In open set recognition, deep neural networks encounter object classes that were unknown during training. Existing open set classifiers distinguish between known and unknown classes by measuring distance in a network's logit space, assuming that known classes cluster closer to the training data than unknown classes. However, this approach is applied post-hoc to networks trained with cross-entropy loss, which does not guarantee this clustering behaviour. To overcome this limitation, we introduce the Class Anchor Clustering (CAC) loss. CAC is a distance-based loss that explicitly trains known classes to form tight clusters around anchored class-dependent centres in the logit space. We show that training with CAC achieves state-of-the-art performance for distance-based open set classifiers on all six standard benchmark datasets, with a 15.2% AUROC increase on the challenging TinyImageNet, without sacrificing classification accuracy. We also show that our anchored class centres achieve higher open set performance than learnt class centres, particularly on object-based datasets and large numbers of training classes.
Hyperspectral image (HSI) clustering, which aims at dividing hyperspectral pixels into clusters, has drawn significant attention in practical applications. Recently, many graph-based clustering methods, which construct an adjacent graph to model the data relationship, have shown dominant performance. However, the high dimensionality of HSI data makes it hard to construct the pairwise adjacent graph. Besides, abundant spatial structures are often overlooked during the clustering procedure. In order to better handle the high dimensionality problem and preserve the spatial structures, this paper …
Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box regression, or discard sequence learning. To tackle these issues, we propose a pair of coupling modules, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to form feature sequences. The proposed CAM localizes the text in a shape-insensitive way by design by anchoring charact…
German Research Center for Artificial Intelligence（德国人工智能研究中心）；University of Kaiserslautern（凯泽斯劳滕大学）；Mindgrage；Luleå University of Technology（吕勒奥理工大学）；Bilojix Soft Technologies（Bilojix软件技术公司）
This paper presents the novel approach towards table structure recognition by leveraging the guided anchors. The concept differs from current state-of-the-art approaches for table structure recognition that naively apply object detection methods. In contrast to prior techniques, first, we estimate the viable anchors for table structure recognition. Subsequently, these anchors are exploited to locate the rows and columns in tabular images. Furthermore, the paper introduces a simple and effective method that improves the results by using tabular layouts in realistic scenarios. The proposed metho…
Beijing Jiaotong University（北京交通大学）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）
In zero-shot learning (ZSL), the samples to be classified are usually projected into side information templates such as attributes. However, the irregular distribution of templates makes classification results confused. To alleviate this issue, we propose a novel framework called Discriminative Anchor Generation and Distribution Alignment Model (DAGDA). Firstly, in order to rectify the distribution of original templates, a diffusion based graph convolutional network, which can explicitly model the interaction between class and side information, is proposed to produce discriminative anchors. Se…
One-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning
National Key Laboratory of Human–Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；Xi’an Jiaotong University（西安交通大学）；School of Electrical and Electronic Engineering（电子工程学院）；Nanyang Technological University（南洋理工大学）
Detecting objects in a two-dimensional setting is often insufficient in the context of real-life applications where the surrounding environment needs to be accurately recognized and oriented in three-dimension (3D), such as in the case of autonomous driving vehicles. Therefore, accurately and efficiently detecting objects in the three-dimensional setting is becoming increasingly relevant to a wide range of industrial applications, and thus is progressively attracting the attention of researchers. Building systems to detect objects in 3D is a challenging task though, because it relies on the mu…
Enhancing Multi-Camera People Tracking with Anchor-Guided Clustering and Spatio-Temporal Consistency ID Re-Assignment
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子与电信研究所）；National Center for High-Performance Computing（国家高性能计算中心）
提出一种结合锚定引导聚类与时空一致性的多摄像机多人员跟踪方法，在CVPR AI City Challenge 2023上以95.36% IDF1获第一名。
Recently, several clustering algorithms have been used to solve variety of problems from different discipline. This dissertation aims to address different challenging tasks in computer vision and pattern recognition by casting the problems as a clustering problem. We proposed novel approaches to solve multi-target tracking, visual geo-localization and outlier detection problems using a unified underlining clustering framework, i.e., dominant set clustering and its extensions, and presented a superior result over several state-of-the-art approaches.
Anchor-based Multi-view Subspace Clustering with Hierarchical Feature Descent
College of Computer, National University of Defense Technology（国防科技大学计算机学院）；Intelligent Game and Decision Lab（智能游戏与决策实验室）；College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学智能科学学院）
South China University of Technology（华南理工大学）；Institute for Infocomm Research（资讯通信研究院）；Peng Cheng Laboratory（鹏城实验室）
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT) prot…
Free Lunch for Gait Recognition: A Novel Relation Descriptor
University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Normal University（北京师范大学）
Skeleton sequences are widely used for action recognition task due to its lightweight and compact characteristics. Recent graph convolutional network (GCN) approaches have achieved great success for skeleton-based action recognition since its grateful modeling ability of non-Euclidean data. GCN is able to utilize the short-range joint dependencies while lack to directly model the distant joints relations that are vital to distinguishing various actions. Thus, many GCN approaches try to employ hierarchical mechanism to aggregate wider-range neighborhood information. We propose a novel self-atte…
McGill University（麦吉尔大学）；Ca’ Foscari University of Venice（威尼斯大学）
View based strategies for 3D object recognition have proven to be very successful. The state-of-the-art methods now achieve over 90% correct category level recognition performance on appearance images. We improve upon these methods by introducing a view clustering and pooling layer based on dominant sets. The key idea is to pool information from views which are similar and thus belong to the same cluster. The pooled feature vectors are then fed as inputs to the same layer, in a recurrent fashion. This recurrent clustering and pooling module, when inserted in an off-the-shelf pretrained CNN, bo…
National Institute of Technology, Durgapur（印度杜尔加普尔国家理工学院）
Facial expressions convey non-verbal cues, which play an important role in interpersonal relations. Automatic recognition of human face based on facial expression can be an important component of natural human-machine interface. It may also be used in behavioural science. Although human can recognize the face practically without any effort, but reliable face recognition by machine is a challenge. This paper presents a new approach for recognizing the face of a person considering the expressions of the same human face at different instances of time. This methodology is developed combining Eigen…
University of Chinese Academy of Sciences（中国科学院大学）；Huawei Inc（华为公司）；Huazhong University of Science and Technology（华中科技大学）
Object detection, instance segmentation, and pose estimation are popular visual recognition tasks which require localizing the object by internal or boundary landmarks. This paper summarizes these tasks as location-sensitive visual recognition and proposes a unified solution named location-sensitive network (LSNet). Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object. The key to optimizing the LSNet lies in the ability of fitting various scales, for which we design a novel loss function named…
I2R, A-STAR（A*STAR信息通信研究所）；South China University of Technology（华南理工大学）；Southwest Jiaotong University（西南交通大学）
Deploying models on target domain data subject to distribution shift requires adaptation. Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required. Despite many efforts into TTT, there is a confusion over the experimental settings, thus leading to unfair comparisons. In this work, we first revisit TTT assumptions and categorize TTT protocols by two key factors. Among the multiple protocols, we adopt a realistic sequential test-time training (sTTT)…
Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC
Xi'an Jiaotong University（西安交通大学）；Queen Mary University of London（伦敦女王玛丽大学）；Center for Multimodal AI（多模态人工智能中心）；Digital Environment Research Institute（数字环境研究院）
Amirkabir University of Technology（阿米卡比尔理工大学）；Université de Mons（蒙斯大学）；Faculté Polytechnique（理工学院）
Sparse subspace clustering (SSC) is one of the current state-of-the-art methods for partitioning data points into the union of subspaces, with strong theoretical guarantees. However, it is not practical for large data sets as it requires solving a LASSO problem for each data point, where the number of variables in each LASSO problem is the number of data points. To improve the scalability of SSC, we propose to select a few sets of anchor points using a randomized hierarchical clustering method, and, for each set of anchor points, solve the LASSO problems for each data point allowing only ancho…
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等理工学院）；Universidad de Zaragoza（萨拉戈萨大学）；Bitbrain Technologies（Bitbrain技术公司）；Politecnico di Milano（米兰理工大学）
One-shot action recognition aims to recognize new action categories from a single reference example, typically referred to as the anchor example. This work presents a novel approach for one-shot action recognition in the wild that computes motion representations robust to variable kinematic conditions. One-shot action recognition is then performed by evaluating anchor and target motion representations. We also develop a set of complementary steps that boost the action recognition performance in the most challenging scenarios. Our approach is evaluated on the public NTU-120 one-shot action reco…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Peking University（北京大学）
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse localization of objects and leads to a correspondingly coarse extraction of object features. In this paper, we present \textbf{RepPoints} (representative points), a new finer representation of objects as a set of sample points useful for both localization and recognition. Given ground truth localization and recognition targets for training, RepPoints learn to…
University of Science and Technology of China（中国科学技术大学）
In this work, we consider the problem of cross-domain 3D action recognition in the open-set setting, which has been rarely explored before. Specifically, there is a source domain and a target domain that contain the skeleton sequences with different styles and categories, and our purpose is to cluster the target data by utilizing the labeled source data and unlabeled target data. For such a challenging task, this paper presents a novel approach dubbed CoDT to collaboratively cluster the domain-shared features and target-specific features. CoDT consists of two parallel branches. One branch aims…
Artist, year and style classification of fine-art paintings are generally achieved using standard image classification methods, image segmentation, or more recently, convolutional neural networks (CNNs). This works aims to use newly developed face recognition methods such as FaceNet that use CNNs to cluster fine-art paintings using the extracted faces in the paintings, which are found abundantly. A dataset consisting of over 80,000 paintings from over 1000 artists is chosen, and three separate face recognition and clustering tasks are performed. The produced clusters are analyzed by the file n…
Unsupervised Domain Adaptation with Dynamic Clustering and Contrastive Refinement for Gait Recognition
School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；School of Electronics and Computer Science, University of Southampton（南安普顿大学电子与计算机科学学院）
Beijing University of Posts and Telecommunications（北京邮电大学）
Despite great progress in face recognition tasks achieved by deep convolution neural networks (CNNs), these models often face challenges in real world tasks where training images gathered from Internet are different from test images because of different lighting condition, pose and image quality. These factors increase domain discrepancy between training (source domain) and testing (target domain) database and make the learnt models degenerate in application. Meanwhile, due to lack of labeled target data, directly fine-tuning the pre-learnt models becomes intractable and impractical. In this p…
RRPN is among the outstanding scene text detection approaches, but the manually-designed anchor and coarse proposal refinement make the performance still far from perfection. In this paper, we propose RRPN++ to exploit the potential of RRPN-based model by several improvements. Based on RRPN, we propose the Anchor-free Pyramid Proposal Networks (APPN) to generate first-stage proposals, which adopts the anchor-free design to reduce proposal number and accelerate the inference speed. In our second stage, both the detection branch and the recognition branch are incorporated to perform multi-task l…
In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first propose a semantic scene descriptor that jointly captures the subtle differences between fine-grained scenes, while being robust to varying object configurations across domains. We model the occurrence patterns of objects in scenes, capturing the informativeness and discriminability of each object for each scene. We then transform such occurrences into scene prob…
Xidian University（西安电子科技大学）；School of Electronic Engineering, Xidian University（西安电子科技大学电子工程学院）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
Graph-based multi-view clustering has become an active topic due to the efficiency in characterizing both the complex structure and relationship between multimedia data. However, existing methods have the following shortcomings: (1) They are inefficient or even fail for graph learning in large scale due to the graph construction and eigen-decomposition. (2) They cannot well exploit both the complementary information and spatial structure embedded in graphs of different views. To well exploit complementary information and tackle the scalability issue plaguing graph-based multi-view clustering, …
Microsoft AI R&D Center（微软人工智能研发中心）；Microsoft Cloud and AI（微软云与人工智能）
Due to the rising concern of data privacy, it's reasonable to assume the local client data can't be transferred to a centralized server, nor their associated identity label is provided. To support continuous learning and fill the last-mile quality gap, we introduce a new problem setup called Local-Adaptive Face Recognition (LaFR). Leveraging the environment-specific local data after the deployment of the initial global model, LaFR aims at getting optimal performance by training local-adapted models automatically and un-supervisely, as opposed to fixing their initial global model. We achieve th…
Amazon（亚马逊）；NEC Labs America（NEC美国实验室）；University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；Google（谷歌）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）
While deep face recognition has benefited significantly from large-scale labeled data, current research is focused on leveraging unlabeled data to further boost performance, reducing the cost of human annotation. Prior work has mostly been in controlled settings, where the labeled and unlabeled data sets have no overlapping identities by construction. This is not realistic in large-scale face recognition, where one must contend with such overlaps, the frequency of which increases with the volume of data. Ignoring identity overlap leads to significant labeling noise, as data from the same ident…
University of South Carolina（南卡罗来纳大学）；Chongqing University（重庆大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）；University of Houston（休斯顿大学）；University of Macau（澳门大学）
This paper introduces a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between source and target domain, the proposed method is more flexible to capture individual class variations across domains. By adopting a natural and widely used assumption -- "the data samples from the same class should lay on a low-dimensional subspace, even if they come from different domains", the proposed method circumvents the limitation of the global domain shift, and solves the cross-domain recogni…
Despite significant recent advances in the field of face recognition, implementing face verification and recognition efficiently at scale presents serious challenges to current approaches. In this paper we present a system, called FaceNet, that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure of face similarity. Once this space has been produced, tasks such as face recognition, verification and clustering can be easily implemented using standard techniques with FaceNet embeddings as feature vectors. Our method uses a deep …
The University of Kansas（堪萨斯大学）；Ryerson University（瑞尔森大学）
The paper proposes a semantic clustering based deduction learning by mimicking the learning and thinking process of human brains. Human beings can make judgments based on experience and cognition, and as a result, no one would recognize an unknown animal as a car. Inspired by this observation, we propose to train deep learning models using the clustering prior that can guide the models to learn with the ability of semantic deducing and summarizing from classification attributes, such as a cat belonging to animals while a car pertaining to vehicles. %Specifically, if an image is labeled as a ca…
Carnegie Mellon University（卡内基梅隆大学）；University of Pittsburgh（匹兹堡大学）
Spatio-temporal action recognition has been a challenging task that involves detecting where and when actions occur. Current state-of-the-art action detectors are mostly anchor-based, requiring sensitive anchor designs and huge computations due to calculating large numbers of anchor boxes. Motivated by nascent anchor-free approaches, we propose Point3D, a flexible and computationally efficient network with high precision for spatio-temporal action recognition. Our Point3D consists of a Point Head for action localization and a 3D Head for action classification. Firstly, Point Head is used to tr…
Action recognition is an important problem in multimedia understanding. This paper addresses this problem by building an expressive compositional action model. We model one action instance in the video with an ensemble of spatio-temporal compositions: a number of discrete temporal anchor frames, each of which is further decomposed to a layout of deformable parts. In this way, our model can identify a Spatio-Temporal And-Or Graph (STAOG) to represent the latent structure of actions e.g. triple jumping, swinging and high jumping. The STAOG model comprises four layers: (i) a batch of leaf-nodes i…
ClusVPR: Efficient Visual Place Recognition with Clustering-based Weighted Transformer
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University（上海交通大学图像处理与模式识别研究所）；School of Communication and Electrical Engineering, East China Normal University（华东师范大学通信与电子工程学院）
Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to instances of unseen classes without losing dis-crimination between classes. Neural networks can modelthe complex boundaries between visual classes, which ex-plains their success as supervised models. However, inzero-shot learning, these highly specialized class bound-aries may not transfer well from seen to unseen classes.In this paper we propose a centroid-ba…
Deep learning technology has enabled successful modeling of complex facial features when high quality images are available. Nonetheless, accurate modeling and recognition of human faces in real world scenarios `on the wild' or under adverse conditions remains an open problem. When unconstrained faces are mapped into deep features, variations such as illumination, pose, occlusion, etc., can create inconsistencies in the resultant feature space. Hence, deriving conclusions based on direct associations could lead to degraded performance. This rises the requirement for a basic feature space analys…
École Normale Supérieure（巴黎高等师范学院）；Inria（法国国家信息与自动化研究所）；CIIRC（捷克信息学、机器人与控制论研究所）；Czech Technical University in Prague（布拉格捷克理工大学）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）
Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks. Such applications include person and action recognition, text-to-video alignment, object co-segmentation and colocalization in videos and images. One drawback of discriminative clustering, however, is its limited scalability. We address this issue and propose an online optimization algorithm based on the Block-Coordinate Frank-Wolfe algorithm. We apply the proposed method to the problem of weakly supervised learning of actions and actors from movies together with corresponding movie scripts…
TCFormer: Visual Recognition via Token Clustering Transformer
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；Shanghai AI Laboratory（上海人工智能实验室）；Centre for Perceptual and Interactive Intelligence Limited（感知与交互智能中心有限公司）
This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data. Albeit state-of-the-art approaches designed for this application are all supervised, in this paper we pursue a more challenging direction: Solving the problem with unsupervised learning. To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action's discriminability and a timestamp pruning approach that allow us to better handle the temporal dimension of the data. Through a broad experimenta…
Novustech Services（诺沃斯特科技服务公司）；University of Bucharest（布加勒斯特大学）
In this paper, we study the task of facial expression recognition under strong occlusion. We are particularly interested in cases where 50% of the face is occluded, e.g. when the subject wears a Virtual Reality (VR) headset. While previous studies show that pre-training convolutional neural networks (CNNs) on fully-visible (non-occluded) faces improves the accuracy, we propose to employ knowledge distillation to achieve further improvements. First of all, we employ the classic teacher-student training strategy, in which the teacher is a CNN trained on fully-visible faces and the student is a C…
DAP: Doppler-aware Point Network for Heterogeneous mmWave Action Recognition
Peking University（北京大学）；Huazhong University of Science and Technology（华中科技大学）；DJI Technology Company Ltd.（大疆技术创新有限公司）；Christian-Albrechts-Universität zu Kiel（基尔大学）
Beijing Institute of Technology（北京理工大学）；UC Berkeley（加州大学伯克利分校）
A rapid pattern-recognition approach to characterize driver's curve-negotiating behavior is proposed. To shorten the recognition time and improve the recognition of driving styles, a k-means clustering-based support vector machine ( kMC-SVM) method is developed and used for classifying drivers into two types: aggressive and moderate. First, vehicle speed and throttle opening are treated as the feature parameters to reflect the driving styles. Second, to discriminate driver curve-negotiating behaviors and reduce the number of support vectors, the k-means clustering method is used to extract and…
Institute of Mathematics of the Romanian Academy（罗马尼亚科学院数学研究所）；Faculty of Automatic Control and Computer Science, University Politehnica of Bucharest（布加勒斯特理工大学自动控制与计算机科学学院）；Google Research（谷歌研究院）
Feature selection is an essential problem in computer vision, important for category learning and recognition. Along with the rapid development of a wide variety of visual features and classifiers, there is a growing need for efficient feature selection and combination methods, to construct powerful classifiers for more complex and higher-level recognition tasks. We propose an algorithm that efficiently discovers sparse, compact representations of input features or classifiers, from a vast sea of candidates, with important optimality properties, low computational cost and excellent accuracy in…
It is possible to associate a highly constrained subset of relative 6 DoF poses between two 3D shapes, as long as the local surface orientation, the normal vector, is available at every surface point. Local shape features can be used to find putative point correspondences between the models due to their ability to handle noisy and incomplete data. However, this correspondence set is usually contaminated by outliers in practical scenarios, which has led to many past contributions based on robust detectors such as the Hough transform or RANSAC. The key insight of our work is that a single corres…
Waste recycling is an important way of saving energy and materials in the production process. In general cases recyclable objects are mixed with unrecyclable objects, which raises a need for identification and classification. This paper proposes a convolutional neural network (CNN) model to complete both tasks. The model uses transfer learning from a pretrained Resnet-50 CNN to complete feature extraction. A subsequent fully connected layer for classification was trained on the augmented TrashNet dataset [1]. In the application, sliding-window is used for image segmentation in the pre-classifi…
