Computer Vision and Pattern Recognition (cs.CV)

Abstract: Gait recognition aims to distinguish different walking patterns by analyzing video-level human silhouettes, rather than relying on appearance information. Previous research on gait recognition has primarily focused on extracting local or global spatial-temporal representations, while overlooking the intrinsic periodic features of gait sequences, which, when fully utilized, can significantly enhance performance. In this work, we propose a plug-and-play strategy, called Temporal Periodic Alignment (TPA), which leverages the periodic nature and fine-grained temporal dependencies of gait patterns. The TPA strategy comprises two key components. The first component is Adaptive Fourier-transform Position Encoding (AFPE), which adaptively converts features and discrete-time signals into embeddings that are sensitive to periodic walking patterns. The second component is the Temporal Aggregation Module (TAM), which separates embeddings into trend and seasonal components, and extracts meaningful temporal correlations to identify primary components, while filtering out random noise. We present a simple and effective baseline method for gait recognition, based on the TPA strategy. Extensive experiments conducted on three popular public datasets (CASIA-B, OU-MVLP, and GREW) demonstrate that our proposed method achieves state-of-the-art performance on multiple benchmark tests.

Abstract: We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1 to 6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.

Abstract: Although face recognition starts to play an important role in our daily life, we need to pay attention that data-driven face recognition vision systems are vulnerable to adversarial attacks. However, the current two categories of adversarial attacks, namely digital attacks and physical attacks both have drawbacks, with the former ones impractical and the latter one conspicuous, high-computational and inexecutable. To address the issues, we propose a practical, executable, inconspicuous and low computational adversarial attack based on LED illumination modulation. To fool the systems, the proposed attack generates imperceptible luminance changes to human eyes through fast intensity modulation of scene LED illumination and uses the rolling shutter effect of CMOS image sensors in face recognition systems to implant luminance information perturbation to the captured face images. In summary,we present a denial-of-service (DoS) attack for face detection and a dodging attack for face verification. We also evaluate their effectiveness against well-known face detection models, Dlib, MTCNN and RetinaFace , and face verification models, Dlib, FaceNet,and ArcFace.The extensive experiments show that the success rates of DoS attacks against face detection models reach 97.67%, 100%, and 100%, respectively, and the success rates of dodging attacks against all face verification models reach 100%.

Abstract: Common deep learning models for 3D environment perception often use pillarization/voxelization methods to convert point cloud data into pillars/voxels and then process it with a 2D/3D convolutional neural network (CNN). The pioneer work PointNet has been widely applied as a local feature descriptor, a fundamental component in deep learning models for 3D perception, to extract features of a point cloud. This is achieved by using a symmetric max-pooling operator which provides unique pillar/voxel features. However, by ignoring most of the points, the max-pooling operator causes an information loss, which reduces the model performance. To address this issue, we propose a novel local feature descriptor, mini-PointNetPlus, as an alternative for plug-and-play to PointNet. Our basic idea is to separately project the data points to the individual features considered, each leading to a permutation invariant. Thus, the proposed descriptor transforms an unordered point cloud to a stable order. The vanilla PointNet is proved to be a special case of our mini-PointNetPlus. Due to fully utilizing the features by the proposed descriptor, we demonstrate in experiment a considerable performance improvement for 3D perception.

Abstract: Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate frontend contour initialization, multi-stage error accumulation, or deficient local information aggregation. To tackle these limitations, we propose a novel arbitrary-shaped scene text detection framework named CT-Net by progressive contour regression with contour transformers. Specifically, we first employ a contour initialization module that generates coarse text contours without any post-processing. Then, we adopt contour refinement modules to adaptively refine text contours in an iterative manner, which are beneficial for context information capturing and progressive global contour deformation. Besides, we propose an adaptive training strategy to enable the contour transformers to learn more potential deformation paths, and introduce a re-score mechanism that can effectively suppress false positives. Extensive experiments are conducted on four challenging datasets, which demonstrate the accuracy and efficiency of our CT-Net over state-of-the-art methods. Particularly, CT-Net achieves F-measure of 86.1 at 11.2 frames per second (FPS) and F-measure of 87.8 at 10.1 FPS for CTW1500 and Total-Text datasets, respectively.

Abstract: Machine learning makes multimedia data (e.g., images) more attractive, however, multimedia data is usually distributed and privacy sensitive. Multiple distributed multimedia clients can resort to federated learning (FL) to jointly learn a global shared model without requiring to share their private samples with any third-party entities. In this paper, we show that FL suffers from the cross-client generative adversarial networks (GANs)-based (C-GANs) attack, in which a malicious client (i.e., adversary) can reconstruct samples with the same distribution as the training samples from other clients (i.e., victims). Since a benign client's data can be leaked to the adversary, this attack brings the risk of local data leakage for clients in many security-critical FL applications. Thus, we propose Fed-EDKD (i.e., Federated Ensemble Data-free Knowledge Distillation) technique to improve the current popular FL schemes to resist C-GANs attack. In Fed-EDKD, each client submits a local model to the server for obtaining an ensemble global model. Then, to avoid model expansion, Fed-EDKD adopts data-free knowledge distillation techniques to transfer knowledge from the ensemble global model to a compressed model. By this way, Fed-EDKD reduces the adversary's control capability over the global model, so Fed-EDKD can effectively mitigate C-GANs attack. Finally, the experimental results demonstrate that Fed-EDKD significantly mitigates C-GANs attack while only incurring a slight accuracy degradation of FL.

Abstract: Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics results in high uncertainty around the objects' boundaries and numerous false positives. We propose a paradigm change by shifting from a per-pixel classification to a mask classification. Our mask-based method, Mask2Anomaly, demonstrates the feasibility of integrating an anomaly detection method in a mask-classification architecture. Mask2Anomaly includes several technical novelties that are designed to improve the detection of anomalies in masks: i) a global masked attention module to focus individually on the foreground and background regions; ii) a mask contrastive learning that maximizes the margin between an anomaly and known classes; and iii) a mask refinement solution to reduce false positives. Mask2Anomaly achieves new state-of-the-art results across a range of benchmarks, both in the per-pixel and component-level evaluations. In particular, Mask2Anomaly reduces the average false positives rate by 60% wrt the previous state-of-the-art. Github page: https://github.com/shyam671/Mask2Anomaly-Unmasking-Anomalies-in-Road-Scene-Segmentation.

Abstract: Quantization is a promising approach to reduce the high computational complexity of image super-resolution (SR) networks. However, compared to high-level tasks like image classification, low-bit quantization leads to severe accuracy loss in SR networks. This is because feature distributions of SR networks are significantly divergent for each channel or input image, and is thus difficult to determine a quantization range. Existing SR quantization works approach this distribution mismatch problem by dynamically adapting quantization ranges to the variant distributions during test time. However, such dynamic adaptation incurs additional computational costs that limit the benefits of quantization. Instead, we propose a new quantization-aware training framework that effectively Overcomes the Distribution Mismatch problem in SR networks without the need for dynamic adaptation. Intuitively, the mismatch can be reduced by directly regularizing the variance in features during training. However, we observe that variance regularization can collide with the reconstruction loss during training and adversely impact SR accuracy. Thus, we avoid the conflict between two losses by regularizing the variance only when the gradients of variance regularization are cooperative with that of reconstruction. Additionally, to further reduce the distribution mismatch, we introduce distribution offsets to layers with a significant mismatch, which either scales or shifts channel-wise features. Our proposed algorithm, called ODM, effectively reduces the mismatch in distributions with minimal computational overhead. Experimental results show that ODM effectively outperforms existing SR quantization approaches with similar or fewer computations, demonstrating the importance of reducing the distribution mismatch problem. Our code is available at https://github.com/Cheeun/ODM.

Abstract: The local road network information is essential for autonomous navigation. This information is commonly obtained from offline HD-Maps in terms of lane graphs. However, the local road network at a given moment can be drastically different than the one given in the offline maps; due to construction works, accidents etc. Moreover, the autonomous vehicle might be at a location not covered in the offline HD-Map. Thus, online estimation of the lane graph is crucial for widespread and reliable autonomous navigation. In this work, we tackle online Bird's-Eye-View lane graph extraction from a single onboard camera image. We propose to use prior information to increase quality of the estimations. The prior is extracted from the dataset through a transformer based Wasserstein Autoencoder. The autoencoder is then used to enhance the initial lane graph estimates. This is done through optimization of the latent space vector. The optimization encourages the lane graph estimation to be logical by discouraging it to diverge from the prior distribution. We test the method on two benchmark datasets, NuScenes and Argoverse. The results show that the proposed method significantly improves the performance compared to state-of-the-art methods.

Abstract: Deep Learning models like Convolutional Neural Networks (CNN) are powerful image classifiers, but what factors determine whether they attend to similar image areas as humans do? While previous studies have focused on technological factors, little is known about the role of factors that affect human attention. In the present study, we investigated how the tasks used to elicit human attention maps interact with image characteristics in modulating the similarity between humans and CNN. We varied the intentionality of human tasks, ranging from spontaneous gaze during categorization over intentional gaze-pointing up to manual area selection. Moreover, we varied the type of image to be categorized, using either singular, salient objects, indoor scenes consisting of object arrangements, or landscapes without distinct objects defining the category. The human attention maps generated in this way were compared to the CNN attention maps revealed by explainable artificial intelligence (Grad-CAM). The influence of human tasks strongly depended on image type: For objects, human manual selection produced maps that were most similar to CNN, while the specific eye movement task has little impact. For indoor scenes, spontaneous gaze produced the least similarity, while for landscapes, similarity was equally low across all human tasks. To better understand these results, we also compared the different human attention maps to each other. Our results highlight the importance of taking human factors into account when comparing the attention of humans and CNN.

Abstract: Numerous fields, such as ecology, biology, and neuroscience, use animal recordings to track and measure animal behaviour. Over time, a significant volume of such data has been produced, but some computer vision techniques cannot explore it due to the lack of annotations. To address this, we propose an approach for estimating 2D mouse body pose from unlabelled images using a synthetically generated empirical pose prior. Our proposal is based on a recent self-supervised method for estimating 2D human pose that uses single images and a set of unpaired typical 2D poses within a GAN framework. We adapt this method to the limb structure of the mouse and generate the empirical prior of 2D poses from a synthetic 3D mouse model, thereby avoiding manual annotation. In experiments on a new mouse video dataset, we evaluate the performance of the approach by comparing pose predictions to a manually obtained ground truth. We also compare predictions with those from a supervised state-of-the-art method for animal pose estimation. The latter evaluation indicates promising results despite the lack of paired training data. Finally, qualitative results using a dataset of horse images show the potential of the setting to adapt to other animal species.

Abstract: 3D visual grounding aims to localize the target object in a 3D point cloud by a free-form language description. Typically, the sentences describing the target object tend to provide information about its relative relation between other objects and its position within the whole scene. In this work, we propose a relation-aware one-stage framework, named 3D Relative Position-aware Network (3DRP-Net), which can effectively capture the relative spatial relationships between objects and enhance object attributes. Specifically, 1) we propose a 3D Relative Position Multi-head Attention (3DRP-MA) module to analyze relative relations from different directions in the context of object pairs, which helps the model to focus on the specific object relations mentioned in the sentence. 2) We designed a soft-labeling strategy to alleviate the spatial ambiguity caused by redundant points, which further stabilizes and enhances the learning process through a constant and discriminative distribution. Extensive experiments conducted on three benchmarks (i.e., ScanRefer and Nr3D/Sr3D) demonstrate that our method outperforms all the state-of-the-art methods in general. The source code will be released on GitHub.

Abstract: We introduce a novel speaker model \textsc{Kefa} for navigation instruction generation. The existing speaker models in Vision-and-Language Navigation suffer from the large domain gap of vision features between different environments and insufficient temporal grounding capability. To address the challenges, we propose a Knowledge Refinement Module to enhance the feature representation with external knowledge facts, and an Adaptive Temporal Alignment method to enforce fine-grained alignment between the generated instructions and the observation sequences. Moreover, we propose a new metric SPICE-D for navigation instruction evaluation, which is aware of the correctness of direction phrases. The experimental results on R2R and UrbanWalk datasets show that the proposed KEFA speaker achieves state-of-the-art instruction generation performance for both indoor and outdoor scenes.

Abstract: Today, many cities seek to transition to more sustainable transportation systems. Cycling is critical in this transition for shorter trips, including first-and-last-mile links to transit. Yet, if individuals perceive cycling as unsafe, they will not cycle and choose other transportation modes. This study presents a novel approach to identifying how the perception of cycling safety can be analyzed and understood and the impact of the built environment and cycling contexts on such perceptions. We base our work on other perception studies and pairwise comparisons, using real-world images to survey respondents. We repeatedly show respondents two road environments and ask them to select the one they perceive as safer for cycling. We compare several methods capable of rating cycling environments from pairwise comparisons and classify cycling environments perceived as safe or unsafe. Urban planning can use this score to improve interventions' effectiveness and improve cycling promotion campaigns. Furthermore, this approach facilitates the continuous assessment of changing cycling environments, allows for a short-term evaluation of measures, and is efficiently deployed in different locations or contexts.

Abstract: Encoding-decoding CNNs play a central role in data-driven noise reduction and can be found within numerous deep-learning algorithms. However, the development of these CNN architectures is often done in ad-hoc fashion and theoretical underpinnings for important design choices is generally lacking. Up to this moment there are different existing relevant works that strive to explain the internal operation of these CNNs. Still, these ideas are either scattered and/or may require significant expertise to be accessible for a bigger audience. In order to open up this exciting field, this article builds intuition on the theory of deep convolutional framelets and explains diverse ED CNN architectures in a unified theoretical framework. By connecting basic principles from signal processing to the field of deep learning, this self-contained material offers significant guidance for designing robust and efficient novel CNN architectures.

Abstract: This paper describes an adaptation of the Local Interpretable Model-Agnostic Explanations (LIME) AI method to operate under a biometric verification setting. LIME was initially proposed for networks with the same output classes used for training, and it employs the softmax probability to determine which regions of the image contribute the most to classification. However, in a verification setting, the classes to be recognized have not been seen during training. In addition, instead of using the softmax output, face descriptors are usually obtained from a layer before the classification layer. The model is adapted to achieve explainability via cosine similarity between feature vectors of perturbated versions of the input image. The method is showcased for face biometrics with two CNN models based on MobileNetv2 and ResNet50.

Abstract: The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with different topologies. We thus propose a novel weakly-supervised keypoint-based framework to overcome these difficulties. Specifically, we use a topology-agnostic keypoint detector with inverse kinematics to compute transformations between the source and target meshes. Our method only requires supervision on the keypoints, can be applied to meshes with different topologies and is shape-invariant for the target which allows extraction of pose-only information from the target meshes without transferring shape information. We further design a cycle reconstruction to perform self-supervised pose transfer without the need for ground truth deformed mesh with the same pose and shape as the target and source, respectively. We evaluate our approach on benchmark human and animal datasets, where we achieve superior performance compared to the state-of-the-art unsupervised approaches and even comparable performance with the fully supervised approaches. We test on the more challenging Mixamo dataset to verify our approach's ability in handling meshes with different topologies and complex clothes. Cross-dataset evaluation further shows the strong generalization ability of our approach.

Abstract: The emergence of artificial emotional intelligence technology is revolutionizing the fields of computers and robotics, allowing for a new level of communication and understanding of human behavior that was once thought impossible. While recent advancements in deep learning have transformed the field of computer vision, automated understanding of evoked or expressed emotions in visual media remains in its infancy. This foundering stems from the absence of a universally accepted definition of "emotion", coupled with the inherently subjective nature of emotions and their intricate nuances. In this article, we provide a comprehensive, multidisciplinary overview of the field of emotion analysis in visual media, drawing on insights from psychology, engineering, and the arts. We begin by exploring the psychological foundations of emotion and the computational principles that underpin the understanding of emotions from images and videos. We then review the latest research and systems within the field, accentuating the most promising approaches. We also discuss the current technological challenges and limitations of emotion analysis, underscoring the necessity for continued investigation and innovation. We contend that this represents a "Holy Grail" research problem in computing and delineate pivotal directions for future inquiry. Finally, we examine the ethical ramifications of emotion-understanding technologies and contemplate their potential societal impacts. Overall, this article endeavors to equip readers with a deeper understanding of the domain of emotion analysis in visual media and to inspire further research and development in this captivating and rapidly evolving field.

Abstract: We propose Cos R-CNN, a simple exemplar-based R-CNN formulation that is designed for online few-shot object detection. That is, it is able to localise and classify novel object categories in images with few examples without fine-tuning. Cos R-CNN frames detection as a learning-to-compare task: unseen classes are represented as exemplar images, and objects are detected based on their similarity to these exemplars. The cosine-based classification head allows for dynamic adaptation of classification parameters to the exemplar embedding, and encourages the clustering of similar classes in embedding space without the need for manual tuning of distance-metric hyperparameters. This simple formulation achieves best results on the recently proposed 5-way ImageNet few-shot detection benchmark, beating the online 1/5/10-shot scenarios by more than 8/3/1%, as well as performing up to 20% better in online 20-way few-shot VOC across all shots on novel classes.

Abstract: Deep learning has made significant advancements in supervised learning. However, models trained in this setting often face challenges due to domain shift between training and test sets, resulting in a significant drop in performance during testing. To address this issue, several domain generalization methods have been developed to learn robust and domain-invariant features from multiple training domains that can generalize well to unseen test domains. Data augmentation plays a crucial role in achieving this goal by enhancing the diversity of the training data. In this paper, inspired by the observation that normalizing an image with different statistics generated by different batches with various domains can perturb its feature, we propose a simple yet effective method called NormAUG (Normalization-guided Augmentation). Our method includes two paths: the main path and the auxiliary (augmented) path. During training, the auxiliary path includes multiple sub-paths, each corresponding to batch normalization for a single domain or a random combination of multiple domains. This introduces diverse information at the feature level and improves the generalization of the main path. Moreover, our NormAUG method effectively reduces the existing upper boundary for generalization based on theoretical perspectives. During the test stage, we leverage an ensemble strategy to combine the predictions from the auxiliary path of our model, further boosting performance. Extensive experiments are conducted on multiple benchmark datasets to validate the effectiveness of our proposed method.

Abstract: Vision-based Bird's Eye View (BEV) representation is an emerging perception formulation for autonomous driving. The core challenge is to construct BEV space with multi-camera features, which is a one-to-many ill-posed problem. Diving into all previous BEV representation generation methods, we found that most of them fall into two types: modeling depths in image views or modeling heights in the BEV space, mostly in an implicit way. In this work, we propose to explicitly model heights in the BEV space, which needs no extra data like LiDAR and can fit arbitrary camera rigs and types compared to modeling depths. Theoretically, we give proof of the equivalence between height-based methods and depth-based methods. Considering the equivalence and some advantages of modeling heights, we propose HeightFormer, which models heights and uncertainties in a self-recursive way. Without any extra data, the proposed HeightFormer could estimate heights in BEV accurately. Benchmark results show that the performance of HeightFormer achieves SOTA compared with those camera-only methods.

Abstract: Diffusion Models (DM) are highly effective at generating realistic, high-quality images. However, these models lack creativity and merely compose outputs based on their training data, guided by a textual input provided at creation time. Is it acceptable to generate images reminiscent of an artist, employing his name as input? This imply that if the DM is able to replicate an artist's work then it was trained on some or all of his artworks thus violating copyright. In this paper, a preliminary study to infer the probability of use of an artist's name in the input string of a generated image is presented. To this aim we focused only on images generated by the famous DALL-E 2 and collected images (both original and generated) of five renowned artists. Finally, a dedicated Siamese Neural Network was employed to have a first kind of probability. Experimental results demonstrate that our approach is an optimal starting point and can be employed as a prior for predicting a complete input string of an investigated image. Dataset and code are available at: https://github.com/ictlab-unict/not-with-my-name .

Abstract: Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets. Despite the challenges posed by the numerous interaction combinations, they also offer opportunities for multimodal learning of visual texts. In this paper, we present a systematic and unified framework (RmLR) that enhances HOI detection by incorporating structured text knowledge. Firstly, we qualitatively and quantitatively analyze the loss of interaction information in the two-stage HOI detector and propose a re-mining strategy to generate more comprehensive visual representation.Secondly, we design more fine-grained sentence- and word-level alignment and knowledge transfer strategies to effectively address the many-to-many matching problem between multiple interactions and multiple texts.These strategies alleviate the matching confusion problem that arises when multiple interactions occur simultaneously, thereby improving the effectiveness of the alignment process. Finally, HOI reasoning by visual features augmented with textual knowledge substantially improves the understanding of interactions. Experimental results illustrate the effectiveness of our approach, where state-of-the-art performance is achieved on public benchmarks. We further analyze the effects of different components of our approach to provide insights into its efficacy.

Abstract: Current referring video object segmentation (R-VOS) techniques extract conditional kernels from encoded (low-resolution) vision-language features to segment the decoded high-resolution features. We discovered that this causes significant feature drift, which the segmentation kernels struggle to perceive during the forward computation. This negatively affects the ability of segmentation kernels. To address the drift problem, we propose a Spectrum-guided Multi-granularity (SgMg) approach, which performs direct segmentation on the encoded features and employs visual details to further optimize the masks. In addition, we propose Spectrum-guided Cross-modal Fusion (SCF) to perform intra-frame global interactions in the spectral domain for effective multimodal representation. Finally, we extend SgMg to perform multi-object R-VOS, a new paradigm that enables simultaneous segmentation of multiple referred objects in a video. This not only makes R-VOS faster, but also more practical. Extensive experiments show that SgMg achieves state-of-the-art performance on four video benchmark datasets, outperforming the nearest competitor by 2.8% points on Ref-YouTube-VOS. Our extended SgMg enables multi-object R-VOS, runs about 3 times faster while maintaining satisfactory performance. Code is available at https://github.com/bo-miao/SgMg.

Abstract: For safety-related applications, it is crucial to produce trustworthy deep neural networks whose prediction is associated with confidence that can represent the likelihood of correctness for subsequent decision-making. Existing dense binary classification models are prone to being over-confident. To improve model calibration, we propose Adaptive Stochastic Label Perturbation (ASLP) which learns a unique label perturbation level for each training image. ASLP employs our proposed Self-Calibrating Binary Cross Entropy (SC-BCE) loss, which unifies label perturbation processes including stochastic approaches (like DisturbLabel), and label smoothing, to correct calibration while maintaining classification rates. ASLP follows Maximum Entropy Inference of classic statistical mechanics to maximise prediction entropy with respect to missing information. It performs this while: (1) preserving classification accuracy on known data as a conservative solution, or (2) specifically improves model calibration degree by minimising the gap between the prediction accuracy and expected confidence of the target training label. Extensive results demonstrate that ASLP can significantly improve calibration degrees of dense binary classification models on both in-distribution and out-of-distribution data. The code is available on https://github.com/Carlisle-Liu/ASLP.

Abstract: Group activity recognition is a hot topic in computer vision. Recognizing activities through group relationships plays a vital role in group activity recognition. It holds practical implications in various scenarios, such as video analysis, surveillance, automatic driving, and understanding social activities. The model's key capabilities encompass efficiently modeling hierarchical relationships within a scene and accurately extracting distinctive spatiotemporal features from groups. Given this technology's extensive applicability, identifying group activities has garnered significant research attention. This work examines the current progress in technology for recognizing group activities, with a specific focus on global interactivity and activities. Firstly, we comprehensively review the pertinent literature and various group activity recognition approaches, from traditional methodologies to the latest methods based on spatial structure, descriptors, non-deep learning, hierarchical recurrent neural networks (HRNN), relationship models, and attention mechanisms. Subsequently, we present the relational network and relational architectures for each module. Thirdly, we investigate methods for recognizing group activity and compare their performance with state-of-the-art technologies. We summarize the existing challenges and provide comprehensive guidance for newcomers to understand group activity recognition. Furthermore, we review emerging perspectives in group activity recognition to explore new directions and possibilities.

Abstract: Similarity analysis using neural networks has emerged as a powerful technique for understanding and categorizing complex patterns in various domains. By leveraging the latent representations learned by neural networks, data objects such as images can be compared effectively. This research explores the utilization of latent information generated by fully convolutional networks (FCNs) in similarity analysis, notably to estimate the visual resemblance of objects segmented in 2D pictures. To do this, the analytical scheme comprises two steps: (1) extracting and transforming feature patterns per 2D object from a trained FCN, and (2) identifying the most similar patterns through fuzzy inference. The step (2) can be further enhanced by incorporating a weighting scheme that considers the significance of latent variables in the analysis. The results provide valuable insights into the benefits and challenges of employing neural network-based similarity analysis for discerning data patterns effectively.

Abstract: End-to-end region-based object detectors like Sparse R-CNN usually have multiple cascade bounding box decoding stages, which refine the current predictions according to their previous results. Model parameters within each stage are independent, evolving a huge cost. In this paper, we find the general setting of decoding stages is actually redundant. By simply sharing parameters and making a recursive decoder, the detector already obtains a significant improvement. The recursive decoder can be further enhanced by positional encoding (PE) of the proposal box, which makes it aware of the exact locations and sizes of input bounding boxes, thus becoming adaptive to proposals from different stages during the recursion. Moreover, we also design centerness-based PE to distinguish the RoI feature element and dynamic convolution kernels at different positions within the bounding box. To validate the effectiveness of the proposed method, we conduct intensive ablations and build the full model on three recent mainstream region-based detectors. The RecusiveDet is able to achieve obvious performance boosts with even fewer model parameters and slightly increased computation cost. Codes are available at https://github.com/bravezzzzzz/RecursiveDet.

Abstract: Accurate 3D face shape estimation is an enabling technology with applications in healthcare, security, and creative industries, yet current state-of-the-art methods either rely on self-supervised training with 2D image data or supervised training with very limited 3D data. To bridge this gap, we present a novel approach which uses a conditioned stable diffusion model for face image generation, leveraging the abundance of 2D facial information to inform 3D space. By conditioning stable diffusion on depth maps sampled from a 3D Morphable Model (3DMM) of the human face, we generate diverse and shape-consistent images, forming the basis of SynthFace. We introduce this large-scale synthesised dataset of 250K photorealistic images and corresponding 3DMM parameters. We further propose ControlFace, a deep neural network, trained on SynthFace, which achieves competitive performance on the NoW benchmark, without requiring 3D supervision or manual 3D asset creation.

Abstract: Unsupervised localization and segmentation are long-standing robot vision challenges that describe the critical ability for an autonomous robot to learn to decompose images into individual objects without labeled data. These tasks are important because of the limited availability of dense image manual annotation and the promising vision of adapting to an evolving set of object categories in lifelong learning. Most recent methods focus on using visual appearance continuity as object cues by spatially clustering features obtained from self-supervised vision transformers (ViT). In this work, we leverage motion cues, inspired by the common fate principle that pixels that share similar movements tend to belong to the same object. We propose a new loss term formulation that uses optical flow in unlabeled videos to encourage self-supervised ViT features to become closer to each other if their corresponding spatial locations share similar movements, and vice versa. We use the proposed loss function to finetune vision transformers that were originally trained on static images. Our fine-tuning procedure outperforms state-of-the-art techniques for unsupervised semantic segmentation through linear probing, without the use of any labeled data. This procedure also demonstrates increased performance over original ViT networks across unsupervised object localization and semantic segmentation benchmarks.

Abstract: Obtaining labelled data in medical image segmentation is challenging due to the need for pixel-level annotations by experts. Recent works have shown that augmenting the object of interest with deformable transformations can help mitigate this challenge. However, these transformations have been learned globally for the image, limiting their transferability across datasets or applicability in problems where image alignment is difficult. While object-centric augmentations provide a great opportunity to overcome these issues, existing works are only focused on position and random transformations without considering shape variations of the objects. To this end, we propose a novel object-centric data augmentation model that is able to learn the shape variations for the objects of interest and augment the object in place without modifying the rest of the image. We demonstrated its effectiveness in improving kidney tumour segmentation when leveraging shape variations learned both from within the same dataset and transferred from external datasets.

Abstract: Image quality remains a key problem for both traditional and deep learning (DL)-based approaches to retinal image analysis, but identifying poor quality images can be time consuming and subjective. Thus, automated methods for retinal image quality scoring (RIQS) are needed. The current state-of-the-art is MCFNet, composed of three Densenet121 backbones each operating in a different colour space. MCFNet, and the EyeQ dataset released by the same authors, was a huge step forward for RIQS. We present QuickQual, a simple approach to RIQS, consisting of a single off-the-shelf ImageNet-pretrained Densenet121 backbone plus a Support Vector Machine (SVM). QuickQual performs very well, setting a new state-of-the-art for EyeQ (Accuracy: 88.50% vs 88.00% for MCFNet; AUC: 0.9687 vs 0.9588). This suggests that RIQS can be solved with generic perceptual features learned on natural images, as opposed to requiring DL models trained on large amounts of fundus images. Additionally, we propose a Fixed Prior linearisation scheme, that converts EyeQ from a 3-way classification to a continuous logistic regression task. For this task, we present a second model, QuickQual MEga Minified Estimator (QuickQual-MEME), that consists of only 10 parameters on top of an off-the-shelf Densenet121 and can distinguish between gradable and ungradable images with an accuracy of 89.18% (AUC: 0.9537). Code and model are available on GitHub: https://github.com/justinengelmann/QuickQual . QuickQual is so lightweight, that the entire inference code (and even the parameters for QuickQual-MEME) is already contained in this paper.

Abstract: Object detection has been widely applied for construction safety management, especially personal protective equipment (PPE) detection. Though the existing PPE detection models trained on conventional datasets have achieved excellent results, their performance dramatically declines in extreme construction conditions. A robust detection model NST-YOLOv5 is developed by combining the neural style transfer (NST) and YOLOv5 technologies. Five extreme conditions are considered and simulated via the NST module to endow the detection model with excellent robustness, including low light, intense light, sand dust, fog, and rain. Experiments show that the NST has great potential as a tool for extreme data synthesis since it is better at simulating extreme conditions than other traditional image processing algorithms and helps the NST-YOLOv5 achieve 0.141 and 0.083 mAP_(05:95) improvements in synthesized and real-world extreme data. This study provides a new feasible way to obtain a more robust detection model for extreme construction conditions.

Abstract: Advancements in large pre-trained generative models have expanded their potential as effective data generators in visual recognition. This work delves into the impact of generative images, primarily comparing paradigms that harness external data (\ie generative \vs retrieval \vs original). Our key contributions are: \textbf{1) GenBench Construction:} We devise \textbf{GenBench}, a broad benchmark comprising 22 datasets with 2548 categories, to appraise generative data across various visual recognition tasks. \textbf{2) CLER Score:} To address the insufficient correlation of existing metrics (\eg, FID, CLIP score) with downstream recognition performance, we propose \textbf{CLER}, a training-free metric indicating generative data's efficiency for recognition tasks prior to training. \textbf{3) New Baselines:} Comparisons of generative data with retrieved data from the same external pool help to elucidate the unique traits of generative data. \textbf{4) External Knowledge Injection:} By fine-tuning special token embeddings for each category via Textual Inversion, performance improves across 17 datasets, except when dealing with low-resolution reference images. Our exhaustive benchmark and analysis spotlight generative data's promise in visual recognition, while identifying key challenges for future investigation.