Showing papers in "IEEE Transactions on Pattern Analysis and Machine Intelligence in 2023"
TL;DR: Transformer as discussed by the authors is a type of deep neural network mainly based on the self-attention mechanism, which has been applied to the field of natural language processing, and has been shown to perform similar to or better than other types of networks such as convolutional and recurrent neural networks.
Abstract: Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to apply transformer to computer vision tasks. In a variety of visual benchmarks, transformer-based models perform similar to or better than other types of networks such as convolutional and recurrent neural networks. Given its high performance and less need for vision-specific inductive bias, transformer is receiving more and more attention from the computer vision community. In this paper, we review these vision transformer models by categorizing them in different tasks and analyzing their advantages and disadvantages. The main categories we explore include the backbone network, high/mid-level vision, low-level vision, and video processing. We also include efficient transformer methods for pushing transformer into real device-based applications. Furthermore, we also take a brief look at the self-attention mechanism in computer vision, as it is the base component in transformer. Toward the end of this paper, we discuss the challenges and provide several further research directions for vision transformers.
221 citations
TL;DR: CCNet as discussed by the authors proposes a recurrent crisscross attention module to harvest the contextual information of all pixels on its criss-cross path to obtain full-image contextual information in a very effective and efficient way.
Abstract: Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a criss-cross network (CCNet) for obtaining full-image contextual information in a very effective and efficient way. Concretely, for each pixel, a novel criss-cross attention module harvests the contextual information of all the pixels on its criss-cross path. By taking a further recurrent operation, each pixel can finally capture the full-image dependencies. Besides, a category consistent loss is proposed to enforce the criss-cross attention module to produce more discriminative features. Overall, CCNet is with the following merits: 1) GPU memory friendly. Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11× less GPU memory usage. 2) High computational efficiency. The recurrent criss-cross attention significantly reduces FLOPs by about 85 percent of the non-local block. 3) The state-of-the-art performance. We conduct extensive experiments on semantic segmentation benchmarks including Cityscapes, ADE20K, human parsing benchmark LIP, instance segmentation benchmark COCO, video segmentation benchmark CamVid. In particular, our CCNet achieves the mIoU scores of 81.9, 45.76 and 55.47 percent on the Cityscapes test set, the ADE20K validation set and the LIP validation set respectively, which are the new state-of-the-art results. The source codes are available at https://github.com/speedinghzl/CCNethttps://github.com/speedinghzl/CCNet.
81 citations
76 citations
TL;DR: Ji et al. as mentioned in this paper proposed Contextual Transformer Network (CoTNet) to exploit the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthen the capacity of visual representation.
Abstract: Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer ( CoT ) block, for visual recognition. Such design fully capitalizes on the contextual information among input keys to guide the learning of dynamic attention matrix and thus strengthens the capacity of visual representation. Technically, CoT block first contextually encodes input keys via a $3\times 3$ $1\times 1$ $3\times 3$ https://github.com/JDAI-CV/CoTNet .
68 citations
TL;DR: Wang et al. as discussed by the authors proposed a multi-stage architecture for action segmentation, where the first stage generates an initial prediction that is refined by the next ones. But their architecture still suffers from a small receptive field, and they propose a dual dilated layer that combines both large and small receptive fields.
Abstract: With the success of deep learning in classifying short trimmed videos, more attention has been focused on temporally segmenting and classifying activities in long untrimmed videos. State-of-the-art approaches for action segmentation utilize several layers of temporal convolution and temporal pooling. Despite the capabilities of these approaches in capturing temporal dependencies, their predictions suffer from over-segmentation errors. In this paper, we propose a multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches. The first stage generates an initial prediction that is refined by the next ones. In each stage we stack several layers of dilated temporal convolutions covering a large receptive field with few parameters. While this architecture already performs well, lower layers still suffer from a small receptive field. To address this limitation, we propose a dual dilated layer that combines both large and small receptive fields. We further decouple the design of the first stage from the refining stages to address the different requirements of these stages. Extensive evaluation shows the effectiveness of the proposed model in capturing long-range dependencies and recognizing action segments. Our models achieve state-of-the-art results on three datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.
47 citations
TL;DR: In this paper , a generalized negation method is proposed for quantum basic belief assignment (QBBA), called QBBA negation, which provides promising solutions to knowledge representation, uncertainty measure, and fusion of quantum information.
Abstract: In artificial intelligence systems, a question on how to express the uncertainty in knowledge remains an open issue. The negation scheme provides a new perspective to solve this issue. In this paper, we study quantum decisions from the negation perspective. Specifically, complex evidence theory (CET) is considered to be effective to express and handle uncertain information in a complex plane. Therefore, we first express CET in the quantum framework of Hilbert space. On this basis, a generalized negation method is proposed for quantum basic belief assignment (QBBA), called QBBA negation. In addition, a QBBA entropy is revisited to study the QBBA negation process to reveal the variation tendency of negation iteration. Meanwhile, the properties of the QBBA negation function are analyzed and discussed along with special cases. Then, several multisource quantum information fusion (MSQIF) algorithms are designed to support decision making. Finally, these MSQIF algorithms are applied in pattern classification to demonstrate their effectiveness. This is the first work to design MSQIF algorithms to support quantum decision making from a new perspective of "negation", which provides promising solutions to knowledge representation, uncertainty measure, and fusion of quantum information.
43 citations
TL;DR: Wang et al. as discussed by the authors introduced the idea of denoising on the feature map to enhance the detection to small and cluttered objects and added a novel IoU constant factor to the smooth L1 loss to address the long standing boundary problem, which is mainly caused by the periodicity of angular (PoA) and exchangeability of edges (EoE).
Abstract: Small and cluttered objects are common in real-world which are challenging for detection. The difficulty is further pronounced when the objects are rotated, as traditional detectors often routinely locate the objects in horizontal bounding box such that the region of interest is contaminated with background or nearby interleaved objects. In this paper, we first innovatively introduce the idea of denoising to object detection. Instance-level denoising on the feature map is performed to enhance the detection to small and cluttered objects. To handle the rotation variation, we also add a novel IoU constant factor to the smooth L1 loss to address the long standing boundary problem, which to our analysis, is mainly caused by the periodicity of angular (PoA) and exchangeability of edges (EoE). By combing these two features, our proposed detector is termed as SCRDet++. Extensive experiments are performed on large aerial images public datasets DOTA, DIOR, UCAS-AOD as well as natural image dataset COCO, scene text dataset ICDAR2015, small traffic light dataset BSTLD and our released S 2 TLD by this paper. The results show the effectiveness of our approach. The released dataset S 2 TLD is made public available, which contains 5,786 images with 14,130 traffic light instances across five categories.
39 citations
TL;DR: EfficientGCN-B4 as mentioned in this paper proposes a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters.
Abstract: One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and over-parameterized. The low efficiency in model training and inference has increased the validation costs of model architectures in large-scale datasets. To address the above issue, recent advanced separable convolutional layers are embedded into an early fused Multiple Input Branches (MIB) network, constructing an efficient Graph Convolutional Network (GCN) baseline for skeleton-based action recognition. In addition, based on such the baseline, we design a compound scaling strategy to expand the model's width and depth synchronously, and eventually obtain a family of efficient GCN baselines with high accuracies and small amounts of trainable parameters, termed EfficientGCN-Bx, where "x" denotes the scaling coefficient. On two large-scale datasets, i.e., NTU RGB+D 60 and 120, the proposed EfficientGCN-B4 baseline outperforms other SOTA methods, e.g., achieving 92.1% accuracy on the cross-subject benchmark of NTU 60 dataset, while being 5.82× smaller and 5.85× faster than MS-G3D, which is one of the SOTA methods. The source code in PyTorch version and the pretrained models are available at https://github.com/yfsong0709/EfficientGCNv1.
39 citations
TL;DR: Zhang et al. as discussed by the authors proposed PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment.
Abstract: The predictive learning of spatiotemporal sequences aims to generate future images by learning from the historical context, where the visual dynamics are believed to have modular structures that can be learned with compositional subsystems. This paper models these structures by presenting PredRNN, a new recurrent network, in which a pair of memory cells are explicitly decoupled, operate in nearly independent transition manners, and finally form unified representations of the complex environment. Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned visual dynamics at different levels of RNNs to communicate. It also leverages a memory decoupling loss to keep the memory cells from learning redundant features. We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. We provide detailed ablation studies to verify the effectiveness of each component. Our approach is shown to obtain highly competitive results on five datasets for both action-free and action-conditioned predictive learning scenarios.
34 citations
TL;DR: HiGCIN as mentioned in this paper proposes a hierarchical graph-based cross-inference network to simultaneously capture the latent spatio-temporal dependencies among body regions and persons, and two modules are designed to extract and refine features for group activities at each level.
Abstract: Group activity recognition (GAR) is a challenging task aimed at recognizing the behavior of a group of people. It is a complex inference process in which visual cues collected from individuals are integrated into the final prediction, being aware of the interaction between them. This paper goes one step further beyond the existing approaches by designing a Hierarchical Graph-based Cross Inference Network (HiGCIN), in which three levels of information, i.e., the body-region level, person level, and group-activity level, are constructed, learned, and inferred in an end-to-end manner. Primarily, we present a generic Cross Inference Block (CIB), which is able to concurrently capture the latent spatiotemporal dependencies among body regions and persons. Based on the CIB, two modules are designed to extract and refine features for group activities at each level. Experiments on two popular benchmarks verify the effectiveness of our approach, particularly in the ability to infer with multilevel visual cues. In addition, training our approach does not require individual action labels to be provided, which greatly reduces the amount of labor required in data annotation.
33 citations
TL;DR: Deep ROC analysis as discussed by the authors measures performance in multiple groups of predicted risk (like calibration), or groups of true positive rate or false positive rate, and provides a new interpretation of AUC in whole or part, as balanced average accuracy, relevant to individuals instead of pairs.
Abstract: Optimal performance is desired for decision-making in any field with binary classifiers and diagnostic tests, however common performance measures lack depth in information. The area under the receiver operating characteristic curve (AUC) and the area under the precision recall curve are too general because they evaluate all decision thresholds including unrealistic ones. Conversely, accuracy, sensitivity, specificity, positive predictive value and the F1 score are too specific—they are measured at a single threshold that is optimal for some instances, but not others, which is not equitable. In between both approaches, we propose deep ROC analysis to measure performance in multiple groups of predicted risk (like calibration), or groups of true positive rate or false positive rate. In each group, we measure the group AUC (properly), normalized group AUC, and averages of: sensitivity, specificity, positive and negative predictive value, and likelihood ratio positive and negative. The measurements can be compared between groups, to whole measures, to point measures and between models. We also provide a new interpretation of AUC in whole or part, as balanced average accuracy, relevant to individuals instead of pairs. We evaluate models in three case studies using our method and Python toolkit and confirm its utility.
TL;DR: Wang et al. as mentioned in this paper proposed to use second-order pooling as graph pooling, which naturally solves the above challenges and is able to use information from all nodes and collect secondorder statistics, making it more powerful.
Abstract: Graph neural networks have achieved great success in learning node representations for graph tasks such as node classification and link prediction. Graph representation learning requires graph pooling to obtain graph representations from node representations. It is challenging to develop graph pooling methods due to the variable sizes and isomorphic structures of graphs. In this work, we propose to use second-order pooling as graph pooling, which naturally solves the above challenges. In addition, compared to existing graph pooling methods, second-order pooling is able to use information from all nodes and collect second-order statistics, making it more powerful. We show that direct use of second-order pooling with graph neural networks leads to practical problems. To overcome these problems, we propose two novel global graph pooling methods based on second-order pooling; namely, bilinear mapping and attentional second-order pooling. In addition, we extend attentional second-order pooling to hierarchical graph pooling for more flexible use in GNNs. We perform thorough experiments on graph classification tasks to demonstrate the effectiveness and superiority of our proposed methods. Experimental results show that our methods improve the performance significantly and consistently.
TL;DR: Wang et al. as discussed by the authors proposed a contrastive learning paradigm which uses the available pairs as positives and randomly chooses some cross-view samples as negatives to reduce the influence of the false negatives caused by random sampling.
Abstract: The success of existing multi-view clustering methods heavily relies on the assumption of view consistency and instance completeness, referred to as the complete information. However, these two assumptions would be inevitably violated in data collection and transmission, thus leading to the so-called Partially View-unaligned Problem (PVP) and Partially Sample-missing Problem (PSP). To overcome such incomplete information challenges, we propose a novel method, termed robuSt mUlti-view clusteRing with incomplEte information (SURE), which solves PVP and PSP under a unified framework. In brief, SURE is a novel contrastive learning paradigm which uses the available pairs as positives and randomly chooses some cross-view samples as negatives. To reduce the influence of the false negatives caused by random sampling, SURE is with a noise-robust contrastive loss that theoretically and empirically mitigates or even eliminates the influence of the false negatives. To the best of our knowledge, this could be the first successful attempt that simultaneously handles PVP and PSP using a unified solution. In addition, this could be one of the first studies on the noisy correspondence problem (i.e., the false negatives) which is a novel paradigm of noisy labels. Extensive experiments demonstrate the effectiveness and efficiency of SURE comparing with 10 state-of-the-art approaches on the multi-view clustering task.
TL;DR: Zhang et al. as discussed by the authors proposed a symbiotic attention mechanism to encourage the mutual interaction between the two branches and select the most action-relevant candidates for classification, which achieved the state-of-the-art on the largest egocentric video dataset.
Abstract: In this paper, we propose to tackle egocentric action recognition by suppressing background distractors and enhancing action-relevant interactions. The existing approaches usually utilize two independent branches to recognize egocentric actions, i.e., a verb branch and a noun branch. However, the mechanism to suppress distracting objects and exploit local human-object correlations is missing. To this end, we introduce two extra sources of information, i.e., the candidate objects spatial location and their discriminative features, to enable concentration on the occurring interactions. We design a Symbiotic Attention with Object-centric feature Alignment framework (SAOA) to provide meticulous reasoning between the actor and the environment. First, we introduce an object-centric feature alignment method to inject the local object features to the verb branch and noun branch. Second, we propose a symbiotic attention mechanism to encourage the mutual interaction between the two branches and select the most action-relevant candidates for classification. The framework benefits from the communication among the verb branch, the noun branch, and the local object information. Experiments based on different backbones and modalities demonstrate the effectiveness of our method. Notably, our framework achieves the state-of-the-art on the largest egocentric video dataset.
TL;DR: Li et al. as mentioned in this paper proposed a new reinforced weighted multi-relational graph neural network framework by using a Multi-agent Reinforcement Learning algorithm to select optimal aggregation thresholds across different relations/edges to learn social message embeddings.
Abstract: Detecting hot social events (e.g., political scandal, momentous meetings, natural hazards, etc.) from social messages is crucial as it highlights significant happenings to help people understand the real world. On account of the streaming nature of social messages, incremental social event detection models in acquiring, preserving, and updating messages over time have attracted great attention. However, the challenge is that the existing event detection methods towards streaming social messages are generally confronted with ambiguous events features, dispersive text contents, and multiple languages, and hence result in low accuracy and generalization ability. In this paper, we present a novel reinForced, incremental and cross-lingual social Event detection architecture, namely FinEvent, from streaming social messages. Concretely, we first model social messages into heterogeneous graphs integrating both rich meta-semantics and diverse meta-relations, and convert them to weighted multi-relational message graphs. Second, we propose a new reinforced weighted multi-relational graph neural network framework by using a Multi-agent Reinforcement Learning algorithm to select optimal aggregation thresholds across different relations/edges to learn social message embeddings. To solve the long-tail problem in social event detection, a balanced sampling strategy guided Contrastive Learning mechanism is designed for incremental social message representation learning. Third, a new Deep Reinforcement Learning guided density-based spatial clustering model is designed to select the optimal minimum number of samples required to form a cluster and optimal minimum distance between two clusters in social event detection tasks. Finally, we implement incremental social message representation learning based on knowledge preservation on the graph neural network and achieve the transferring cross-lingual social event detection. We conduct extensive experiments to evaluate the FinEvent on Twitter streams, demonstrating a significant and consistent improvement in model quality with 14%-118%, 8%-170%, and 2%-21% increases in performance on offline, online, and cross-lingual social event detection tasks.
TL;DR: Deep GCN as discussed by the authors transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs, achieving promising performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs.
Abstract: Convolutional Neural Networks (CNNs) have been very successful at solving a variety of computer vision tasks such as object classification and detection, semantic segmentation, activity understanding, to name just a few. One key enabling factor for their great performance has been the ability to train very deep networks. Despite their huge success in many tasks, CNNs do not work well with non-Euclidean data, which is prevalent in many real-world applications. Graph Convolutional Networks (GCNs) offer an alternative that allows for non-Eucledian data input to a neural network. While GCNs already achieve encouraging results, they are currently limited to architectures with a relatively small number of layers, primarily due to vanishing gradients during training. This work transfers concepts such as residual/dense connections and dilated convolutions from CNNs to GCNs in order to successfully train very deep GCNs. We show the benefit of using deep GCNs (with as many as 112 layers) experimentally across various datasets and tasks. Specifically, we achieve very promising performance in part segmentation and semantic segmentation on point clouds and in node classification of protein functions across biological protein-protein interaction (PPI) graphs. We believe that the insights in this work will open avenues for future research on GCNs and their application to further tasks not explored in this paper. The source code for this work is available at https://github.com/lightaime/deep_gcns_torch and https://github.com/lightaime/deep_gcns for PyTorch and TensorFlow implementation respectively.
TL;DR: A recent survey of scene graphs can be found in this paper , where the authors present a survey of the scene graph-based approaches to image captioning and visual question answering tasks.
Abstract: Scene graph is a structured representation of a scene that can clearly express the objects, attributes, and relationships between objects in the scene. As computer vision technology continues to develop, people are no longer satisfied with simply detecting and recognizing objects in images; instead, people look forward to a higher level of understanding and reasoning about visual scenes. For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content. Alternatively, we might want the machine to tell us what the little girl in the image is doing (Visual Question Answering (VQA)), or even remove the dog from the image and find similar images (image editing and retrieval), etc. These tasks require a higher level of understanding and reasoning for image vision tasks. The scene graph is just such a powerful tool for scene understanding. Therefore, scene graphs have attracted the attention of a large number of researchers, and related research is often cross-modal, complex, and rapidly developing. However, no relatively systematic survey of scene graphs exists at present.
TL;DR: In this article , Momentum-Net uses momentum terms in extrapolation modules, and noniterative MBIR modules at each iteration by using majorizers, where each iteration of MomentumNet consists of three core modules: image refining, extrapolation, and mBIR.
Abstract: Iterative neural networks (INN) are rapidly gaining attention for solving inverse problems in imaging, image processing, and computer vision. INNs combine regression NNs and an iterative model-based image reconstruction (MBIR) algorithm, often leading to both good generalization capability and outperforming reconstruction quality over existing MBIR optimization models. This paper proposes the first fast and convergent INN architecture, Momentum-Net, by generalizing a block-wise MBIR algorithm that uses momentum and majorizers with regression NNs. For fast MBIR, Momentum-Net uses momentum terms in extrapolation modules, and noniterative MBIR modules at each iteration by using majorizers, where each iteration of Momentum-Net consists of three core modules: image refining, extrapolation, and MBIR. Momentum-Net guarantees convergence to a fixed-point for general differentiable (non)convex MBIR functions (or data-fit terms) and convex feasible sets, under two asymptomatic conditions. To consider data-fit variations across training and testing samples, we also propose a regularization parameter selection scheme based on the "spectral spread" of majorization matrices. Numerical experiments for light-field photography using a focal stack and sparse-view computational tomography demonstrate that, given identical regression NN architectures, Momentum-Net significantly improves MBIR speed and accuracy over several existing INNs; it significantly improves reconstruction quality compared to a state-of-the-art MBIR method in each application.
TL;DR: Zhang et al. as discussed by the authors used deep neural networks to learn the node and edge feature, as well as the affinity model for graph matching in an end-to-end fashion, where the learning is supervised by combinatorial permutation loss over nodes.
Abstract: Graph matching aims to establish node correspondence between two graphs, which has been a fundamental problem for its NP-hard nature. One practical consideration is the effective modeling of the affinity function in the presence of noise, such that the mathematically optimal matching result is also physically meaningful. This paper resorts to deep neural networks to learn the node and edge feature, as well as the affinity model for graph matching in an end-to-end fashion. The learning is supervised by combinatorial permutation loss over nodes. Specifically, the parameters belong to convolutional neural networks for image feature extraction, graph neural networks for node embedding that convert the structural (beyond second-order) information into node-wise features that leads to a linear assignment problem, as well as the affinity kernel between two graphs. Our approach enjoys flexibility in that the permutation loss is agnostic to the number of nodes, and the embedding model is shared among nodes such that the network can deal with varying numbers of nodes for both training and inference. Moreover, our network is class-agnostic. Experimental results on extensive benchmarks show its state-of-the-art performance. It bears some generalization capability across categories and datasets, and is capable for robust matching against outliers.
TL;DR: A comprehensive overview of breakthroughs and recent developments in gait recognition with deep learning can be found in this article , where the authors present broad topics including datasets, test protocols, state-of-the-art solutions, challenges, and future research directions.
Abstract: Gait recognition is an appealing biometric modality which aims to identify individuals based on the way they walk. Deep learning has reshaped the research landscape in this area since 2015 through the ability to automatically learn discriminative representations. Gait recognition methods based on deep learning now dominate the state-of-the-art in the field and have fostered real-world applications. In this paper, we present a comprehensive overview of breakthroughs and recent developments in gait recognition with deep learning, and cover broad topics including datasets, test protocols, state-of-the-art solutions, challenges, and future research directions. We first review the commonly used gait datasets along with the principles designed for evaluating them. We then propose a novel taxonomy made up of four separate dimensions namely body representation, temporal representation, feature representation, and neural architecture, to help characterize and organize the research landscape and literature in this area. Following our proposed taxonomy, a comprehensive survey of gait recognition methods using deep learning is presented with discussions on their performances, characteristics, advantages, and limitations. We conclude this survey with a discussion on current challenges and mention a number of promising directions for future research in gait recognition.
TL;DR: Wang et al. as discussed by the authors proposed a generic disentangling mechanism to disentangle spatial and angular information for light field image processing, which can well incorporate the LF structure prior and effectively handle 4D LF data.
Abstract: Light field (LF) cameras record both intensity and directions of light rays, and encode 3D scenes into 4D LF images. Recently, many convolutional neural networks (CNNs) have been proposed for various LF image processing tasks. However, it is challenging for CNNs to effectively process LF images since the spatial and angular information are highly inter-twined with varying disparities. In this paper, we propose a generic mechanism to disentangle these coupled information for LF image processing. Specifically, we first design a class of domain-specific convolutions to disentangle LFs from different dimensions, and then leverage these disentangled features by designing task-specific modules. Our disentangling mechanism can well incorporate the LF structure prior and effectively handle 4D LF data. Based on the proposed mechanism, we develop three networks (i.e., DistgSSR, DistgASR and DistgDisp) for spatial super-resolution, angular super-resolution and disparity estimation. Experimental results show that our networks achieve state-of-the-art performance on all these three tasks, which demonstrates the effectiveness, efficiency, and generality of our disentangling mechanism. Project page: https://yingqianwang.github.io/DistgLF/.
TL;DR: A survey of hand-based FV applications can be found in this paper , where the authors categorize the existing approaches into: localization, interpretation, and application (e.g., systems that used egocentric hand cues for solving a specific problem).
Abstract: Egocentric vision (a.k.a. first-person vision–FPV) applications have thrived over the past few years, thanks to the availability of affordable wearable cameras and large annotated datasets. The position of the wearable camera (usually mounted on the head) allows recording exactly what the camera wearers have in front of them, in particular hands and manipulated objects. This intrinsic advantage enables the study of the hands from multiple perspectives: localizing hands and their parts within the images; understanding what actions and activities the hands are involved in; and developing human-computer interfaces that rely on hand gestures. In this survey, we review the literature that focuses on the hands using egocentric vision, categorizing the existing approaches into: localization (where are the hands or parts of them?); interpretation (what are the hands doing?); and application (e.g., systems that used egocentric hand cues for solving a specific problem). Moreover, a list of the most prominent datasets with hand-based annotations is provided.
TL;DR: In this paper , a probabilistic variable is used to model the participant's gaze as a variable and the distribution of the variable is modeled using stochastic units in a deep network.
Abstract: We address the task of jointly determining what a person is doing and where they are looking based on the analysis of video captured by a headworn camera. To facilitate our research, we first introduce the EGTEA Gaze+ dataset. Our dataset comes with videos, gaze tracking data, hand masks and action annotations, thereby providing the most comprehensive benchmark for First Person Vision (FPV). Moving beyond the dataset, we propose a novel deep model for joint gaze estimation and action recognition in FPV. Our method describes the participant's gaze as a probabilistic variable and models its distribution using stochastic units in a deep network. We further sample from these stochastic units, generating an attention map to guide the aggregation of visual features for action recognition. Our method is evaluated on our EGTEA Gaze+ dataset and achieves a performance level that exceeds the state-of-the-art by a significant margin. More importantly, we demonstrate that our model can be applied to larger scale FPV dataset—EPIC-Kitchens even without using gaze, offering new state-of-the-art results on FPV action recognition.
TL;DR: A comprehensive overview of image captioning approaches can be found in this article , where the authors quantitatively compare many relevant state-of-the-art approaches to identify the most impactful technical innovations in architectures and training strategies.
Abstract: Connecting Vision and Language plays an essential role in Generative Intelligence. For this reason, large research efforts have been devoted to image captioning, i.e. describing images with syntactically and semantically meaningful sentences. Starting from 2015 the task has generally been addressed with pipelines composed of a visual encoder and a language model for text generation. During these years, both components have evolved considerably through the exploitation of object regions, attributes, the introduction of multi-modal connections, fully-attentive approaches, and BERT-like early-fusion strategies. However, regardless of the impressive results, research in image captioning has not reached a conclusive answer yet. This work aims at providing a comprehensive overview of image captioning approaches, from visual encoding and text generation to training strategies, datasets, and evaluation metrics. In this respect, we quantitatively compare many relevant state-of-the-art approaches to identify the most impactful technical innovations in architectures and training strategies. Moreover, many variants of the problem and its open challenges are discussed. The final goal of this work is to serve as a tool for understanding the existing literature and highlighting the future directions for a research area where Computer Vision and Natural Language Processing can find an optimal synergy.
TL;DR: In this paper , the authors present a new egocentric dataset collected from a social mobile manipulator, which includes 64 minutes of annotated multimodal sensor data, including stereo cylindrical 360° RGB video at 15 fps, 3D point clouds from two 16 planar rays Velodyne LiDARs, line 3D points from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360° spherical image from a fisheye camera and encoder values from the robot's wheels.
Abstract: We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360 ° RGB video at 15 fps, 3D point clouds from two 16 planar rays Velodyne LiDARs, line 3D point clouds from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360 ° spherical image from a fisheye camera and encoder values from the robot's wheels. Our dataset incorporates data from traditionally underrepresented scenes such as indoor environments and pedestrian areas, all from the ego-perspective of the robot, both stationary and navigating. The dataset has been annotated with over 2.4 million bounding boxes spread over five individual cameras and 1.8 million associated 3D cuboids around all people in the scenes totaling over 3500 time consistent trajectories. Together with our dataset and the annotations, we launch a benchmark and metrics for 2D and 3D person detection and tracking. With this dataset, which we plan on extending with further types of annotation in the future, we hope to provide a new source of data and a test-bench for research in the areas of egocentric robot vision, autonomous navigation, and all perceptual tasks around social robotics in human environments.
TL;DR: In this article , a Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network is proposed.
Abstract: Recently, segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field, because of their superiority in detecting the text instances of arbitrary shapes and extreme aspect ratios, profiting from the pixel-level descriptions. However, the vast majority of the existing segmentation-based approaches are limited to their complex post-processing algorithms and the scale robustness of their segmentation models, where the post-processing algorithms are not only isolated to the model optimization but also time-consuming and the scale robustness is usually strengthened by fusing multi-scale feature maps directly. In this paper, we propose a Differentiable Binarization (DB) module that integrates the binarization process, one of the most important steps in the post-processing procedure, into a segmentation network. Optimized along with the proposed DB module, the segmentation network can produce more accurate results, which enhances the accuracy of text detection with a simple pipeline. Furthermore, an efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively. By incorporating the proposed DB and ASF with the segmentation network, our proposed scene text detector consistently achieves state-of-the-art results, in terms of both detection accuracy and speed, on five standard benchmarks.
TL;DR: CensNet as discussed by the authors is a general graph embedding framework, which embeds both nodes and edges to a latent feature space by using line graph of the original undirected graph, and two novel graph convolution operations are proposed for feature propagation.
Abstract: Graph, as an important data representation, is ubiquitous in many real world applications ranging from social network analysis to biology. How to correctly and effectively learn and extract information from graph is essential for a large number of machine learning tasks. Graph embedding is a way to transform and encode the data structure in high dimensional and non-euclidean feature space to a low dimensional and structural space, which is easily exploited by other machine learning algorithms. We have witnessed a huge surge of such embedding methods, from statistical approaches to recent deep learning methods such as the graph convolutional networks (GCN). Deep learning approaches usually outperform the traditional methods in most graph learning benchmarks by building an end-to-end learning framework to optimize the loss function directly. However, most of the existing GCN methods can only perform convolution operations with node features, while ignoring the handy information in edge features, such as relations in knowledge graphs. To address this problem, we present CensNet, Convolution with Edge-Node Switching graph neural network, for learning tasks in graph-structured data with both node and edge features. CensNet is a general graph embedding framework, which embeds both nodes and edges to a latent feature space. By using line graph of the original undirected graph, the role of nodes and edges are switched, and two novel graph convolution operations are proposed for feature propagation. Experimental results on real-world academic citation networks and quantum chemistry graphs show that our approach achieves or matches the state-of-the-art performance in four graph learning tasks, including semi-supervised node classification, multi-task graph classification, graph regression, and link prediction.
TL;DR: Qibin et al. as discussed by the authors proposed Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition, which separately encodes the feature representations along the height and width dimensions with linear projections.
Abstract: In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections. This allows Vision Permutator to capture long-range dependencies and meanwhile avoid the attention building process in transformers. The outputs are then aggregated in a mutually complementing manner to form expressive representations. We show that our Vision Permutators are formidable competitors to convolutional neural networks (CNNs) and vision transformers. Without the dependence on spatial convolutions or attention mechanisms, Vision Permutator achieves 81.5% top-1 accuracy on ImageNet without extra large-scale training data (e.g., ImageNet-22k) using only 25M learnable parameters, which is much better than most CNNs and vision transformers under the same model size constraint. When scaling up to 88M, it attains 83.2% top-1 accuracy, greatly improving the performance of recent state-of-the-art MLP-like networks for visual recognition. We hope this work could encourage research on rethinking the way of encoding spatial information and facilitate the development of MLP-like models. PyTorch/MindSpore/Jittor code is available at https://github.com/Andrew-Qibin/VisionPermutator .
TL;DR: In this paper , a survey of different ways of training GNNs using self-supervised learning (SSL) is provided, which is a new paradigm for making use of large amounts of unlabeled samples.
Abstract: Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled samples. SSL has achieved promising performance on natural language and image learning tasks. Recently, there is a trend to extend such success to graph data using graph neural networks (GNNs). In this survey, we provide a unified review of different ways of training GNNs using SSL. Specifically, we categorize SSL methods into contrastive and predictive models. In either category, we provide a unified framework for methods as well as how these methods differ in each component under the framework. Our unified treatment of SSL methods for GNNs sheds light on the similarities and differences of various methods, setting the stage for developing new methods and algorithms. We also summarize different SSL settings and the corresponding datasets used in each setting. To facilitate methodological development and empirical comparison, we develop a standardized testbed for SSL in GNNs, including implementations of common baseline methods, datasets, and evaluation metrics.
TL;DR: In this article , the authors systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space.
Abstract: As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy human supervision over the data collection process exposes organizations to security vulnerabilities; training data can be manipulated to control and degrade the downstream behaviors of learned models. The goal of this work is to systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space.