Learning Spatial-Frequency Transformer for Visual Object 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）；Anhui University（安徽大学）；Harbin Institute of Technology（哈尔滨工业大学）；Pengcheng Laboratory（鹏城实验室）
Recent trackers adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. Although their trackers work well in regular scenarios, however, they simply flatten the 2D features into a sequence to better match the Transformer. We believe these operations ignore the spatial prior of the target object which may lead to sub-optimal results only. In addition, many works demonstrate that self-attention is actually a low-pass filter, which is independent of input features or key/queries. That is to say, it may suppress the high-frequency component of the input features and preserve or even amplify the low-frequency information. To handle these issues, in this paper, we propose a unified Spatial-Frequency Transformer that models the Gaussian spatial Prior and High-frequency emphasis Attention (GPHA) simultaneously. To be specific, Gaussian spatial prior is generated using dual Multi-Layer Perceptrons (MLPs) and injected into the similarity matrix produced by multiplying Query and Key features in self-attention. The output will be fed into a Softmax layer and then decomposed into two components, i.e., the direct signal and high-frequency signal. The low- and high-pass branches are rescaled and combined to achieve all-pass, therefore, the high-frequency features will be protected well in stacked self-attention layers. We further integrate the Spatial-Frequency Transformer into the Siamese tracking framework and propose a novel tracking algorithm, termed SFTransT. The cross-scale fusion based SwinTransformer is adopted as the backbone, and also a multi-head cross-attention module is used to boost the interaction between search and template features. The output will be fed into the tracking head for target localization. Extensive experiments on both short-term and long-term tracking benchmarks all demonstrate the effectiveness of our proposed framework.
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…
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…
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 George Washington University（乔治华盛顿大学）；University of Central Florida（中佛罗里达大学）；Emory University（埃默里大学）
In this paper, we study a discriminatively trained deep convolutional network for the task of visual tracking. Our tracker utilizes both motion and appearance features that are extracted from a pre-trained dual stream deep convolution network. We show that the features extracted from our dual-stream network can provide rich information about the target and this leads to competitive performance against state of the art tracking methods on a visual tracking benchmark.
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 …
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）
Nanjing University of Science and Technology（南京理工大学）
Siamese network based trackers formulate 3D single object tracking as cross-correlation learning between point features of a template and a search area. Due to the large appearance variation between the template and search area during tracking, how to learn the robust cross correlation between them for identifying the potential target in the search area is still a challenging problem. In this paper, we explicitly use Transformer to form a 3D Siamese Transformer network for learning robust cross correlation between the template and the search area of point clouds. Specifically, we develop a Sia…
Monash University（莫纳什大学）；The University of Melbourne（墨尔本大学）；The University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
Tracking a time-varying indefinite number of objects in a video sequence over time remains a challenge despite recent advances in the field. Most existing approaches are not able to properly handle multi-object tracking challenges such as occlusion, in part because they ignore long-term temporal information. To address these shortcomings, we present MO3TR: a truly end-to-end Transformer-based online multi-object tracking (MOT) framework that learns to handle occlusions, track initiation and termination without the need for an explicit data association module or any heuristics. MO3TR encodes ob…
Northeastern University（东北大学）；Science and Technology on Near-Surface Detection Laboratory（近地面探测技术重点实验室）
LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point clouds, which makes the features extracted by the model ambiguous. Ambiguous features will make it hard to locate the target object and finally lead to bad tracking results. To solve this problem, we utilize the powerful Transformer architecture and propose a Point-Track-Transformer (PTT) module for point cloud-based 3D single object tracking task. Specific…
School of Computing and Communications, Lancaster University（兰卡斯特大学计算与通信学院）
Motion models play a great role in visual tracking applications for predicting the possible locations of objects in the next frame. Unlike target tracking in radar or aerospace domain which considers only points, object tracking in computer vision involves sizes of objects. Constant velocity motion model is the most widely used motion model for visual tracking, however, there is no clear and understandable derivation involving sizes of objects specially for new researchers joining this research field. In this document, we derive the constant velocity motion model that incorporates sizes of obj…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Visual tracking is fragile in some difficult scenarios, for instance, appearance ambiguity and variation, occlusion can easily degrade most of visual trackers to some extent. In this paper, visual tracking is empowered with wireless positioning to achieve high accuracy while maintaining robustness. Fundamentally different from the previous works, this study does not involve any specific wireless positioning algorithms. Instead, we use the confidence region derived from the wireless positioning Cramer-Rao bound (CRB) as the search region of visual trackers. The proposed framework is low-cost an…
Wuhan University（武汉大学）；Wuhan Optics Valley Information Technology Co., Ltd.（武汉光谷信息技术股份有限公司）；Mobile Broadcasting and Information Service Industry Innovation Research Institute (Wuhan) Co., Ltd（移动广播与信息服务产业创新研究院（武汉）有限公司）
This study proposes an improved end-to-end multi-target tracking algorithm that adapts to multi-view multi-scale scenes based on the self-attentive mechanism of the transformer's encoder-decoder structure. A multi-dimensional feature extraction backbone network is combined with a self-built semantic raster map, which is stored in the encoder for correlation and generates target position encoding and multi-dimensional feature vectors. The decoder incorporates four methods: spatial clustering and semantic filtering of multi-view targets, dynamic matching of multi-dimensional features, space-time…
Hangzhou Dianzi University（杭州电子科技大学）；The University of Sydney（悉尼大学）
Current 3D single object tracking methods are typically based on VoteNet, a 3D region proposal network. Despite the success, using a single seed point feature as the cue for offset learning in VoteNet prevents high-quality 3D proposals from being generated. Moreover, seed points with different importance are treated equally in the voting process, aggravating this defect. To address these issues, we propose a novel global-local transformer voting scheme to provide more informative cues and guide the model pay more attention on potential seed points, promoting the generation of high-quality 3D p…
Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV 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）；Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing（广西嵌入式技术与智能信息处理重点实验室）；School of Computer Science, Fudan University（复旦大学计算机科学学院）；School of Artificial Intelligence, Sun Yat-sen University（中山大学人工智能学院）；College of Computer Science, Sichuan University（四川大学计算机科学学院）
Learning Motion Blur Robust Vision Transformers for Real-Time UAV Tracking
College of Computer Science（计算机科学学院）；Guilin University of Technology（桂林理工大学）；School of Computer Science（计算机科学学院）；Fudan University（复旦大学）；Sun Yat-sen University（中山大学）；Sichuan University（四川大学）
How to combine the complementary capabilities of an ensemble of different algorithms has been of central interest in visual object tracking. A significant progress on such a problem has been achieved, but considering short-term tracking scenarios. Instead, long-term tracking settings have been substantially ignored by the solutions. In this paper, we explicitly consider long-term tracking scenarios and provide a framework, named CoCoLoT, that combines the characteristics of complementary visual trackers to achieve enhanced long-term tracking performance. CoCoLoT perceives whether the trackers …
