Recent advances in Siamese network-based visual tracking methods have enabled high performance on numerous tracking benchmarks. However, extensive scale variations of the target object and distractor objects with similar categories have consistently posed challenges in visual tracking. To address these persisting issues, we propose novel TridentAlign and context embedding modules for Siamese network-based visual tracking methods. The TridentAlign module facilitates adaptability to extensive scale variations and large deformations of the target, where it pools the feature representation of the target object into multiple spatial dimensions to form a feature pyramid, which is then utilized in the region proposal stage. Meanwhile, context embedding module aims to discriminate the target from distractor objects by accounting for the global context information among objects. The context embedding module extracts and embeds the global context information of a given frame into a local feature representation such that the information can be utilized in the final classification stage. Experimental results obtained on multiple benchmark datasets show that the performance of the proposed tracker is comparable to that of state-of-the-art trackers, while the proposed tracker runs at real-time speed.
SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）；SenseTime Computer Vision Research Group（商汤科技计算机视觉研究组）
We propose a unified framework for multi-person pose estimation and tracking. Our framework consists of two main components,~\ie~SpatialNet and TemporalNet. The SpatialNet accomplishes body part detection and part-level data association in a single frame, while the TemporalNet groups human instances in consecutive frames into trajectories. Specifically, besides body part detection heatmaps, SpatialNet also predicts the Keypoint Embedding (KE) and Spatial Instance Embedding (SIE) for body part association. We model the grouping procedure into a differentiable Pose-Guided Grouping (PGG) module t…
KU Leuven（鲁汶大学）；ETH Zurich（苏黎世联邦理工学院）；TRACE vzw（TRACE非营利组织）
3D object tracking is a critical task in autonomous driving systems. It plays an essential role for the system's awareness about the surrounding environment. At the same time there is an increasing interest in algorithms for autonomous cars that solely rely on inexpensive sensors, such as cameras. In this paper we investigate the use of triplet embeddings in combination with motion representations for 3D object tracking. We start from an off-the-shelf 3D object detector, and apply a tracking mechanism where objects are matched by an affinity score computed on local object feature embeddings an…
Tianjin University（天津大学）；Nanjing University of Information Science and Technology（南京信息工程大学）；University of Science and Technology of China（中国科学技术大学）；Automotive Data of China (Tianjin) Co., Ltd（中国汽车技术研究中心有限公司）
Recently, template-based trackers have become the leading tracking algorithms with promising performance in terms of efficiency and accuracy. However, the correlation operation between query feature and the given template only exploits accurate target localization, leading to state estimation error especially when the target suffers from severe deformable variations. To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively. However, most of existing trackers only refer to the targe…
Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
Zhejiang University-University of Illinois at Urbana-Champaign Institute, Zhejiang University（浙江大学-伊利诺伊大学厄巴纳-香槟分校研究院，浙江大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Department of Electrical and Computer Engineering, the University of Washington（华盛顿大学电气与计算机工程系）
Zhejiang University（浙江大学）；Hangzhou Dianzi University（杭州电子科技大学）；Guangdong University of Petrochemical Technology（广东石油化工学院）；University of Washington（华盛顿大学）
Vehicle tracking is an essential task in the multi-object tracking (MOT) field. A distinct characteristic in vehicle tracking is that the trajectories of vehicles are fairly smooth in both the world coordinate and the image coordinate. Hence, models that capture motion consistencies are of high necessity. However, tracking with the standalone motion-based trackers is quite challenging because targets could get lost easily due to limited information, detection error and occlusion. Leveraging appearance information to assist object re-identification could resolve this challenge to some extent. H…
Beijing Institute of Technology（北京理工大学）；University of Sheffield（谢菲尔德大学）
Joint detection and embedding (JDE) based methods usually estimate bounding boxes and embedding features of objects with a single network in Multi-Object Tracking (MOT). In the tracking stage, JDE-based methods fuse the target motion information and appearance information by applying the same rule, which could fail when the target is briefly lost or blocked. To overcome this problem, we propose a new association matrix, the Embedding and Giou matrix, which combines embedding cosine distance and Giou distance of objects. To further improve the performance of data association, we develop a simpl…
The University of Sydney（悉尼大学）；ShanghaiTech University（上海科技大学）；National University of Singapore（新加坡国立大学）；Stevens Institute of Technology（史蒂文斯理工学院）
Modern online multiple object tracking (MOT) methods usually focus on two directions to improve tracking performance. One is to predict new positions in an incoming frame based on tracking information from previous frames, and the other is to enhance data association by generating more discriminative identity embeddings. Some works combined both directions within one framework but handled them as two individual tasks, thus gaining little mutual benefits. In this paper, we propose a novel unified model with synergy between position prediction and embedding association. The two tasks are linked …
Harvard Medical School（哈佛医学院）；Harvard University（哈佛大学）；Ryerson University（瑞尔森大学）；Tsinghua University（清华大学）
The paper focuses on a classical tracking model, subspace learning, grounded on the fact that the targets in successive frames are considered to reside in a low-dimensional subspace or manifold due to the similarity in their appearances. In recent years, a number of subspace trackers have been proposed and obtained impressive results. Inspired by the most recent results that the tracking performance is boosted by the subspace with discrimination capability learned over the recently localized targets and their immediately surrounding background, this work aims at solving such a problem: how to …
Tsinghua University（清华大学）；Australian National University（澳大利亚国立大学）
Modern multiple object tracking (MOT) systems usually follow the \emph{tracking-by-detection} paradigm. It has 1) a detection model for target localization and 2) an appearance embedding model for data association. Having the two models separately executed might lead to efficiency problems, as the running time is simply a sum of the two steps without investigating potential structures that can be shared between them. Existing research efforts on real-time MOT usually focus on the association step, so they are essentially real-time association methods but not real-time MOT system. In this paper…
3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature embedding, position encoding, and self-attention feature computation. Feature embedding aims to place features closer in the embedding space if they have similar semantic information. Position encoding is used to encode coordinates of point clouds into high dimension distinguishable features. Self-attention generates refined attention features by computing attentio…
STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Optics and Electronics（光电技术研究所）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
Center for Mathematical Sciences（数学科学中心）；Lund University（隆德大学）
Formulating the multi object tracking problem as a network flow optimization problem is a popular choice. In this paper an efficient way of learning the weights of such a network is presented. It separates the problem into one embedding of feasible solutions into a one dimensional feature space and one optimization problem. The embedding can be learned using standard SGD type optimization without relying on an additional optimizations within each step. Training data is produced by performing small perturbations of ground truth tracks and representing them using generalized graph differences, w…
Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art results on the Multi-Object Tracking (MOT) benchmarks. However, their success depends on the availability of videos that are fully annotated with tracking data, which is expensive and hard to obtain. This can limit the model generalization. In comparison, the two-stage approach, which performs detection and embedding separately, is slower but easier to train as their data are easier to annotate. We propose to combine …
Kyushu University（九州大学）；Tianjin University of Technology（天津理工大学）；Alibaba Group（阿里巴巴集团）；Nanyang Technological University（南洋理工大学）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））
Online updating of the object model via samples from historical frames is of great importance for accurate visual object tracking. Recent works mainly focus on constructing effective and efficient updating methods while neglecting the training samples for learning discriminative object models, which is also a key part of a learning problem. In this paper, we propose the DeepMix that takes historical samples' embeddings as input and generates augmented embeddings online, enhancing the state-of-the-art online learning methods for visual object tracking. More specifically, we first propose the on…
Multiple object tracking (MOT) is a crucial task in computer vision society. However, most tracking-by-detection MOT methods, with available detected bounding boxes, cannot effectively handle static, slow-moving and fast-moving camera scenarios simultaneously due to ego-motion and frequent occlusion. In this work, we propose a novel tracking framework, called "instance-aware MOT" (IA-MOT), that can track multiple objects in either static or moving cameras by jointly considering the instance-level features and object motions. First, robust appearance features are extracted from a variant of Mas…
Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking
School of Information Science and Technology, Shanghaitech University（上海科技大学信息科学与技术学院）；State Key Laboratory of Multimodal Artificial Intelligence System, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（电子科技大学深圳高等研究院）；School of Automation Engineering, University of Electronic Science and Technology of China（电子科技大学自动化工程学院）；KargoBot, China（卡果机器人公司（中国））；Department of Computer Science and Information Systems, Birkbeck College（伯克贝克学院计算机科学与信息系统系）
针对 JDE 中检测与 ReID 特征学习冲突及外观判别力不足的问题，本文提出利用连续帧互相关学习运动特征的 TCBTrack，在多个 MOT 基准上实现实时且最先进的跟踪性能。
Online tracking of multiple objects in videos requires strong capacity of modeling and matching object appearances. Previous methods for learning appearance embedding mostly rely on instance-level matching without considering the temporal continuity provided by videos. We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker. It enables us to learn not only from videos labeled with complete tracks, but also unlabeled or partially labeled videos. We implement this learning objec…
AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Optics and Electronics, Chinese Academy of Sciences（中国科学院光电技术研究所）；Computer Vision Center（计算机视觉中心）；Universitat Autonoma de Barcelona（巴塞罗那自治大学）
University of Science and Technology of China（中国科学技术大学）；Baidu Inc.（百度公司）
Multiple-object tracking and segmentation (MOTS) is a novel computer vision task that aims to jointly perform multiple object tracking (MOT) and instance segmentation. In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework. To begin with, PointTrack adopts an efficient one-stage framework for instance segmentation, and learns instance embeddings by converting compact image representations to un-ordered 2D point cloud. Compared with PointTrack, our proposed PointTrack++ offers three major improvements. …
University of Science and Technology of China（中国科学技术大学）；Baidu Inc.（百度公司）
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt convolutions for feature extraction. However, as affected by the inherent receptive field, convolution based feature extraction inevitably mixes up the foreground features and the background features, resulting in ambiguities in the subsequent instance association. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. Our method generates a ne…
HieDG: A Hierarchical Discrete Geometry-Guided Framework for Multi-Animal Tracking
State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所脑认知与脑启发智能技术国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Technology, Beijing Forestry University（北京林业大学工学院）；School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学前沿交叉科学学院）；College of Computer Science, Sichuan University（四川大学计算机学院）；C²DL, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所C²DL）；School of Automation, Chongqing University（重庆大学自动化学院）；Faculty of Life and Health Sciences, Shenzhen University of Advanced Technology（深圳理工大学生命健康学院）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）
Peng Cheng Laboratory（鹏城实验室）；Dalian University of Technology（大连理工大学）；ByteDance（字节跳动）；The University of Hong Kong（香港大学）
We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters. Due to the fragmented definitions of the object tracking problem itself, most existing trackers are developed to address a single or part of tasks and overspecialize on the characteristics of specific tasks. By contrast, Unicorn provides a unified solution, adopting the same input, backbone, embedding, and head across all tracking tasks. For the first time, we accomplish the great unification of the tracking network archi…
Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and association in subsequent phases. However, this is not suitable for actual industrial applications due to unavailability of detections upfront. In their recent work, Wang et al. proposed a tracking pipeline that uses a Joint detection and embedding model and performs target localization and association in realtime. Upon investigating the tracking by detection paradigm…
Nanjing University of Science and Technology（南京理工大学）；Graz University of Technology（格拉茨技术大学）
Existing Multiple Object Tracking (MOT) methods design complex architectures for better tracking performance. However, without a proper organization of input information, they still fail to perform tracking robustly and suffer from frequent identity switches. In this paper, we propose two novel methods together with a simple online Message Passing Network (MPN) to address these limitations. First, we explore different integration methods for the graph node and edge embeddings and put forward a new IoU (Intersection over Union) guided function, which improves long term tracking and handles iden…
AWS AI Labs（AWS人工智能实验室）；University of Washington（华盛顿大学）
We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core inf…
University of Macau（澳门大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Baidu Research（百度研究院）
In this paper, we propose a learning-based moving-object tracking method utilizing our newly developed LiDAR sensor, Frequency Modulated Continuous Wave (FMCW) LiDAR. Compared with most existing commercial LiDAR sensors, our FMCW LiDAR can provide additional Doppler velocity information to each 3D point of the point clouds. Benefiting from this, we can generate instance labels as ground truth in a semi-automatic manner. Given the labels, we propose a contrastive learning framework, which pulls together the features from the same instance in embedding space and pushes apart the features from di…
Dalian University of Technology（大连理工大学）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects…
University of Surrey（萨里大学）；Jiangnan University（江南大学）
Siamese approaches have achieved promising performance in visual object tracking recently. The key to the success of Siamese trackers is to learn appearance-invariant feature embedding functions via pair-wise offline training on large-scale video datasets. However, the Siamese paradigm uses one-shot learning to model the online tracking task, which impedes online adaptation in the tracking process. Additionally, the uncertainty of an online tracking response is not measured, leading to the problem of ignoring potential failures. In this paper, we advocate online adaptation in the tracking stag…
University of Electronic Science and Technology of China（电子科技大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Due to balanced accuracy and speed, one-shot models which jointly learn detection and identification embeddings, have drawn great attention in multi-object tracking (MOT). However, the inherent differences and relations between detection and re-identification (ReID) are unconsciously overlooked because of treating them as two isolated tasks in the one-shot tracking paradigm. This leads to inferior performance compared with existing two-stage methods. In this paper, we first dissect the reasoning process for these two tasks, which reveals that the competition between them inevitably would destr…
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars. Tracking objects, however, remains a highly challenging problem, especially in cluttered autonomous driving scenes in which objects tend to interact with each other in complex ways and frequently get occluded. We propose a novel approach to MOT that uses attention to compute track embeddings that encode the spatiotemporal dependencies between observed objects. This attention measurement encoding allows our model to relax hard data associations, which may lead to unrecoverable errors. Instead, our mo…
AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes
Institute of Software Chinese Academy of Science（中国科学院软件研究所）；Turing Quantum Company（图灵量子公司）；OPPO Research Institute（OPPO研究院）；University of North Texas（北德克萨斯大学）
Huazhong University of Science and Technology（华中科技大学）；Wormpex AI Research（Wormpex AI研究院）；Shanghai Jiao Tong University（上海交通大学）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Transformer trackers have achieved impressive advancements recently, where the attention mechanism plays an important role. However, the independent correlation computation in the attention mechanism could result in noisy and ambiguous attention weights, which inhibits further performance improvement. To address this issue, we propose an attention in attention (AiA) module, which enhances appropriate correlations and suppresses erroneous ones by seeking consensus among all correlation vectors. Our AiA module can be readily applied to both self-attention blocks and cross-attention blocks to fac…
Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box. By utilizing offline feature learning, the siamese paradigm has recently been the leading framework for high performance tracking. However, current existing siamese trackers either heavily rely on complicated anchor-based detection networks or lack the ability to resist to distractors. In this paper, we propose the Siamese keypoint prediction network (SiamKPN) to address these challenges. Upon a Siamese backbone for feature embedding, SiamKPN benefits from a cascade h…
School of Computer Science（计算机学院）；Northwestern Polytechnical University（西北工业大学）；Aberystwyth University（阿伯里斯特威斯大学）
Discriminative correlation filters (DCF) and siamese networks have achieved promising performance on visual tracking tasks thanks to their superior computational efficiency and reliable similarity metric learning, respectively. However, how to effectively take advantages of powerful deep networks, while maintaining the real-time response of DCF, remains a challenging problem. Embedding the cross-correlation operator as a separate layer into siamese networks is a popular choice to enhance the tracking accuracy. Being a key component of such a network, the correlation layer is updated online tog…
Nanyang Technological University（南洋理工大学）；Advanced Digital Science Center（先进数字科学中心）；City University of Hong Kong（香港城市大学）
In this paper, we propose an approach to learn hierarchical features for visual object tracking. First, we offline learn features robust to diverse motion patterns from auxiliary video sequences. The hierarchical features are learned via a two-layer convolutional neural network. Embedding the temporal slowness constraint in the stacked architecture makes the learned features robust to complicated motion transformations, which is important for visual object tracking. Then, given a target video sequence, we propose a domain adaptation module to online adapt the pre-learned features according to …
Northwestern Polytechnical University（西北工业大学）；National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）
The problem of visual object tracking has traditionally been handled by variant tracking paradigms, either learning a model of the object's appearance exclusively online or matching the object with the target in an offline-trained embedding space. Despite the recent success, each method agonizes over its intrinsic constraint. The online-only approaches suffer from a lack of generalization of the model they learn thus are inferior in target regression, while the offline-only approaches (e.g., convolutional siamese trackers) lack the target-specific context information thus are not discriminativ…
GOT-JEPA: Generic Object Tracking with Model Adaptation and Occlusion Handling using Joint-Embedding Predictive Architecture
Department of Computer Science, National Yang Ming Chiao Tung University（国家阳明交通大学计算机科学系）；Research Center for Information Technology Innovation, Academia Sinica（中华学术院信息技术创新研究中心）；Microsoft AI（微软人工智能）
University of Michigan（密歇根大学）；Tsinghua University（清华大学）
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predict…
Although short-term fully occlusion happens rare in visual object tracking, most trackers will fail under these circumstances. However, humans can still catch up the target by anticipating the trajectory of the target even the target is invisible. Recent psychology also has shown that humans build the mental image of the future. Inspired by that, we present a HAllucinating Features to Track (HAFT) model that enables to forecast the visual feature embedding of future frames. The anticipated future frames focus on the movement of the target while hallucinating the occluded part of the target. Jo…
SOTFormer: A Minimal Transformer for Unified Object Tracking and Trajectory Prediction
School of Computer Science University College Dublin（计算机科学学院都柏林大学学院）；School of Computer Science and Technology Dalian University of Technology（计算机科学与技术学院大连理工大学）
We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed tech…
Object tracking is divided into single-object tracking (SOT) and multi-object tracking (MOT). MOT aims to maintain the identities of multiple objects across a series of continuous video sequences. In recent years, MOT has made rapid progress. However, modeling the motion and appearance models of objects in complex scenes still faces various challenging issues. In this paper, we design a novel direction consistency method for smooth trajectory prediction (STP-DC) to increase the modeling of motion information and overcome the lack of robustness in previous methods in complex scenes. Existing me…
