Computer Vision and Pattern Recognition (cs.CV)

Abstract: Text segmentation tasks have a very wide range of application values, such as image editing, style transfer, watermark removal, etc.However, existing public datasets are of poor quality of pixel-level labels that have been shown to be notoriously costly to acquire, both in terms of money and time. At the same time, when pretraining is performed on synthetic datasets, the data distribution of the synthetic datasets is far from the data distribution in the real scene. These all pose a huge challenge to the current pixel-level text segmentation algorithms.To alleviate the above problems, we propose a self-supervised scene text segmentation algorithm with layered decoupling of representations derived from the object-centric manner to segment images into texts and background. In our method, we propose two novel designs which include Region Query Module and Representation Consistency Constraints adapting to the unique properties of text as complements to Auto Encoder, which improves the network's sensitivity to texts.For this unique design, we treat the polygon-level masks predicted by the text localization model as extra input information, and neither utilize any pixel-level mask annotations for training stage nor pretrain on synthetic datasets.Extensive experiments show the effectiveness of the method proposed. On several public scene text datasets, our method outperforms the state-of-the-art unsupervised segmentation algorithms.

Abstract: With the advent of digital scanners and deep learning, diagnostic operations may move from a microscope to a desktop. Hematoxylin and Eosin (H&E) staining is one of the most frequently used stains for disease analysis, diagnosis, and grading, but pathologists do need different immunohistochemical (IHC) stains to analyze specific structures or cells. Obtaining all of these stains (H&E and different IHCs) on a single specimen is a tedious and time-consuming task. Consequently, virtual staining has emerged as an essential research direction. Here, we propose a novel generative model, Structural Cycle-GAN (SC-GAN), for synthesizing IHC stains from H&E images, and vice versa. Our method expressly incorporates structural information in the form of edges (in addition to color data) and employs attention modules exclusively in the decoder of the proposed generator model. This integration enhances feature localization and preserves contextual information during the generation process. In addition, a structural loss is incorporated to ensure accurate structure alignment between the generated and input markers. To demonstrate the efficacy of the proposed model, experiments are conducted with two IHC markers emphasizing distinct structures of glands in the colon: the nucleus of epithelial cells (CDX2) and the cytoplasm (CK818). Quantitative metrics such as FID and SSIM are frequently used for the analysis of generative models, but they do not correlate explicitly with higher-quality virtual staining results. Therefore, we propose two new quantitative metrics that correlate directly with the virtual staining specificity of IHC markers.

Abstract: This paper introduces a novel benchmark to study the impact and relationship of built environment elements on pedestrian collision prediction, intending to enhance environmental awareness in autonomous driving systems to prevent pedestrian injuries actively. We introduce a built environment detection task in large-scale panoramic images and a detection-based pedestrian collision frequency prediction task. We propose a baseline method that incorporates a collision prediction module into a state-of-the-art detection model to tackle both tasks simultaneously. Our experiments demonstrate a significant correlation between object detection of built environment elements and pedestrian collision frequency prediction. Our results are a stepping stone towards understanding the interdependencies between built environment conditions and pedestrian safety.

Abstract: Hotspot detection using thermal imaging has recently become essential in several industrial applications, such as security applications, health applications, and equipment monitoring applications. Hotspot detection is of utmost importance in industrial safety where equipment can develop anomalies. Hotspots are early indicators of such anomalies. We address the problem of hotspot detection in thermal images by proposing a self-supervised learning approach. Self-supervised learning has shown potential as a competitive alternative to their supervised learning counterparts but their application to thermography has been limited. This has been due to lack of diverse data availability, domain specific pre-trained models, standardized benchmarks, etc. We propose a self-supervised representation learning approach followed by fine-tuning that improves detection of hotspots by classification. The SimSiam network based ensemble classifier decides whether an image contains hotspots or not. Detection of hotspots is followed by precise hotspot isolation. By doing so, we are able to provide a highly accurate and precise hotspot identification, applicable to a wide range of applications. We created a novel large thermal image dataset to address the issue of paucity of easily accessible thermal images. Our experiments with the dataset created by us and a publicly available segmentation dataset show the potential of our approach for hotspot detection and its ability to isolate hotspots with high accuracy. We achieve a Dice Coefficient of 0.736, the highest when compared with existing hotspot identification techniques. Our experiments also show self-supervised learning as a strong contender of supervised learning, providing competitive metrics for hotspot detection, with the highest accuracy of our approach being 97%.

Abstract: Echocardiography (echo) is an ultrasound imaging modality that is widely used for various cardiovascular diagnosis tasks. Due to inter-observer variability in echo-based diagnosis, which arises from the variability in echo image acquisition and the interpretation of echo images based on clinical experience, vision-based machine learning (ML) methods have gained popularity to act as secondary layers of verification. For such safety-critical applications, it is essential for any proposed ML method to present a level of explainability along with good accuracy. In addition, such methods must be able to process several echo videos obtained from various heart views and the interactions among them to properly produce predictions for a variety of cardiovascular measurements or interpretation tasks. Prior work lacks explainability or is limited in scope by focusing on a single cardiovascular task. To remedy this, we propose a General, Echo-based, Multi-Level Transformer (GEMTrans) framework that provides explainability, while simultaneously enabling multi-video training where the inter-play among echo image patches in the same frame, all frames in the same video, and inter-video relationships are captured based on a downstream task. We show the flexibility of our framework by considering two critical tasks including ejection fraction (EF) and aortic stenosis (AS) severity detection. Our model achieves mean absolute errors of 4.15 and 4.84 for single and dual-video EF estimation and an accuracy of 96.5 % for AS detection, while providing informative task-specific attention maps and prototypical explainability.

Abstract: Supervised visual captioning models typically require a large scale of images or videos paired with descriptions in a specific language (i.e., the vision-caption pairs) for training. However, collecting and labeling large-scale datasets is time-consuming and expensive for many scenarios and languages. Therefore, sufficient labeled pairs are usually not available. To deal with the label shortage problem, we present a simple yet effective zero-shot approach MultiCapCLIP that can generate visual captions for different scenarios and languages without any labeled vision-caption pairs of downstream datasets. In the training stage, MultiCapCLIP only requires text data for input. Then it conducts two main steps: 1) retrieving concept prompts that preserve the corresponding domain knowledge of new scenarios; 2) auto-encoding the prompts to learn writing styles to output captions in a desired language. In the testing stage, MultiCapCLIP instead takes visual data as input directly to retrieve the concept prompts to generate the final visual descriptions. The extensive experiments on image and video captioning across four benchmarks and four languages (i.e., English, Chinese, German, and French) confirm the effectiveness of our approach. Compared with state-of-the-art zero-shot and weakly-supervised methods, our method achieves 4.8% and 21.5% absolute improvements in terms of BLEU@4 and CIDEr metrics. Our code is available at https://github.com/yangbang18/MultiCapCLIP.

Abstract: While the image diffusion model has made significant strides in text-driven 3D content creation, it often falls short in accurately capturing the intended meaning of the text prompt, particularly with respect to direction information. This shortcoming gives rise to the Janus problem, where multi-faced 3D models are produced with the guidance of such diffusion models. In this paper, we present a robust pipeline for generating high-fidelity 3D content with orthogonal-view image guidance. Specifically, we introduce a novel 2D diffusion model that generates an image consisting of four orthogonal-view sub-images for the given text prompt. The 3D content is then created with this diffusion model, which enhances 3D consistency and provides strong structured semantic priors. This addresses the infamous Janus problem and significantly promotes generation efficiency. Additionally, we employ a progressive 3D synthesis strategy that results in substantial improvement in the quality of the created 3D contents. Both quantitative and qualitative evaluations show that our method demonstrates a significant improvement over previous text-to-3D techniques.

Abstract: Unsupervised methods for reconstructing structures face significant challenges in capturing the geometric details with consistent structures among diverse shapes of the same category. To address this issue, we present a novel unsupervised structural reconstruction method, named DPF-Net, based on a new Deformable Primitive Field (DPF) representation, which allows for high-quality shape reconstruction using parameterized geometric primitives. We design a two-stage shape reconstruction pipeline which consists of a primitive generation module and a primitive deformation module to approximate the target shape of each part progressively. The primitive generation module estimates the explicit orientation, position, and size parameters of parameterized geometric primitives, while the primitive deformation module predicts a dense deformation field based on a parameterized primitive field to recover shape details. The strong shape prior encoded in parameterized geometric primitives enables our DPF-Net to extract high-level structures and recover fine-grained shape details consistently. The experimental results on three categories of objects in diverse shapes demonstrate the effectiveness and generalization ability of our DPF-Net on structural reconstruction and shape segmentation.

Abstract: Multi-Camera Multi-Object Tracking (MC-MOT) utilizes information from multiple views to better handle problems with occlusion and crowded scenes. Recently, the use of graph-based approaches to solve tracking problems has become very popular. However, many current graph-based methods do not effectively utilize information regarding spatial and temporal consistency. Instead, they rely on single-camera trackers as input, which are prone to fragmentation and ID switch errors. In this paper, we propose a novel reconfigurable graph model that first associates all detected objects across cameras spatially before reconfiguring it into a temporal graph for Temporal Association. This two-stage association approach enables us to extract robust spatial and temporal-aware features and address the problem with fragmented tracklets. Furthermore, our model is designed for online tracking, making it suitable for real-world applications. Experimental results show that the proposed graph model is able to extract more discriminating features for object tracking, and our model achieves state-of-the-art performance on several public datasets.

Abstract: Black-box unsupervised domain adaptation (UDA) learns with source predictions of target data without accessing either source data or source models during training, and it has clear superiority in data privacy and flexibility in target network selection. However, the source predictions of target data are often noisy and training with them is prone to learning collapses. We propose BiMem, a bi-directional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly, leading to robust black-box UDA that can generalize across different visual recognition tasks. BiMem constructs three types of memory, including sensory memory, short-term memory, and long-term memory, which interact in a bi-directional manner for comprehensive and robust memorization of learnt features. It includes a forward memorization flow that identifies and stores useful features and a backward calibration flow that rectifies features' pseudo labels progressively. Extensive experiments show that BiMem achieves superior domain adaptation performance consistently across various visual recognition tasks such as image classification, semantic segmentation and object detection.

Abstract: While impressive progress has recently been made in image-oriented facial attribute translation, shape-oriented 3D facial attribute translation remains an unsolved issue. This is primarily limited by the lack of 3D generative models and ineffective usage of 3D facial data. We propose a learning framework for 3D facial attribute translation to relieve these limitations. Firstly, we customize a novel geometric map for 3D shape representation and embed it in an end-to-end generative adversarial network. The geometric map represents 3D shapes symmetrically on a square image grid, while preserving the neighboring relationship of 3D vertices in a local least-square sense. This enables effective learning for the latent representation of data with different attributes. Secondly, we employ a unified and unpaired learning framework for multi-domain attribute translation. It not only makes effective usage of data correlation from multiple domains, but also mitigates the constraint for hardly accessible paired data. Finally, we propose a hierarchical architecture for the discriminator to guarantee robust results against both global and local artifacts. We conduct extensive experiments to demonstrate the advantage of the proposed framework over the state-of-the-art in generating high-fidelity facial shapes. Given an input 3D facial shape, the proposed framework is able to synthesize novel shapes of different attributes, which covers some downstream applications, such as expression transfer, gender translation, and aging. Code at https://github.com/NaughtyZZ/3D_facial_shape_attribute_translation_ssgmap.

Abstract: Tracking any given object(s) spatially and temporally is a common purpose in Visual Object Tracking (VOT) and Video Object Segmentation (VOS). Joint tracking and segmentation have been attempted in some studies but they often lack full compatibility of both box and mask in initialization and prediction, and mainly focus on single-object scenarios. To address these limitations, this paper proposes a Multi-object Mask-box Integrated framework for unified Tracking and Segmentation, dubbed MITS. Firstly, the unified identification module is proposed to support both box and mask reference for initialization, where detailed object information is inferred from boxes or directly retained from masks. Additionally, a novel pinpoint box predictor is proposed for accurate multi-object box prediction, facilitating target-oriented representation learning. All target objects are processed simultaneously from encoding to propagation and decoding, as a unified pipeline for VOT and VOS. Experimental results show MITS achieves state-of-the-art performance on both VOT and VOS benchmarks. Notably, MITS surpasses the best prior VOT competitor by around 6% on the GOT-10k test set, and significantly improves the performance of box initialization on VOS benchmarks. The code is available at https://github.com/yoxu515/MITS.

Abstract: Bundle adjustment is the common way to solve localization and mapping. It is an iterative process in which a system of non-linear equations is solved using two optimization methods, weighted by a damping factor. In the classic approach, the latter is chosen heuristically by the Levenberg-Marquardt algorithm on each iteration. This might take many iterations, making the process computationally expensive, which might be harmful to real-time applications. We propose to replace this heuristic by viewing the problem in a holistic manner, as a game, and formulating it as a reinforcement-learning task. We set an environment which solves the non-linear equations and train an agent to choose the damping factor in a learned manner. We demonstrate that our approach considerably reduces the number of iterations required to reach the bundle adjustment's convergence, on both synthetic and real-life scenarios. We show that this reduction benefits the classic approach and can be integrated with other bundle adjustment acceleration methods.

Abstract: The 2D animation workflow is typically initiated with the creation of keyframes using sketch-based drawing. Subsequent inbetweens (i.e., intermediate sketch frames) are crafted through manual interpolation for smooth animations, which is a labor-intensive process. Thus, the prospect of automatic animation sketch interpolation has become highly appealing. However, existing video interpolation methods are generally hindered by two key issues for sketch inbetweening: 1) limited texture and colour details in sketches, and 2) exaggerated alterations between two sketch keyframes. To overcome these issues, we propose a novel deep learning method, namely Fine-to-Coarse Sketch Interpolation Network (FC-SIN). This approach incorporates multi-level guidance that formulates region-level correspondence, sketch-level correspondence and pixel-level dynamics. A multi-stream U-Transformer is then devised to characterize sketch inbewteening patterns using these multi-level guides through the integration of both self-attention and cross-attention mechanisms. Additionally, to facilitate future research on animation sketch inbetweening, we constructed a large-scale dataset - STD-12K, comprising 30 sketch animation series in diverse artistic styles. Comprehensive experiments on this dataset convincingly show that our proposed FC-SIN surpasses the state-of-the-art interpolation methods. Our code and dataset will be publicly available.

Abstract: Recently, anatomical landmark detection has achieved great progresses on single-domain data, which usually assumes training and test sets are from the same domain. However, such an assumption is not always true in practice, which can cause significant performance drop due to domain shift. To tackle this problem, we propose a novel framework for anatomical landmark detection under the setting of unsupervised domain adaptation (UDA), which aims to transfer the knowledge from labeled source domain to unlabeled target domain. The framework leverages self-training and domain adversarial learning to address the domain gap during adaptation. Specifically, a self-training strategy is proposed to select reliable landmark-level pseudo-labels of target domain data with dynamic thresholds, which makes the adaptation more effective. Furthermore, a domain adversarial learning module is designed to handle the unaligned data distributions of two domains by learning domain-invariant features via adversarial training. Our experiments on cephalometric and lung landmark detection show the effectiveness of the method, which reduces the domain gap by a large margin and outperforms other UDA methods consistently. The code is available at https://github.com/jhb86253817/UDA_Med_Landmark.

Abstract: The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available.

Abstract: LiDAR-based semantic perception tasks are critical yet challenging for autonomous driving. Due to the motion of objects and static/dynamic occlusion, temporal information plays an essential role in reinforcing perception by enhancing and completing single-frame knowledge. Previous approaches either directly stack historical frames to the current frame or build a 4D spatio-temporal neighborhood using KNN, which duplicates computation and hinders realtime performance. Based on our observation that stacking all the historical points would damage performance due to a large amount of redundant and misleading information, we propose the Sparse Voxel-Adjacent Query Network (SVQNet) for 4D LiDAR semantic segmentation. To take full advantage of the historical frames high-efficiently, we shunt the historical points into two groups with reference to the current points. One is the Voxel-Adjacent Neighborhood carrying local enhancing knowledge. The other is the Historical Context completing the global knowledge. Then we propose new modules to select and extract the instructive features from the two groups. Our SVQNet achieves state-of-the-art performance in LiDAR semantic segmentation of the SemanticKITTI benchmark and the nuScenes dataset.

Abstract: Whole slide image (WSI) analysis has become increasingly important in the medical imaging community, enabling automated and objective diagnosis, prognosis, and therapeutic-response prediction. However, in clinical practice, the ever-evolving environment hamper the utility of WSI analysis models. In this paper, we propose the FIRST continual learning framework for WSI analysis, named ConSlide, to tackle the challenges of enormous image size, utilization of hierarchical structure, and catastrophic forgetting by progressive model updating on multiple sequential datasets. Our framework contains three key components. The Hierarchical Interaction Transformer (HIT) is proposed to model and utilize the hierarchical structural knowledge of WSI. The Breakup-Reorganize (BuRo) rehearsal method is developed for WSI data replay with efficient region storing buffer and WSI reorganizing operation. The asynchronous updating mechanism is devised to encourage the network to learn generic and specific knowledge respectively during the replay stage, based on a nested cross-scale similarity learning (CSSL) module. We evaluated the proposed ConSlide on four public WSI datasets from TCGA projects. It performs best over other state-of-the-art methods with a fair WSI-based continual learning setting and achieves a better trade-off of the overall performance and forgetting on previous task

Abstract: The ability of humans to infer head poses from face shapes, and vice versa, indicates a strong correlation between the two. Accordingly, recent studies on face alignment have employed head pose information to predict facial landmarks in computer vision tasks. In this study, we propose a novel method that employs head pose information to improve face alignment performance by fusing said information with the feature maps of a face alignment network, rather than simply using it to initialize facial landmarks. Furthermore, the proposed network structure performs robust face alignment through a dual-dimensional network using multidimensional features represented by 2D feature maps and a 3D heatmap. For effective dense face alignment, we also propose a prediction method for facial geometric landmarks through training based on knowledge distillation using predicted keypoints. We experimentally assessed the correlation between the predicted facial landmarks and head pose information, as well as variations in the accuracy of facial landmarks with respect to the quality of head pose information. In addition, we demonstrated the effectiveness of the proposed method through a competitive performance comparison with state-of-the-art methods on the AFLW2000-3D, AFLW, and BIWI datasets.

Abstract: The task of semantic segmentation requires a model to assign semantic labels to each pixel of an image. However, the performance of such models degrades when deployed in an unseen domain with different data distributions compared to the training domain. We present a new augmentation-driven approach to domain generalization for semantic segmentation using a re-parameterized vision transformer (ReVT) with weight averaging of multiple models after training. We evaluate our approach on several benchmark datasets and achieve state-of-the-art mIoU performance of 47.3% (prior art: 46.3%) for small models and of 50.1% (prior art: 47.8%) for midsized models on commonly used benchmark datasets. At the same time, our method requires fewer parameters and reaches a higher frame rate than the best prior art. It is also easy to implement and, unlike network ensembles, does not add any computational complexity during inference.

Abstract: Gait recognition is a promising biometric technology for identification due to its non-invasiveness and long-distance. However, external variations such as clothing changes and viewpoint differences pose significant challenges to gait recognition. Silhouette-based methods preserve body shape but neglect internal structure information, while skeleton-based methods preserve structure information but omit appearance. To fully exploit the complementary nature of the two modalities, a novel triple branch gait recognition framework, TriGait, is proposed in this paper. It effectively integrates features from the skeleton and silhouette data in a hybrid fusion manner, including a two-stream network to extract static and motion features from appearance, a simple yet effective module named JSA-TC to capture dependencies between all joints, and a third branch for cross-modal learning by aligning and fusing low-level features of two modalities. Experimental results demonstrate the superiority and effectiveness of TriGait for gait recognition. The proposed method achieves a mean rank-1 accuracy of 96.0% over all conditions on CASIA-B dataset and 94.3% accuracy for CL, significantly outperforming all the state-of-the-art methods. The source code will be available at https://github.com/feng-xueling/TriGait/.

Abstract: Convolutional neural networks have spatial representations which read patterns in the vision tasks. Squeeze and excitation links the channel wise representations by explicitly modeling on channel level. Multi layer perceptrons learn global representations and in most of the models it is used often at the end after all convolutional layers to gather all the information learned before classification. We propose a method of inducing the global representations within channels to have better performance of the model. We propose SaEnet, Squeeze aggregated excitation network, for learning global channelwise representation in between layers. The proposed module takes advantage of passing important information after squeeze by having aggregated excitation before regaining its shape. We also introduce a new idea of having a multibranch linear(dense) layer in the network. This learns global representations from the condensed information which enhances the representational power of the network. The proposed module have undergone extensive experiments by using Imagenet and CIFAR100 datasets and compared with closely related architectures. The analyzes results that proposed models outputs are comparable and in some cases better than existing state of the art architectures.

Abstract: Despite their simpler information fusion designs compared with Vision Transformers and Convolutional Neural Networks, Vision MLP architectures have demonstrated strong performance and high data efficiency in recent research. However, existing works such as CycleMLP and Vision Permutator typically model spatial information in equal-size spatial regions and do not consider cross-scale spatial interactions. Further, their token mixers only model 1- or 2-axis correlations, avoiding 3-axis spatial-channel mixing due to its computational demands. We therefore propose CS-Mixer, a hierarchical Vision MLP that learns dynamic low-rank transformations for spatial-channel mixing through cross-scale local and global aggregation. The proposed methodology achieves competitive results on popular image recognition benchmarks without incurring substantially more compute. Our largest model, CS-Mixer-L, reaches 83.2% top-1 accuracy on ImageNet-1k with 13.7 GFLOPs and 94 M parameters.

Abstract: Wildfire detection using satellite images is a widely studied task in remote sensing with many applications to fire delineation and mapping. Recently, deep learning methods have become a scalable solution to automate this task, especially in the field of unsupervised learning where no training data is available. This is particularly important in the context of emergency risk monitoring where fast and effective detection is needed, generally based on high-resolution satellite data. Among various approaches, Anomaly Detection (AD) appears to be highly potential thanks to its broad applications in computer vision, medical imaging, as well as remote sensing. In this work, we build upon the framework of Vector Quantized Variational Autoencoder (VQ-VAE), a popular reconstruction-based AD method with discrete latent spaces, to perform unsupervised burnt area extraction. We integrate VQ-VAE into an end-to-end framework with an intensive post-processing step using dedicated vegetation, water and brightness indexes. Our experiments conducted on high-resolution SPOT-6/7 images provide promising results of the proposed technique, showing its high potential in future research on unsupervised burnt area extraction.

Abstract: Recovering a 3D human mesh from a single RGB image is a challenging task due to depth ambiguity and self-occlusion, resulting in a high degree of uncertainty. Meanwhile, diffusion models have recently seen much success in generating high-quality outputs by progressively denoising noisy inputs. Inspired by their capability, we explore a diffusion-based approach for human mesh recovery, and propose a Human Mesh Diffusion (HMDiff) framework which frames mesh recovery as a reverse diffusion process. We also propose a Distribution Alignment Technique (DAT) that injects input-specific distribution information into the diffusion process, and provides useful prior knowledge to simplify the mesh recovery task. Our method achieves state-of-the-art performance on three widely used datasets. Project page: https://gongjia0208.github.io/HMDiff/.

Abstract: PURPOSE: Subarachnoid hemorrhage (SAH) entails high morbidity and mortality rates. Convolutional neural networks (CNN), a form of deep learning, are capable of generating highly accurate predictions from imaging data. Our objective was to predict mortality in SAH patients by processing the initial CT scan on a CNN based algorithm. METHODS: Retrospective multicentric study of a consecutive cohort of patients with SAH between 2011-2022. Demographic, clinical and radiological variables were analyzed. Pre-processed baseline CT scan images were used as the input for training a CNN using AUCMEDI Framework. Our model's architecture leverages the DenseNet-121 structure, employing transfer learning principles. The output variable was mortality in the first three months. Performance of the model was evaluated by statistical parameters conventionally used in studies involving artificial intelligence methods. RESULTS: Images from 219 patients were processed, 175 for training and validation of the CNN and 44 for its evaluation. 52%(115/219) of patients were female, and the median age was 58(SD=13.06) years. 18.5%(39/219) were idiopathic SAH. Mortality rate was 28.5%(63/219). The model showed good accuracy at predicting mortality in SAH patients exclusively using the images of the initial CT scan (Accuracy=74%, F1=75% and AUC=82%). CONCLUSION: Modern image processing techniques based on AI and CNN make possible to predict mortality in SAH patients with high accuracy using CT scan images as the only input. These models might be optimized by including more data and patients resulting in better training, development and performance on tasks which are beyond the skills of conventional clinical knowledge.

Abstract: This paper presents a novel visual-language model called DFER-CLIP, which is based on the CLIP model and designed for in-the-wild Dynamic Facial Expression Recognition (DFER). Specifically, the proposed DFER-CLIP consists of a visual part and a textual part. For the visual part, based on the CLIP image encoder, a temporal model consisting of several Transformer encoders is introduced for extracting temporal facial expression features, and the final feature embedding is obtained as a learnable "class" token. For the textual part, we use as inputs textual descriptions of the facial behaviour that is related to the classes (facial expressions) that we are interested in recognising -- those descriptions are generated using large language models, like ChatGPT. This, in contrast to works that use only the class names and more accurately captures the relationship between them. Alongside the textual description, we introduce a learnable token which helps the model learn relevant context information for each expression during training. Extensive experiments demonstrate the effectiveness of the proposed method and show that our DFER-CLIP also achieves state-of-the-art results compared with the current supervised DFER methods on the DFEW, FERV39k, and MAFW benchmarks. Code is publicly available at https://github.com/zengqunzhao/DFER-CLIP.

Abstract: Moire patterns occur when capturing images or videos on screens, severely degrading the quality of the captured images or videos. Despite the recent progresses, existing video demoireing methods neglect the physical characteristics and formation process of moire patterns, significantly limiting the effectiveness of video recovery. This paper presents a unified framework, DTNet, a direction-aware and temporal-guided bilateral learning network for video demoireing. DTNet effectively incorporates the process of moire pattern removal, alignment, color correction, and detail refinement. Our proposed DTNet comprises two primary stages: Frame-level Direction-aware Demoireing and Alignment (FDDA) and Tone and Detail Refinement (TDR). In FDDA, we employ multiple directional DCT modes to perform the moire pattern removal process in the frequency domain, effectively detecting the prominent moire edges. Then, the coarse and fine-grained alignment is applied on the demoired features for facilitating the utilization of neighboring information. In TDR, we propose a temporal-guided bilateral learning pipeline to mitigate the degradation of color and details caused by the moire patterns while preserving the restored frequency information in FDDA. Guided by the aligned temporal features from FDDA, the affine transformations for the recovery of the ultimate clean frames are learned in TDR. Extensive experiments demonstrate that our video demoireing method outperforms state-of-the-art approaches by 2.3 dB in PSNR, and also delivers a superior visual experience.

Abstract: Whilst contrastive learning yields powerful representations by matching different augmented views of the same instance, it lacks the ability to capture the similarities between different instances. One popular way to address this limitation is by learning global features (after the global pooling) to capture inter-instance relationships based on knowledge distillation, where the global features of the teacher are used to guide the learning of the global features of the student. Inspired by cross-modality learning, we extend this existing framework that only learns from global features by encouraging the global features and intermediate layer features to learn from each other. This leads to our novel self-supervised framework: cross-context learning between global and hypercolumn features (CGH), that enforces the consistency of instance relations between low- and high-level semantics. Specifically, we stack the intermediate feature maps to construct a hypercolumn representation so that we can measure instance relations using two contexts (hypercolumn and global feature) separately, and then use the relations of one context to guide the learning of the other. This cross-context learning allows the model to learn from the differences between the two contexts. The experimental results on linear classification and downstream tasks show that our method outperforms the state-of-the-art methods.

Abstract: This paper presents a novel neural implicit radiance representation for free viewpoint relighting from a small set of unstructured photographs of an object lit by a moving point light source different from the view position. We express the shape as a signed distance function modeled by a multi layer perceptron. In contrast to prior relightable implicit neural representations, we do not disentangle the different reflectance components, but model both the local and global reflectance at each point by a second multi layer perceptron that, in addition, to density features, the current position, the normal (from the signed distace function), view direction, and light position, also takes shadow and highlight hints to aid the network in modeling the corresponding high frequency light transport effects. These hints are provided as a suggestion, and we leave it up to the network to decide how to incorporate these in the final relit result. We demonstrate and validate our neural implicit representation on synthetic and real scenes exhibiting a wide variety of shapes, material properties, and global illumination light transport.

Abstract: Glaucoma is the number one cause of irreversible blindness globally. A major challenge for accurate glaucoma detection and progression forecasting is the bottleneck of limited labeled patients with the state-of-the-art (SOTA) 3D retinal imaging data of optical coherence tomography (OCT). To address the data scarcity issue, this paper proposes two solutions. First, we develop a novel generalization-reinforced semi-supervised learning (SSL) model called pseudo supervisor to optimally utilize unlabeled data. Compared with SOTA models, the proposed pseudo supervisor optimizes the policy of predicting pseudo labels with unlabeled samples to improve empirical generalization. Our pseudo supervisor model is evaluated with two clinical tasks consisting of glaucoma detection and progression forecasting. The progression forecasting task is evaluated both unimodally and multimodally. Our pseudo supervisor model demonstrates superior performance than SOTA SSL comparison models. Moreover, our model also achieves the best results on the publicly available LAG fundus dataset. Second, we introduce the Harvard Glaucoma Detection and Progression (Harvard-GDP) Dataset, a multimodal multitask dataset that includes data from 1,000 patients with OCT imaging data, as well as labels for glaucoma detection and progression. This is the largest glaucoma detection dataset with 3D OCT imaging data and the first glaucoma progression forecasting dataset that is publicly available. Detailed sex and racial analysis are provided, which can be used by interested researchers for fairness learning studies. Our released dataset is benchmarked with several SOTA supervised CNN and transformer deep learning models. The dataset and code are made publicly available via \url{https://ophai.hms.harvard.edu/datasets/harvard-gdp1000}.

Abstract: In this paper, we present our solution to the MuSe-Personalisation sub-challenge in the MuSe 2023 Multimodal Sentiment Analysis Challenge. The task of MuSe-Personalisation aims to predict the continuous arousal and valence values of a participant based on their audio-visual, language, and physiological signal modalities data. Considering different people have personal characteristics, the main challenge of this task is how to build robustness feature presentation for sentiment prediction. To address this issue, we propose exploiting diverse features. Specifically, we proposed a series of feature extraction methods to build a robust representation and model ensemble. We empirically evaluate the performance of the utilized method on the officially provided dataset. \textbf{As a result, we achieved 3rd place in the MuSe-Personalisation sub-challenge.} Specifically, we achieve the results of 0.8492 and 0.8439 for MuSe-Personalisation in terms of arousal and valence CCC.

Abstract: Recently, Multimodal Large Language Models (MLLMs) that enable Large Language Models (LLMs) to interpret images through visual instruction tuning have achieved significant success. However, existing visual instruction tuning methods only utilize image-language instruction data to align the language and image modalities, lacking a more fine-grained cross-modal alignment. In this paper, we propose Position-enhanced Visual Instruction Tuning (PVIT), which extends the functionality of MLLMs by integrating an additional region-level vision encoder. This integration promotes a more detailed comprehension of images for the MLLM. In addition, to efficiently achieve a fine-grained alignment between the vision modules and the LLM, we design multiple data generation strategies to construct an image-region-language instruction dataset. Finally, we present both quantitative experiments and qualitative analysis that demonstrate the superiority of the proposed model. Code and data will be released at https://github.com/THUNLP-MT/PVIT.

Abstract: Population aging is one of the most serious problems in certain countries. In order to implement its countermeasures, understanding its rapid progress is of urgency with a granular resolution. However, a detailed and rigorous survey with high frequency is not feasible due to the constraints of financial and human resources. Nowadays, Deep Learning is prevalent for pattern recognition with significant accuracy, with its application to remote sensing. This paper proposes a multi-head Convolutional Neural Network model with transfer learning from pre-trained ResNet50 for estimating mesh-wise demographics of Japan as one of the most aged countries in the world, with satellite images from Landsat-8/OLI and Suomi NPP/VIIRS-DNS as inputs and census demographics as labels. The trained model was performed on a testing dataset with a test score of at least 0.8914 in $\text{R}^2$ for all the demographic composition groups, and the estimated demographic composition was generated and visualised for 2022 as a non-census year.

Abstract: Medical image segmentation is a critical task that plays a vital role in diagnosis, treatment planning, and disease monitoring. Accurate segmentation of anatomical structures and abnormalities from medical images can aid in the early detection and treatment of various diseases. In this paper, we address the local feature deficiency of the Transformer model by carefully re-designing the self-attention map to produce accurate dense prediction in medical images. To this end, we first apply the wavelet transformation to decompose the input feature map into low-frequency (LF) and high-frequency (HF) subbands. The LF segment is associated with coarse-grained features while the HF components preserve fine-grained features such as texture and edge information. Next, we reformulate the self-attention operation using the efficient Transformer to perform both spatial and context attention on top of the frequency representation. Furthermore, to intensify the importance of the boundary information, we impose an additional attention map by creating a Gaussian pyramid on top of the HF components. Moreover, we propose a multi-scale context enhancement block within skip connections to adaptively model inter-scale dependencies to overcome the semantic gap among stages of the encoder and decoder modules. Throughout comprehensive experiments, we demonstrate the effectiveness of our strategy on multi-organ and skin lesion segmentation benchmarks. The implementation code will be available upon acceptance. \href{https://github.com/mindflow-institue/WaveFormer}{GitHub}.

Abstract: Cross-domain few-shot segmentation (CD-FSS) aims to achieve semantic segmentation in previously unseen domains with a limited number of annotated samples. Although existing CD-FSS models focus on cross-domain feature transformation, relying exclusively on inter-domain knowledge transfer may lead to the loss of critical intra-domain information. To this end, we propose a novel residual transformation network (RestNet) that facilitates knowledge transfer while retaining the intra-domain support-query feature information. Specifically, we propose a Semantic Enhanced Anchor Transform (SEAT) module that maps features to a stable domain-agnostic space using advanced semantics. Additionally, an Intra-domain Residual Enhancement (IRE) module is designed to maintain the intra-domain representation of the original discriminant space in the new space. We also propose a mask prediction strategy based on prototype fusion to help the model gradually learn how to segment. Our RestNet can transfer cross-domain knowledge from both inter-domain and intra-domain without requiring additional fine-tuning. Extensive experiments on ISIC, Chest X-ray, and FSS-1000 show that our RestNet achieves state-of-the-art performance. Our code will be available soon.

Abstract: Due to the lack of more efficient diagnostic tools for monkeypox, its spread remains unchecked, presenting a formidable challenge to global health. While the high efficacy of deep learning models for monkeypox diagnosis has been demonstrated in related studies, the overlook of inference speed, the parameter size and diagnosis performance for early-stage monkeypox renders the models inapplicable in real-world settings. To address these challenges, we proposed an ultrafast and ultralight network named Fast-MpoxNet. Fast-MpoxNet possesses only 0.27M parameters and can process input images at 68 frames per second (FPS) on the CPU. To counteract the diagnostic performance limitation brought about by the small model capacity, it integrates the attention-based feature fusion module and the multiple auxiliary losses enhancement strategy for better detecting subtle image changes and optimizing weights. Using transfer learning and five-fold cross-validation, Fast-MpoxNet achieves 94.26% Accuracy on the Mpox dataset. Notably, its recall for early-stage monkeypox achieves 93.65%. By adopting data augmentation, our model's Accuracy rises to 98.40% and attains a Practicality Score (A new metric for measuring model practicality in real-time diagnosis application) of 0.80. We also developed an application system named Mpox-AISM V2 for both personal computers and mobile phones. Mpox-AISM V2 features ultrafast responses, offline functionality, and easy deployment, enabling accurate and real-time diagnosis for both the public and individuals in various real-world settings, especially in populous settings during the outbreak. Our work could potentially mitigate future monkeypox outbreak and illuminate a fresh paradigm for developing real-time diagnostic tools in the healthcare field.

Abstract: Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are often applied repeatedly across frames or temporal chunks. In this work, we exploit temporal redundancy between subsequent inputs to reduce the cost of Transformers for video processing. We describe a method for identifying and re-processing only those tokens that have changed significantly over time. Our proposed family of models, Eventful Transformers, can be converted from existing Transformers (often without any re-training) and give adaptive control over the compute cost at runtime. We evaluate our method on large-scale datasets for video object detection (ImageNet VID) and action recognition (EPIC-Kitchens 100). Our approach leads to significant computational savings (on the order of 2-4x) with only minor reductions in accuracy.

Abstract: Eye tracking has been a pivotal tool in diverse fields such as vision research, language analysis, and usability assessment. The majority of prior investigations, however, have concentrated on expansive desktop displays employing specialized, costly eye tracking hardware that lacks scalability. Remarkably little insight exists into ocular movement patterns on smartphones, despite their widespread adoption and significant usage. In this manuscript, we present an open-source implementation of a smartphone-based gaze tracker that emulates the methodology proposed by a GooglePaper (whose source code remains proprietary). Our focus is on attaining accuracy comparable to that attained through the GooglePaper's methodology, without the necessity for supplementary hardware. Through the integration of machine learning techniques, we unveil an accurate eye tracking solution that is native to smartphones. Our approach demonstrates precision akin to the state-of-the-art mobile eye trackers, which are characterized by a cost that is two orders of magnitude higher. Leveraging the vast MIT GazeCapture dataset, which is available through registration on the dataset's website, we successfully replicate crucial findings from previous studies concerning ocular motion behavior in oculomotor tasks and saliency analyses during natural image observation. Furthermore, we emphasize the applicability of smartphone-based gaze tracking in discerning reading comprehension challenges. Our findings exhibit the inherent potential to amplify eye movement research by significant proportions, accommodating participation from thousands of subjects with explicit consent. This scalability not only fosters advancements in vision research, but also extends its benefits to domains such as accessibility enhancement and healthcare applications.

Abstract: This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario. The dataset used in our evaluation is FaceForensics++, which features 1000 original videos manipulated by four different techniques, with a total of 5000 videos. We conduct extensive experiments on multi-task learning and contrastive techniques, which are well studied in literature for their generalization benefits. It can be concluded that the proposed detection model is quite generalized, i.e., accurately detects manipulation methods not encountered during training as compared to the state-of-the-art.

Abstract: Current prevailing Video Object Segmentation (VOS) methods usually perform dense matching between the current and reference frames after extracting their features. One on hand, the decoupled modeling restricts the targets information propagation only at high-level feature space. On the other hand, the pixel-wise matching leads to a lack of holistic understanding of the targets. To overcome these issues, we propose a unified VOS framework, coined as JointFormer, for joint modeling the three elements of feature, correspondence, and a compressed memory. The core design is the Joint Block, utilizing the flexibility of attention to simultaneously extract feature and propagate the targets information to the current tokens and the compressed memory token. This scheme allows to perform extensive information propagation and discriminative feature learning. To incorporate the long-term temporal targets information, we also devise a customized online updating mechanism for the compressed memory token, which can prompt the information flow along the temporal dimension and thus improve the global modeling capability. Under the design, our method achieves a new state-of-art performance on DAVIS 2017 val/test-dev (89.7% and 87.6%) and YouTube-VOS 2018/2019 val (87.0% and 87.0%) benchmarks, outperforming existing works by a large margin.