The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to perform Multi-Object Tracking (MOT), resulting in more complicated architectures. We instead show how DETR can be turned into a MOT model by employing an instance-level contrastive loss, a revised sampling strategy and a lightweight assignment method. Our training scheme learns object appearances while preserving detection capabilities and with little overhead. Its performance surpasses the previous state-of-the-art by +2.6 mMOTA on the challenging BDD100K dataset and is comparable to existing transformer-based methods on the MOT17 dataset.
Representation Alignment Contrastive Regularization for Multi-Object Tracking
College of Computer Science and Technology, Zhejiang Gongshang University（浙江工商大学计算机科学与技术学院）；Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology（浙江省大数据与未来电子商务技术重点实验室）；Zhejiang Uniview Technologies Co.,Ltd.（浙江宇视科技有限公司）
Huazhong Univerisity of Science and Technology（华中科技大学）；Tsinghua University（清华大学）
Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation of targets. Although this strategy is effective, it fails to fully exploit the information contained in a whole trajectory. To this end, we propose a strategy, namely multi-view trajectory contrastive learning, in which each trajectory is represented as a center vector. By maintaining all the vectors in a dynamically updated memory bank, a trajectory-level c…
University of Science and Technology of China (USTC)（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
In video object tracking, there exist rich temporal contexts among successive frames, which have been largely overlooked in existing trackers. In this work, we bridge the individual video frames and explore the temporal contexts across them via a transformer architecture for robust object tracking. Different from classic usage of the transformer in natural language processing tasks, we separate its encoder and decoder into two parallel branches and carefully design them within the Siamese-like tracking pipelines. The transformer encoder promotes the target templates via attention-based feature…
Unifying Visual and Vision-Language Tracking via Contrastive Learning
Deep Space Exploration Laboratory（深空探测实验室）；University of Science and Technology of China（中国科学技术大学）；Intelligent Science Technology Academy of CASIC（中国航天科工集团智能科学技术研究院）
The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such as transformers. However, in the pursuit of increased tracking performance, runtime is often hindered. Furthermore, efficient tracking architectures have received surprisingly little attention. In this paper, we introduce the Exemplar Transformer, a transformer module utilizing a single instance level attention layer for realtime visual object tracking. E.T.T…
In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in the current search point cloud given a template point cloud. Motivated by the success of transformers, we propose Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations. PTTR consists of three novel designs. 1) Instead of random sampling, we design Relation-Aware Sampling to preserve relevant points to given templates during subsampling. 2) Furthermore, we propose a Point Relation Tr…
Tracking multiple objects in videos relies on modeling the spatial-temporal interactions of the objects. In this paper, we propose a solution named TransMOT, which leverages powerful graph transformers to efficiently model the spatial and temporal interactions among the objects. TransMOT effectively models the interactions of a large number of objects by arranging the trajectories of the tracked objects as a set of sparse weighted graphs, and constructing a spatial graph transformer encoder layer, a temporal transformer encoder layer, and a spatial graph transformer decoder layer based on the …
Dalian University of Technology（大连理工大学）；National University of Defense Technology（国防科技大学）；Peng Cheng Laboratory（鹏城实验室）
In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinement modules). However, less attention has been paid to tracking speed. Most state-of-the-art trackers are satisfied with the real-time speed on powerful GPUs. However, practical applications necessitate higher requirements for tracking speed, especially when edge platforms with limited resources are used. In this work, we present an efficient tracking method via a hierarchical cross-atten…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Apple（苹果公司）
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise groupin…
Feature fusion and similarity computation are two core problems in 3D object tracking, especially for object tracking using sparse and disordered point clouds. Feature fusion could make similarity computing more efficient by including target object information. However, most existing LiDAR-based approaches directly use the extracted point cloud feature to compute similarity while ignoring the attention changes of object regions during tracking. In this paper, we propose a feature fusion network based on transformer architecture. Benefiting from the self-attention mechanism, the transformer enc…
Columbia University（哥伦比亚大学）；Sony Group Corporation（索尼集团公司）
We propose a light-weight and highly efficient Joint Detection and Tracking pipeline for the task of Multi-Object Tracking using a fully-transformer architecture. It is a modified version of TransTrack, which overcomes the computational bottleneck associated with its design, and at the same time, achieves state-of-the-art MOTA score of 73.20%. The model design is driven by a transformer based backbone instead of CNN, which is highly scalable with the input resolution. We also propose a drop-in replacement for Feed Forward Network of transformer encoder layer, by using Butterfly Transform Opera…
University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）；Meta AI；Zhejiang University（浙江大学）
As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not easily adapted to the other due to the divergent training datasets and tracking objects of both tasks. Although UniTrack \cite{wang2021different} demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on single obje…
Huazhong University of Science and Technology（华中科技大学）；La Trobe University（乐卓博大学）
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and unavoidably ignore the integrity of objects. In this paper, we propose a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level. The cross-window multi-scale attention has the advantage of aggregating attention at different scales and generates the best fi…
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predicto…
School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi（曼迪印度理工学院计算与电气工程学院）
One of the central tasks of multi-object tracking involves learning a distance metric that is consistent with the semantic similarities of objects. The design of an appropriate loss function that encourages discriminative feature learning is among the most crucial challenges in deep neural network-based metric learning. Despite significant progress, slow convergence and a poor local optimum of the existing contrastive and triplet loss based deep metric learning methods necessitates a better solution. In this paper, we propose cosine-margin-contrastive (CMC) and cosine-margin-triplet (CMT) loss…
University of Michigan（密歇根大学）；UC Berkeley（加州大学伯克利分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much denser, pixel-level space-time graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix between two frames in a coarse-to-fine manner, forming a multiscale contrastive random walk when extended in time. This establishes a unifi…
Transformer-based visual object tracking has been utilized extensively. However, the Transformer structure is lack of enough inductive bias. In addition, only focusing on encoding the global feature does harm to modeling local details, which restricts the capability of tracking in aerial robots. Specifically, with local-modeling to global-search mechanism, the proposed tracker replaces the global encoder by a novel local-recognition encoder. In the employed encoder, a local-recognition attention and a local element correction network are carefully designed for reducing the global redundant inf…
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…
The University of Hong Kong（香港大学）；Carnegie Mellon University（卡内基梅隆大学）；ByteDance AI Lab（字节跳动人工智能实验室）；Tongji University（同济大学）
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On …
Technical University of Munich（慕尼黑工业大学）；Facebook AI Research (FAIR)（Facebook人工智能研究院（FAIR））
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce TrackFormer, an end-to-end trainable MOT approach based on an encoder-decoder Transformer architecture. Our model achieves data association between frames via attention by evolving a set of track predictions through a video sequence. The Transformer decoder initializes new tracks from static object queries and autoregressively follows existing tracks in space an…
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…
Southeast University（东南大学）；Microsoft Research Asia（微软亚洲研究院）
We present a Siamese-like Dual-branch network based on solely Transformers for tracking. Given a template and a search image, we divide them into non-overlapping patches and extract a feature vector for each patch based on its matching results with others within an attention window. For each token, we estimate whether it contains the target object and the corresponding size. The advantage of the approach is that the features are learned from matching, and ultimately, for matching. So the features are aligned with the object tracking task. The method achieves better or comparable results as the…
Inria Grenoble Rhône-Alpes（法国国家信息与自动化研究所罗纳-阿尔卑斯大区格勒诺布尔中心）；Massachusetts Institute of Technology（麻省理工学院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense …
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…
Adaptively Bypassing Vision Transformer Blocks for Efficient Visual Tracking
College of Computer Science and Engineering, Guilin University of Technology（桂林理工大学计算机科学与工程学院）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；College of Computer Science, Sichuan University（四川大学计算机学院）
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）
Template-based discriminative trackers are currently the dominant tracking methods due to their robustness and accuracy, and the Siamese-network-based methods that depend on cross-correlation operation between features extracted from template and search images show the state-of-the-art tracking performance. However, general cross-correlation operation can only obtain relationship between local patches in two feature maps. In this paper, we propose a novel tracker network based on a powerful attention mechanism called Transformer encoder-decoder architecture to gain global and rich contextual i…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between …
Beijing Jiaotong University（北京交通大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of North Texas（北得克萨斯大学）
Relying on Transformer for complex visual feature learning, object tracking has witnessed the new standard for state-of-the-arts (SOTAs). However, this advancement accompanies by larger training data and longer training period, making tracking increasingly expensive. In this paper, we demonstrate that the Transformer-reliance is not necessary and the pure ConvNets are still competitive and even better yet more economical and friendly in achieving SOTA tracking. Our solution is to unleash the power of multimodal vision-language (VL) tracking, simply using ConvNets. The essence lies in learning …
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…
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）
Trackastra: Transformer-based cell tracking for live-cell microscopy
Institute of Bioengineering, School of Life Sciences, EPFL（EPFL生命科学学院生物工程研究所）；Center for Scalable Data Analytics and AI (ScaDS.AI)（可扩展数据分析与人工智能中心（ScaDS.AI））；Faculty of Computer Science, TU Dresden（德累斯顿工业大学计算机科学学院）
COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking
Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学合作 medianet 创新中心）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；CloudWalk Technology Co., Ltd（云从科技股份有限公司）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Tongji University（同济大学）；the University of Hong Kong（香港大学）
Vision-based object tracking has boosted extensive autonomous applications for unmanned aerial vehicles (UAVs). However, the dynamic changes in flight maneuver and viewpoint encountered in UAV tracking pose significant difficulties, e.g. , aspect ratio change, and scale variation. The conventional cross-correlation operation, while commonly used, has limitations in effectively capturing perceptual similarity and incorporates extraneous background information. To mitigate these limitations, this work presents a novel saliency-guided dynamic vision Transformer (SGDViT) for UAV tracking. The prop…
Recent object tracking methods depend upon deep networks or convoluted architectures. Most of those trackers can hardly meet real-time processing requirements on mobile platforms with limited computing resources. In this work, we introduce the Siamese Transformer Pyramid Network (SiamTPN), which inherits the advantages from both CNN and Transformer architectures. Specifically, we exploit the inherent feature pyramid of a lightweight network (ShuffleNetV2) and reinforce it with a Transformer to construct a robust target-specific appearance model. A centralized architecture with lateral cross at…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between frames. To this end, we revamped the tracking framework with Progressive Context Encoding Transformer Tracker (ProContEXT), which coherently exploits spatial and temporal contexts to predict object motion trajectories. Specifically, ProContEXT leverages a context-aware self-attention module to encode the spatial and temporal context, refining and updating the …
Columbia University（哥伦比亚大学）；Salesforce Research（Salesforce研究院）
Videos are a rich source for self-supervised learning (SSL) of visual representations due to the presence of natural temporal transformations of objects. However, current methods typically randomly sample video clips for learning, which results in an imperfect supervisory signal. In this work, we propose PreViTS, an SSL framework that utilizes an unsupervised tracking signal for selecting clips containing the same object, which helps better utilize temporal transformations of objects. PreViTS further uses the tracking signal to spatially constrain the frame regions to learn from and trains the…
