Object tracking has achieved significant progress over the past few years. However, state-of-the-art trackers become increasingly heavy and expensive, which limits their deployments in resource-constrained applications. In this work, we present LightTrack, which uses neural architecture search (NAS) to design more lightweight and efficient object trackers. Comprehensive experiments show that our LightTrack is effective. It can find trackers that achieve superior performance compared to handcrafted SOTA trackers, such as SiamRPN++ and Ocean, while using much fewer model Flops and parameters. Moreover, when deployed on resource-constrained mobile chipsets, the discovered trackers run much faster. For example, on Snapdragon 845 Adreno GPU, LightTrack runs $12\times$ faster than Ocean, while using $13\times$ fewer parameters and $38\times$ fewer Flops. Such improvements might narrow the gap between academic models and industrial deployments in object tracking task. LightTrack is released at https://github.com/researchmm/LightTrack.
In this paper, we propose a novel effective light-weight framework, called LightTrack, for online human pose tracking. The proposed framework is designed to be generic for top-down pose tracking and is faster than existing online and offline methods. Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) are incorporated into one unified functioning entity, easily implemented by a replaceable single-person pose estimation module. Our framework unifies single-person pose tracking with multi-person identity association and sheds first light upon bridging keypoint tracking with object…
This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network. The former learns coarse primary information with low cost while the latter conveys residual information for high fidelity to original representations. The proposed parallel architecture is effective to maintain complementary information since fixed-point arithmetic can be utilized in the quantized network and the lightweig…
University of Southern California（南加州大学）；Army Research Laboratory（美国陆军研究实验室）
An unsupervised, lightweight and high-performance single object tracker, called UHP-SOT, was proposed by Zhou et al. recently. As an extension, we present an enhanced version and name it UHP-SOT++ in this work. Built upon the foundation of the discriminative-correlation-filters-based (DCF-based) tracker, two new ingredients are introduced in UHP-SOT and UHP-SOT++: 1) background motion modeling and 2) object box trajectory modeling. The main difference between UHP-SOT and UHP-SOT++ is the fusion strategy of proposals from three models (i.e., DCF, background motion and object box trajectory mode…
The University of Georgia（佐治亚大学）；University of Vermont（佛蒙特大学）
Tracking cell particles in 3D microscopy videos is a challenging task but is of great significance for modeling the motion of cells. Proper characterization of the cell's shape, evolution, and their movement over time is crucial to understanding and modeling the mechanobiology of cell migration in many diseases. One in particular, toxoplasmosis is the disease caused by the parasite Toxoplasma gondii. Roughly, one-third of the world's population tests positive for T. gondii. Its virulence is linked to its lytic cycle, predicated on its motility and ability to enter and exit nucleated cells; the…
CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking
Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（杭州高等研究院，中国科学院大学）；Dept. of Computer Science and Engineering, University of North Texas（计算机科学与工程系，北卡罗来纳州立大学）；Institute of Software Chinese Academy of Science（中国科学院软件研究所）
University of Southern California（南加州大学）；Army Research Laboratory（陆军研究实验室）
Supervised and unsupervised deep trackers that rely on deep learning technologies are popular in recent years. Yet, they demand high computational complexity and a high memory cost. A green unsupervised single-object tracker, called GUSOT, that aims at object tracking for long videos under a resource-constrained environment is proposed in this work. Built upon a baseline tracker, UHP-SOT++, which works well for short-term tracking, GUSOT contains two additional new modules: 1) lost object recovery, and 2) color-saliency-based shape proposal. They help resolve the tracking loss problem and offe…
Facebook；The Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Dartmouth College（达特茅斯学院）
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection and video understanding. Our method operates in two-stages: keypoint estimation in frames or short clips, followed by lightweight tracking to generate keypoint predictions linked over the entire video. For frame-level pose estimation we experiment with Mask R-CNN, as well as our own proposed 3D extension of this model, which leverages temporal information ove…
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…
Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking hinder their adoption on embedded devices with limited computing power. In this paper, we aim to accelerate MOT by transferring the knowledge from high-level features of a complex network (teacher) to a lightweight network (student) at both training and inference times. The proposed AttTrack framework has three key components: 1) cross-model feature learning t…
Yazd University（亚兹德大学）；Sharif University of Technology（谢里夫理工大学）；University of Alberta（阿尔伯塔大学）
In recent years, visual tracking methods that are based on discriminative correlation filters (DCF) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficie…
Tracking by Detection and Query: An Efficient End-to-End Framework for Multi-Object Tracking
organization= School of Automation , addressline= Southeast University , city= Nanjing , postcode= 210096 , country= China；organization= Key Laboratory of Measurement；organization= School of Physical \& Mathematical Sciences , addressline= Nanyang Technological University , postcode= 639798 , country= Singapore；organization= Big Data Institute , addressline= Central South University , city= Changsha , postcode= 410083 , country= China；organization= School of Instrument Science；Engineering , addressline= Southeast University , city= Nanjing , postcode= 210096 , country= China
Learning Frequency and Memory-Aware Prompts for Multi-Modal Object Tracking
State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；School of Information Science and Engineering（信息科学与工程学院）；School of Mathematics（数学学院）；Purple Mountain Laboratories（紫金山实验室）
Paul G. Allen School of Computer Science, University of Washington（保罗·G·艾伦计算机科学学院，华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）
Robust object tracking requires knowledge and understanding of the object being tracked: its appearance, its motion, and how it changes over time. A tracker must be able to modify its underlying model and adapt to new observations. We present Re3, a real-time deep object tracker capable of incorporating temporal information into its model. Rather than focusing on a limited set of objects or training a model at test-time to track a specific instance, we pretrain our generic tracker on a large variety of objects and efficiently update on the fly; Re3 simultaneously tracks and updates the appeara…
Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间应用工程与技术中心）；University of Chinese Academy of Sciences（中国科学院大学）
University of Chinese Academy of Sciences（中国科学院大学）
Discriminant Correlation Filters (DCF) based methods now become a kind of dominant approach to online object tracking. The features used in these methods, however, are either based on hand-crafted features like HoGs, or convolutional features trained independently from other tasks like image classification. In this work, we present an end-to-end lightweight network architecture, namely DCFNet, to learn the convolutional features and perform the correlation tracking process simultaneously. Specifically, we treat DCF as a special correlation filter layer added in a Siamese network, and carefully…
Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Science and Technologies Facilities Council（科学与技术设施委员会）；Beijing Jiaotong University（北京交通大学）
Correlation filter has been proven to be an effective tool for a number of approaches in visual tracking, particularly for seeking a good balance between tracking accuracy and speed. However, correlation filter based models are susceptible to wrong updates stemming from inaccurate tracking results. To date, little effort has been devoted towards handling the correlation filter update problem. In this paper, we propose a novel approach to address the correlation filter update problem. In our approach, we update and maintain multiple correlation filter models in parallel, and we use deep reinfor…
HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking
KTH Royal Institute of Technology, Stockholm, Sweden（皇家理工学院）；College of Computer Science, Nankai University, Tianjin, China（南开大学计算机学院）；IIS, ETH Zurich, Zurich, Switzerland（苏黎世联邦理工学院信息与系统研究所）；Nanjing University of Aeronautics and Astronautics, Nanjing, China（南京航空航天大学）
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）
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）
University of Chinese Academy of Sciences（中国科学院大学）；CASIA（中国科学院自动化研究所）；Microsoft Research（微软研究院）
Siamese networks have drawn great attention in visual tracking because of their balanced accuracy and speed. However, the backbone networks used in Siamese trackers are relatively shallow, such as AlexNet [18], which does not fully take advantage of the capability of modern deep neural networks. In this paper, we investigate how to leverage deeper and wider convolutional neural networks to enhance tracking robustness and accuracy. We observe that direct replacement of backbones with existing powerful architectures, such as ResNet [14] and Inception [33], does not bring improvements. The main r…
Nanjing University of Information Science and Technology（南京信息工程大学）；University of California, Merced（加州大学默塞德分校）
Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less discriminative for tracking specific objects. In this paper we present that, even without offline training with a large amount of auxiliary data, simple two-layer convolutional networks can be powerful enough to develop a robust representation for visual tracking. In the first frame, we employ the k-means algorithm to extract a set of normalized patches from t…
PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
Carnegie Mellon University（卡内基梅隆大学）；National University of Singapore（新加坡国立大学）；Tongji University（同济大学）；New York University（纽约大学）；Tsinghua University（清华大学）
In this paper, we construct a lightweight, high-precision and high-speed object tracking using a trained CNN. Conventional methods with trained CNNs use VGG16 network which requires powerful computational resources. Therefore, there is a problem that it is difficult to apply in low computation resources environments. To solve this problem, we use MobileNetV3, which is a CNN for mobile terminals.Based on Feature Map Selection Tracking, we propose a new architecture that extracts effective features of MobileNet for object tracking. The architecture requires no online learning but only offline le…
The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations. It is well suited to object tracking because its formulation in the Fourier domain provides a fast solution, enabling the detector to be re-trained once per frame. Previous works that use the Correlation Filter, however, have adopted features that were either manually designed or trained for a different task. This work is the first to overcome this limitation by interpreting the Correlation Filter learner, which has a closed-form solution, as a differentiable layer in a d…
Detection and tracking of dynamic objects is a key feature for autonomous behavior in a continuously changing environment. With the increasing popularity and capability of micro aerial vehicles (MAVs) efficient algorithms have to be utilized to enable multi object tracking on limited hardware and data provided by lightweight sensors. We present a novel segmentation approach based on a combination of median filters and an efficient pipeline for detection and tracking of small objects within sparse point clouds generated by a Velodyne VLP-16 sensor. We achieve real-time performance on a single c…
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…
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；School of Electronic and Information Engineering, Anhui University（安徽大学电子与信息工程学院）
Combining traditional RGB cameras with bio-inspired event cameras for robust object tracking has garnered increasing attention in recent years. However, most existing multimodal tracking algorithms depend heavily on high-complexity Vision Transformer architectures for feature extraction and fusion across modalities. This not only leads to substantial computational overhead but also limits the effectiveness of cross-modal interactions. In this paper, we propose an efficient RGB-Event object tracking framework based on the linear-complexity Vision Mamba network, termed Mamba-FETrack V2. Specific…
