight encoder-decoder network architectures, RT-MonoDepth and RT-MonoDepth-S, to reduce computational complexity and latency. Our methodologies demonstrate that it is possible to achieve similar accuracy as prior state-of-the-art works on depth estimation at a faster inference speed. Our proposed networks, RT-MonoDepth and RT-MonoDepth-S, runs at 18.4\&30.5 FPS on NVIDIA Jetson Nano and 253.0\&364.1 FPS on NVIDIA Jetson AGX Orin on a single RGB image of resolution 640$\times$192, and achieve relative state-of-the-art accuracy on the KITTI dataset. To the best of the authors' knowledge, this paper achieves the best accuracy and fastest inference speed compared with existing fast monocular depth estimation methods.

Abstract: Temporal Action Detection (TAD) is challenging but fundamental for real-world video applications. Recently, DETR-based models have been devised for TAD but have not performed well yet. In this paper, we point out the problem in the self-attention of DETR for TAD; the attention modules focus on a few key elements, called temporal collapse problem. It degrades the capability of the encoder and decoder since their self-attention modules play no role. To solve the problem, we propose a novel framework, Self-DETR, which utilizes cross-attention maps of the decoder to reactivate self-attention modules. We recover the relationship between encoder features by simple matrix multiplication of the cross-attention map and its transpose. Likewise, we also get the information within decoder queries. By guiding collapsed self-attention maps with the guidance map calculated, we settle down the temporal collapse of self-attention modules in the encoder and decoder. Our extensive experiments demonstrate that Self-DETR resolves the temporal collapse problem by keeping high diversity of attention over all layers.

Abstract: In daily life, humans utilize hands to manipulate objects. Modeling the shape of objects that are manipulated by the hand is essential for AI to comprehend daily tasks and to learn manipulation skills. However, previous approaches have encountered difficulties in reconstructing the precise shapes of hand-held objects, primarily owing to a deficiency in prior shape knowledge and inadequate data for training. As illustrated, given a particular type of tool, such as a mug, despite its infinite variations in shape and appearance, humans have a limited number of 'effective' modes and poses for its manipulation. This can be attributed to the fact that humans have mastered the shape prior of the 'mug' category, and can quickly establish the corresponding relations between different mug instances and the prior, such as where the rim and handle are located. In light of this, we propose a new method, CHORD, for Category-level Hand-held Object Reconstruction via shape Deformation. CHORD deforms a categorical shape prior for reconstructing the intra-class objects. To ensure accurate reconstruction, we empower CHORD with three types of awareness: appearance, shape, and interacting pose. In addition, we have constructed a new dataset, COMIC, of category-level hand-object interaction. COMIC contains a rich array of object instances, materials, hand interactions, and viewing directions. Extensive evaluation shows that CHORD outperforms state-of-the-art approaches in both quantitative and qualitative measures. Code, model, and datasets are available at https://kailinli.github.io/CHORD.

Abstract: Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from scratch with specialised methods: therefore, access to a training dataset is required when the need for zero-shot classification arises. In this paper, we aim to equip pre-trained models with zero-shot classification capabilities without the use of image data. We achieve this with our proposed Image-free Classifier Injection with Semantics (ICIS) that injects classifiers for new, unseen classes into pre-trained classification models in a post-hoc fashion without relying on image data. Instead, the existing classifier weights and simple class-wise descriptors, such as class names or attributes, are used. ICIS has two encoder-decoder networks that learn to reconstruct classifier weights from descriptors (and vice versa), exploiting (cross-)reconstruction and cosine losses to regularise the decoding process. Notably, ICIS can be cheaply trained and applied directly on top of pre-trained classification models. Experiments on benchmark ZSL datasets show that ICIS produces unseen classifier weights that achieve strong (generalised) zero-shot classification performance. Code is available at https://github.com/ExplainableML/ImageFreeZSL .

Abstract: Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak transferability in the black-box setting. Recently, various methods have been proposed to improve adversarial transferability, in which the input transformation is one of the most effective methods. In this work, we notice that existing input transformation-based works mainly adopt the transformed data in the same domain for augmentation. Inspired by domain generalization, we aim to further improve the transferability using the data augmented from different domains. Specifically, a style transfer network can alter the distribution of low-level visual features in an image while preserving semantic content for humans. Hence, we propose a novel attack method named Style Transfer Method (STM) that utilizes a proposed arbitrary style transfer network to transform the images into different domains. To avoid inconsistent semantic information of stylized images for the classification network, we fine-tune the style transfer network and mix up the generated images added by random noise with the original images to maintain semantic consistency and boost input diversity. Extensive experimental results on the ImageNet-compatible dataset show that our proposed method can significantly improve the adversarial transferability on either normally trained models or adversarially trained models than state-of-the-art input transformation-based attacks. Code is available at: https://github.com/Zhijin-Ge/STM.

Abstract: A number of computer vision deep regression approaches report improved results when adding a classification loss to the regression loss. Here, we explore why this is useful in practice and when it is beneficial. To do so, we start from precisely controlled dataset variations and data samplings and find that the effect of adding a classification loss is the most pronounced for regression with imbalanced data. We explain these empirical findings by formalizing the relation between the balanced and imbalanced regression losses. Finally, we show that our findings hold on two real imbalanced image datasets for depth estimation (NYUD2-DIR), and age estimation (IMDB-WIKI-DIR), and on the problem of imbalanced video progress prediction (Breakfast). Our main takeaway is: for a regression task, if the data sampling is imbalanced, then add a classification loss.

Abstract: Variations of target appearance such as deformations, illumination variance, occlusion, etc., are the major challenges of visual object tracking that negatively impact the performance of a tracker. An effective method to tackle these challenges is template update, which updates the template to reflect the change of appearance in the target object during tracking. However, with template updates, inadequate quality of new templates or inappropriate timing of updates may induce a model drift problem, which severely degrades the tracking performance. Here, we propose BackTrack, a robust and reliable method to quantify the confidence of the candidate template by backward tracking it on the past frames. Based on the confidence score of candidates from BackTrack, we can update the template with a reliable candidate at the right time while rejecting unreliable candidates. BackTrack is a generic template update scheme and is applicable to any template-based trackers. Extensive experiments on various tracking benchmarks verify the effectiveness of BackTrack over existing template update algorithms, as it achieves SOTA performance on various tracking benchmarks.

Abstract: While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation. In response, we introduce FocalDreamer, a framework that merges base shape with editable parts according to text prompts for fine-grained editing within desired regions. Specifically, equipped with geometry union and dual-path rendering, FocalDreamer assembles independent 3D parts into a complete object, tailored for convenient instance reuse and part-wise control. We propose geometric focal loss and style consistency regularization, which encourage focal fusion and congruent overall appearance. Furthermore, FocalDreamer generates high-fidelity geometry and PBR textures which are compatible with widely-used graphics engines. Extensive experiments have highlighted the superior editing capabilities of FocalDreamer in both quantitative and qualitative evaluations.

Abstract: Traditional ear disease diagnosis heavily depends on experienced specialists and specialized equipment, frequently resulting in misdiagnoses, treatment delays, and financial burdens for some patients. Utilizing deep learning models for efficient ear disease diagnosis has proven effective and affordable. However, existing research overlooked model inference speed and parameter size required for deployment. To tackle these challenges, we constructed a large-scale dataset comprising eight ear disease categories and normal ear canal samples from two hospitals. Inspired by ShuffleNetV2, we developed Best-EarNet, an ultrafast and ultralight network enabling real-time ear disease diagnosis. Best-EarNet incorporates the novel Local-Global Spatial Feature Fusion Module which can capture global and local spatial information simultaneously and guide the network to focus on crucial regions within feature maps at various levels, mitigating low accuracy issues. Moreover, our network uses multiple auxiliary classification heads for efficient parameter optimization. With 0.77M parameters, Best-EarNet achieves an average frames per second of 80 on CPU. Employing transfer learning and five-fold cross-validation with 22,581 images from Hospital-1, the model achieves an impressive 95.23% accuracy. External testing on 1,652 images from Hospital-2 validates its performance, yielding 92.14% accuracy. Compared to state-of-the-art networks, Best-EarNet establishes a new state-of-the-art (SOTA) in practical applications. Most importantly, we developed an intelligent diagnosis system called Ear Keeper, which can be deployed on common electronic devices. By manipulating a compact electronic otoscope, users can perform comprehensive scanning and diagnosis of the ear canal using real-time video. This study provides a novel paradigm for ear endoscopy and other medical endoscopic image recognition applications.

Abstract: This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition pipeline that enhances existing 3D perception and 6D object pose datasets. Our approach integrates robotic forward-kinematics, external infrared trackers, and improved calibration and annotation procedures. We present a multi-modal sensor rig, mounted on a robotic end-effector, and demonstrate how it is integrated into the creation of highly accurate datasets. Additionally, we introduce a freehand procedure for wider viewpoint coverage. Both approaches yield high-quality 3D data with accurate object and camera pose annotations. Our methods overcome the limitations of existing datasets and provide valuable resources for 3D vision research.

Abstract: The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting method for automatic person identification at a distance. In this work, we propose a novel gait recognition architecture called Gait Pyramid Transformer (GaitPT) that leverages pose estimation skeletons to capture unique walking patterns, without relying on appearance information. GaitPT adopts a hierarchical transformer architecture that effectively extracts both spatial and temporal features of movement in an anatomically consistent manner, guided by the structure of the human skeleton. Our results show that GaitPT achieves state-of-the-art performance compared to other skeleton-based gait recognition works, in both controlled and in-the-wild scenarios. GaitPT obtains 82.6% average accuracy on CASIA-B, surpassing other works by a margin of 6%. Moreover, it obtains 52.16% Rank-1 accuracy on GREW, outperforming both skeleton-based and appearance-based approaches.

Abstract: 6D pose estimation pipelines that rely on RGB-only or RGB-D data show limitations for photometrically challenging objects with e.g. textureless surfaces, reflections or transparency. A supervised learning-based method utilising complementary polarisation information as input modality is proposed to overcome such limitations. This supervised approach is then extended to a self-supervised paradigm by leveraging physical characteristics of polarised light, thus eliminating the need for annotated real data. The methods achieve significant advancements in pose estimation by leveraging geometric information from polarised light and incorporating shape priors and invertible physical constraints.

Abstract: Psychological trait estimation from external factors such as movement and appearance is a challenging and long-standing problem in psychology, and is principally based on the psychological theory of embodiment. To date, attempts to tackle this problem have utilized private small-scale datasets with intrusive body-attached sensors. Potential applications of an automated system for psychological trait estimation include estimation of occupational fatigue and psychology, and marketing and advertisement. In this work, we propose PsyMo (Psychological traits from Motion), a novel, multi-purpose and multi-modal dataset for exploring psychological cues manifested in walking patterns. We gathered walking sequences from 312 subjects in 7 different walking variations and 6 camera angles. In conjunction with walking sequences, participants filled in 6 psychological questionnaires, totalling 17 psychometric attributes related to personality, self-esteem, fatigue, aggressiveness and mental health. We propose two evaluation protocols for psychological trait estimation. Alongside the estimation of self-reported psychological traits from gait, the dataset can be used as a drop-in replacement to benchmark methods for gait recognition. We anonymize all cues related to the identity of the subjects and publicly release only silhouettes, 2D / 3D human skeletons and 3D SMPL human meshes.

Abstract: Machine learning has demonstrated remarkable performance over finite datasets, yet whether the scores over the fixed benchmarks can sufficiently indicate the model's performance in the real world is still in discussion. In reality, an ideal robust model will probably behave similarly to the oracle (e.g., the human users), thus a good evaluation protocol is probably to evaluate the models' behaviors in comparison to the oracle. In this paper, we introduce a new robustness measurement that directly measures the image classification model's performance compared with a surrogate oracle (i.e., a foundation model). Besides, we design a simple method that can accomplish the evaluation beyond the scope of the benchmarks. Our method extends the image datasets with new samples that are sufficiently perturbed to be distinct from the ones in the original sets, but are still bounded within the same image-label structure the original test image represents, constrained by a foundation model pretrained with a large amount of samples. As a result, our new method will offer us a new way to evaluate the models' robustness performance, free of limitations of fixed benchmarks or constrained perturbations, although scoped by the power of the oracle. In addition to the evaluation results, we also leverage our generated data to understand the behaviors of the model and our new evaluation strategies.

Abstract: We present SCULPT, a novel 3D generative model for clothed and textured 3D meshes of humans. Specifically, we devise a deep neural network that learns to represent the geometry and appearance distribution of clothed human bodies. Training such a model is challenging, as datasets of textured 3D meshes for humans are limited in size and accessibility. Our key observation is that there exist medium-sized 3D scan datasets like CAPE, as well as large-scale 2D image datasets of clothed humans and multiple appearances can be mapped to a single geometry. To effectively learn from the two data modalities, we propose an unpaired learning procedure for pose-dependent clothed and textured human meshes. Specifically, we learn a pose-dependent geometry space from 3D scan data. We represent this as per vertex displacements w.r.t. the SMPL model. Next, we train a geometry conditioned texture generator in an unsupervised way using the 2D image data. We use intermediate activations of the learned geometry model to condition our texture generator. To alleviate entanglement between pose and clothing type, and pose and clothing appearance, we condition both the texture and geometry generators with attribute labels such as clothing types for the geometry, and clothing colors for the texture generator. We automatically generated these conditioning labels for the 2D images based on the visual question answering model BLIP and CLIP. We validate our method on the SCULPT dataset, and compare to state-of-the-art 3D generative models for clothed human bodies. We will release the codebase for research purposes.

Abstract: Despite the existence of numerous Optical Character Recognition (OCR) tools, the lack of comprehensive open-source systems hampers the progress of document digitization in various low resource languages, including Bengali. Low-resource languages, especially those with an alphasyllabary writing system, suffer from the lack of large-scale datasets for various document OCR components such as word-level OCR, document layout extraction, and distortion correction; which are available as individual modules in high-resource languages. In this paper, we introduce Bengali.AI-BRACU-OCR (bbOCR): an open-source scalable document OCR system that can reconstruct Bengali documents into a structured searchable digitized format that leverages a novel Bengali text recognition model and two novel synthetic datasets. We present extensive component-level and system-level evaluation: both use a novel diversified evaluation dataset and comprehensive evaluation metrics. Our extensive evaluation suggests that our proposed solution is preferable over the current state-of-the-art Bengali OCR systems. The source codes and datasets are available here: https://bengaliai.github.io/bbocr.

Abstract: Motivated by the superior performance of image diffusion models, more and more researchers strive to extend these models to the text-based video editing task. Nevertheless, current video editing tasks mainly suffer from the dilemma between the high fine-tuning cost and the limited generation capacity. Compared with images, we conjecture that videos necessitate more constraints to preserve the temporal consistency during editing. Towards this end, we propose EVE, a robust and efficient zero-shot video editing method. Under the guidance of depth maps and temporal consistency constraints, EVE derives satisfactory video editing results with an affordable computational and time cost. Moreover, recognizing the absence of a publicly available video editing dataset for fair comparisons, we construct a new benchmark ZVE-50 dataset. Through comprehensive experimentation, we validate that EVE could achieve a satisfactory trade-off between performance and efficiency. We will release our dataset and codebase to facilitate future researchers.

Abstract: Long-Term Person Re-Identification (LT-ReID) has become increasingly crucial in computer vision and biometrics. In this work, we aim to extend LT-ReID beyond pedestrian recognition to include a wider range of real-world human activities while still accounting for cloth-changing scenarios over large time gaps. This setting poses additional challenges due to the geometric misalignment and appearance ambiguity caused by the diversity of human pose and clothing. To address these challenges, we propose a new approach 3DInvarReID for (i) disentangling identity from non-identity components (pose, clothing shape, and texture) of 3D clothed humans, and (ii) reconstructing accurate 3D clothed body shapes and learning discriminative features of naked body shapes for person ReID in a joint manner. To better evaluate our study of LT-ReID, we collect a real-world dataset called CCDA, which contains a wide variety of human activities and clothing changes. Experimentally, we show the superior performance of our approach for person ReID.

Abstract: Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep-learning approaches have made it possible to develop fully-automated vision-based crowd-monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state-of-the-art.

Abstract: Gestures are integral components of face-to-face communication. They unfold over time, often following predictable movement phases of preparation, stroke, and retraction. Yet, the prevalent approach to automatic gesture detection treats the problem as binary classification, classifying a segment as either containing a gesture or not, thus failing to capture its inherently sequential and contextual nature. To address this, we introduce a novel framework that reframes the task as a multi-phase sequence labeling problem rather than binary classification. Our model processes sequences of skeletal movements over time windows, uses Transformer encoders to learn contextual embeddings, and leverages Conditional Random Fields to perform sequence labeling. We evaluate our proposal on a large dataset of diverse co-speech gestures in task-oriented face-to-face dialogues. The results consistently demonstrate that our method significantly outperforms strong baseline models in detecting gesture strokes. Furthermore, applying Transformer encoders to learn contextual embeddings from movement sequences substantially improves gesture unit detection. These results highlight our framework's capacity to capture the fine-grained dynamics of co-speech gesture phases, paving the way for more nuanced and accurate gesture detection and analysis.

Abstract: Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior identity-relevant features and limited training samples. Existing methods mainly leverage auxiliary information to facilitate discriminative feature learning, including soft-biometrics features of shapes and gaits, and additional labels of clothing. However, these information may be unavailable in real-world applications. In this paper, we propose a novel FIne-grained Representation and Recomposition (FIRe$^{2}$) framework to tackle both limitations without any auxiliary information. Specifically, we first design a Fine-grained Feature Mining (FFM) module to separately cluster images of each person. Images with similar so-called fine-grained attributes (e.g., clothes and viewpoints) are encouraged to cluster together. An attribute-aware classification loss is introduced to perform fine-grained learning based on cluster labels, which are not shared among different people, promoting the model to learn identity-relevant features. Furthermore, by taking full advantage of the clustered fine-grained attributes, we present a Fine-grained Attribute Recomposition (FAR) module to recompose image features with different attributes in the latent space. It can significantly enhance representations for robust feature learning. Extensive experiments demonstrate that FIRe$^{2}$ can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks.

Abstract: We tackle the problem of estimating a Manhattan frame, i.e. three orthogonal vanishing points, and the unknown focal length of the camera, leveraging a prior vertical direction. The direction can come from an Inertial Measurement Unit that is a standard component of recent consumer devices, e.g., smartphones. We provide an exhaustive analysis of minimal line configurations and derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. Additionally, we design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization. Combining all solvers in a hybrid robust estimator, our method achieves increased accuracy even with a rough prior. Experiments on synthetic and real-world datasets demonstrate the superior accuracy of our method compared to the state of the art, while having comparable runtimes. We further demonstrate the applicability of our solvers for relative rotation estimation. The code is available at https://github.com/cvg/VP-Estimation-with-Prior-Gravity.

Abstract: Unsupervised domain adaptive person re-identification (Re-ID) methods alleviate the burden of data annotation through generating pseudo supervision messages. However, real-world Re-ID systems, with continuously accumulating data streams, simultaneously demand more robust adaptation and anti-forgetting capabilities. Methods based on image rehearsal addresses the forgetting issue with limited extra storage but carry the risk of privacy leakage. In this work, we propose a Color Prompting (CoP) method for data-free continual unsupervised domain adaptive person Re-ID. Specifically, we employ a light-weighted prompter network to fit the color distribution of the current task together with Re-ID training. Then for the incoming new tasks, the learned color distribution serves as color style transfer guidance to transfer the images into past styles. CoP achieves accurate color style recovery for past tasks with adequate data diversity, leading to superior anti-forgetting effects compared with image rehearsal methods. Moreover, CoP demonstrates strong generalization performance for fast adaptation into new domains, given only a small amount of unlabeled images. Extensive experiments demonstrate that after the continual training pipeline the proposed CoP achieves 6.7% and 8.1% average rank-1 improvements over the replay method on seen and unseen domains, respectively. The source code for this work is publicly available in https://github.com/vimar-gu/ColorPromptReID.

Abstract: Person Re-IDentification (Re-ID) as a retrieval task, has achieved tremendous development over the past decade. Existing state-of-the-art methods follow an analogous framework to first extract features from the input images and then categorize them with a classifier. However, since there is no identity overlap between training and testing sets, the classifier is often discarded during inference. Only the extracted features are used for person retrieval via distance metrics. In this paper, we rethink the role of the classifier in person Re-ID, and advocate a new perspective to conceive the classifier as a projection from image features to class prototypes. These prototypes are exactly the learned parameters of the classifier. In this light, we describe the identity of input images as similarities to all prototypes, which are then utilized as more discriminative features to perform person Re-ID. We thereby propose a new baseline ProNet, which innovatively reserves the function of the classifier at the inference stage. To facilitate the learning of class prototypes, both triplet loss and identity classification loss are applied to features that undergo the projection by the classifier. An improved version of ProNet++ is presented by further incorporating multi-granularity designs. Experiments on four benchmarks demonstrate that our proposed ProNet is simple yet effective, and significantly beats previous baselines. ProNet++ also achieves competitive or even better results than transformer-based competitors.

Abstract: Deep learning techniques depend on large datasets whose annotation is time-consuming. To reduce annotation burden, the self-training (ST) and active-learning (AL) methods have been developed as well as methods that combine them in an iterative fashion. However, it remains unclear when each method is the most useful, and when it is advantageous to combine them. In this paper, we propose a new method that combines ST with AL using Test-Time Augmentations (TTA). First, TTA is performed on an initial teacher network. Then, cases for annotation are selected based on the lowest estimated Dice score. Cases with high estimated scores are used as soft pseudo-labels for ST. The selected annotated cases are trained with existing annotated cases and ST cases with border slices annotations. We demonstrate the method on MRI fetal body and placenta segmentation tasks with different data variability characteristics. Our results indicate that ST is highly effective for both tasks, boosting performance for in-distribution (ID) and out-of-distribution (OOD) data. However, while self-training improved the performance of single-sequence fetal body segmentation when combined with AL, it slightly deteriorated performance of multi-sequence placenta segmentation on ID data. AL was helpful for the high variability placenta data, but did not improve upon random selection for the single-sequence body data. For fetal body segmentation sequence transfer, combining AL with ST following ST iteration yielded a Dice of 0.961 with only 6 original scans and 2 new sequence scans. Results using only 15 high-variability placenta cases were similar to those using 50 cases. Code is available at: https://github.com/Bella31/TTA-quality-estimation-ST-AL

Abstract: Vision Transformers have achieved great success in computer visions, delivering exceptional performance across various tasks. However, their inherent reliance on sequential input enforces the manual partitioning of images into patch sequences, which disrupts the image's inherent structural and semantic continuity. To handle this, we propose a novel Pattern Transformer (Patternformer) to adaptively convert images to pattern sequences for Transformer input. Specifically, we employ the Convolutional Neural Network to extract various patterns from the input image, with each channel representing a unique pattern that is fed into the succeeding Transformer as a visual token. By enabling the network to optimize these patterns, each pattern concentrates on its local region of interest, thereby preserving its intrinsic structural and semantic information. Only employing the vanilla ResNet and Transformer, we have accomplished state-of-the-art performance on CIFAR-10 and CIFAR-100, and have achieved competitive results on ImageNet.

Abstract: Deep neural networks are vulnerable to adversarial examples, posing a threat to the models' applications and raising security concerns. An intriguing property of adversarial examples is their strong transferability. Several methods have been proposed to enhance transferability, including ensemble attacks which have demonstrated their efficacy. However, prior approaches simply average logits, probabilities, or losses for model ensembling, lacking a comprehensive analysis of how and why model ensembling significantly improves transferability. In this paper, we propose a similar targeted attack method named Similar Target~(ST). By promoting cosine similarity between the gradients of each model, our method regularizes the optimization direction to simultaneously attack all surrogate models. This strategy has been proven to enhance generalization ability. Experimental results on ImageNet validate the effectiveness of our approach in improving adversarial transferability. Our method outperforms state-of-the-art attackers on 18 discriminative classifiers and adversarially trained models.

Abstract: Image classification is a longstanding problem in computer vision and machine learning research. Most recent works (e.g. SupCon , Triplet, and max-margin) mainly focus on grouping the intra-class samples aggressively and compactly, with the assumption that all intra-class samples should be pulled tightly towards their class centers. However, such an objective will be very hard to achieve since it ignores the intra-class variance in the dataset. (i.e. different instances from the same class can have significant differences). Thus, such a monotonous objective is not sufficient. To provide a more informative objective, we introduce Contrast Your Neighbours (CoNe) - a simple yet practical learning framework for supervised image classification. Specifically, in CoNe, each sample is not only supervised by its class center but also directly employs the features of its similar neighbors as anchors to generate more adaptive and refined targets. Moreover, to further boost the performance, we propose ``distributional consistency" as a more informative regularization to enable similar instances to have a similar probability distribution. Extensive experimental results demonstrate that CoNe achieves state-of-the-art performance across different benchmark datasets, network architectures, and settings. Notably, even without a complicated training recipe, our CoNe achieves 80.8\% Top-1 accuracy on ImageNet with ResNet-50, which surpasses the recent Timm training recipe (80.4\%). Code and pre-trained models are available at \href{https://github.com/mingkai-zheng/CoNe}{https://github.com/mingkai-zheng/CoNe}.

Abstract: Masked autoencoding has shown excellent performance on self-supervised video representation learning. Temporal redundancy has led to a high masking ratio and customized masking strategy in VideoMAE. In this paper, we aim to further improve the performance of video masked autoencoding by introducing a motion guided masking strategy. Our key insight is that motion is a general and unique prior in video, which should be taken into account during masked pre-training. Our motion guided masking explicitly incorporates motion information to build temporal consistent masking volume. Based on this masking volume, we can track the unmasked tokens in time and sample a set of temporal consistent cubes from videos. These temporal aligned unmasked tokens will further relieve the information leakage issue in time and encourage the MGMAE to learn more useful structure information. We implement our MGMAE with an online efficient optical flow estimator and backward masking map warping strategy. We perform experiments on the datasets of Something-Something V2 and Kinetics-400, demonstrating the superior performance of our MGMAE to the original VideoMAE. In addition, we provide the visualization analysis to illustrate that our MGMAE can sample temporal consistent cubes in a motion-adaptive manner for more effective video pre-training.

Abstract: This work dedicates to continuous sign language recognition (CSLR), which is a weakly supervised task dealing with the recognition of continuous signs from videos, without any prior knowledge about the temporal boundaries between consecutive signs. Data scarcity heavily impedes the progress of CSLR. Existing approaches typically train CSLR models on a monolingual corpus, which is orders of magnitude smaller than that of speech recognition. In this work, we explore the feasibility of utilizing multilingual sign language corpora to facilitate monolingual CSLR. Our work is built upon the observation of cross-lingual signs, which originate from different sign languages but have similar visual signals (e.g., hand shape and motion). The underlying idea of our approach is to identify the cross-lingual signs in one sign language and properly leverage them as auxiliary training data to improve the recognition capability of another. To achieve the goal, we first build two sign language dictionaries containing isolated signs that appear in two datasets. Then we identify the sign-to-sign mappings between two sign languages via a well-optimized isolated sign language recognition model. At last, we train a CSLR model on the combination of the target data with original labels and the auxiliary data with mapped labels. Experimentally, our approach achieves state-of-the-art performance on two widely-used CSLR datasets: Phoenix-2014 and Phoenix-2014T.

Abstract: Quantization scale and bit-width are the most important parameters when considering how to quantize a neural network. Prior work focuses on optimizing quantization scales in a global manner through gradient methods (gradient descent \& Hessian analysis). Yet, when applying perturbations to quantization scales, we observe a very jagged, highly non-smooth test loss landscape. In fact, small perturbations in quantization scale can greatly affect accuracy, yielding a $0.5-0.8\%$ accuracy boost in 4-bit quantized vision transformers (ViTs). In this regime, gradient methods break down, since they cannot reliably reach local minima. In our work, dubbed Evol-Q, we use evolutionary search to effectively traverse the non-smooth landscape. Additionally, we propose using an infoNCE loss, which not only helps combat overfitting on the small calibration dataset ($1,000$ images) but also makes traversing such a highly non-smooth surface easier. Evol-Q improves the top-1 accuracy of a fully quantized ViT-Base by $10.30\%$, $0.78\%$, and $0.15\%$ for $3$-bit, $4$-bit, and $8$-bit weight quantization levels. Extensive experiments on a variety of CNN and ViT architectures further demonstrate its robustness in extreme quantization scenarios. Our code is available at https://github.com/enyac-group/evol-q

Abstract: Hyperspectral Image (HSI) reconstruction has made gratifying progress with the deep unfolding framework by formulating the problem into a data module and a prior module. Nevertheless, existing methods still face the problem of insufficient matching with HSI data. The issues lie in three aspects: 1) fixed gradient descent step in the data module while the degradation of HSI is agnostic in the pixel-level. 2) inadequate prior module for 3D HSI cube. 3) stage interaction ignoring the differences in features at different stages. To address these issues, in this work, we propose a Pixel Adaptive Deep Unfolding Transformer (PADUT) for HSI reconstruction. In the data module, a pixel adaptive descent step is employed to focus on pixel-level agnostic degradation. In the prior module, we introduce the Non-local Spectral Transformer (NST) to emphasize the 3D characteristics of HSI for recovering. Moreover, inspired by the diverse expression of features in different stages and depths, the stage interaction is improved by the Fast Fourier Transform (FFT). Experimental results on both simulated and real scenes exhibit the superior performance of our method compared to state-of-the-art HSI reconstruction methods. The code is released at: https://github.com/MyuLi/PADUT.

Abstract: Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a large database of geotagged photos, using learned global descriptors. A major challenge in this task is recognizing places seen from different viewpoints. To overcome this limitation, we propose a new method, called EigenPlaces, to train our neural network on images from different point of views, which embeds viewpoint robustness into the learned global descriptors. The underlying idea is to cluster the training data so as to explicitly present the model with different views of the same points of interest. The selection of this points of interest is done without the need for extra supervision. We then present experiments on the most comprehensive set of datasets in literature, finding that EigenPlaces is able to outperform previous state of the art on the majority of datasets, while requiring 60\% less GPU memory for training and using 50\% smaller descriptors. The code and trained models for EigenPlaces are available at {\small{\url{https://github.com/gmberton/EigenPlaces}}}, while results with any other baseline can be computed with the codebase at {\small{\url{https://github.com/gmberton/auto_VPR}}}.

Abstract: This is a further development of Vision Transformer Pruning via matrix decomposition. The purpose of the Vision Transformer Pruning is to prune the dimension of the linear projection of the dataset by learning their associated importance score in order to reduce the storage, run-time memory, and computational demands. In this paper we further reduce dimension and complexity of the linear projection by implementing and comparing several matrix decomposition methods while preserving the generated important features. We end up selected the Singular Value Decomposition as the method to achieve our goal by comparing the original accuracy scores in the original Github repository and the accuracy scores of using those matrix decomposition methods, including Singular Value Decomposition, four versions of QR Decomposition, and LU factorization.

Abstract: We present a framework for generating appropriate facial responses from a listener in dyadic social interactions based on the speaker's words. Given an input transcription of the speaker's words with their timestamps, our approach autoregressively predicts a response of a listener: a sequence of listener facial gestures, quantized using a VQ-VAE. Since gesture is a language component, we propose treating the quantized atomic motion elements as additional language token inputs to a transformer-based large language model. Initializing our transformer with the weights of a language model pre-trained only on text results in significantly higher quality listener responses than training a transformer from scratch. We show that our generated listener motion is fluent and reflective of language semantics through quantitative metrics and a qualitative user study. In our evaluation, we analyze the model's ability to utilize temporal and semantic aspects of spoken text. Project page: https://people.eecs.berkeley.edu/~evonne_ng/projects/text2listen/

Abstract: We study the problem of few-shot physically-aware articulated mesh generation. By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity. Previous mesh generative models either have difficulties in depicting a diverse data space from only a few examples or fail to ensure physical validity of their samples. Regarding the above challenges, we propose two key innovations, including 1) a hierarchical mesh deformation-based generative model based upon the divide-and-conquer philosophy to alleviate the few-shot challenge by borrowing transferrable deformation patterns from large scale rigid meshes and 2) a physics-aware deformation correction scheme to encourage physically plausible generations. We conduct extensive experiments on 6 articulated categories to demonstrate the superiority of our method in generating articulated meshes with better diversity, higher visual fidelity, and better physical validity over previous methods in the few-shot setting. Further, we validate solid contributions of our two innovations in the ablation study. Project page with code is available at https://meowuu7.github.io/few-arti-obj-gen.

Abstract: Neural Radiance Fields (NeRF) can be optimized to obtain high-fidelity 3D scene reconstructions of objects and large-scale scenes. However, NeRFs require accurate camera parameters as input -- inaccurate camera parameters result in blurry renderings. Extrinsic and intrinsic camera parameters are usually estimated using Structure-from-Motion (SfM) methods as a pre-processing step to NeRF, but these techniques rarely yield perfect estimates. Thus, prior works have proposed jointly optimizing camera parameters alongside a NeRF, but these methods are prone to local minima in challenging settings. In this work, we analyze how different camera parameterizations affect this joint optimization problem, and observe that standard parameterizations exhibit large differences in magnitude with respect to small perturbations, which can lead to an ill-conditioned optimization problem. We propose using a proxy problem to compute a whitening transform that eliminates the correlation between camera parameters and normalizes their effects, and we propose to use this transform as a preconditioner for the camera parameters during joint optimization. Our preconditioned camera optimization significantly improves reconstruction quality on scenes from the Mip-NeRF 360 dataset: we reduce error rates (RMSE) by 67% compared to state-of-the-art NeRF approaches that do not optimize for cameras like Zip-NeRF, and by 29% relative to state-of-the-art joint optimization approaches using the camera parameterization of SCNeRF. Our approach is easy to implement, does not significantly increase runtime, can be applied to a wide variety of camera parameterizations, and can straightforwardly be incorporated into other NeRF-like models.