Published: 09 Oct 2015 Category: deep_learning

Learning A Deep Compact Image Representation for Visual Tracking

Hierarchical Convolutional Features for Visual Tracking

Robust Visual Tracking via Convolutional Networks

Transferring Rich Feature Hierarchies for Robust Visual Tracking

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

RATM: Recurrent Attentive Tracking Model

Understanding and Diagnosing Visual Tracking Systems

Recurrently Target-Attending Tracking

Visual Tracking with Fully Convolutional Networks

Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks

Learning to Track at 100 FPS with Deep Regression Networks

Learning by tracking: Siamese CNN for robust target association

Fully-Convolutional Siamese Networks for Object Tracking

Hedged Deep Tracking

Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking

Visual Tracking via Shallow and Deep Collaborative Model

Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network

Modeling and Propagating CNNs in a Tree Structure for Visual Tracking

Robust Scale Adaptive Kernel Correlation Filter Tracker With Hierarchical Convolutional Features

Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks

OTB Results: visual tracker benchmark results

Convolutional Regression for Visual Tracking

Semantic tracking: Single-target tracking with inter-supervised convolutional networks

SANet: Structure-Aware Network for Visual Tracking

ECO: Efficient Convolution Operators for Tracking

Dual Deep Network for Visual Tracking

Deep Motion Features for Visual Tracking

Globally Optimal Object Tracking with Fully Convolutional Networks

Robust and Real-time Deep Tracking Via Multi-Scale Domain Adaptation

Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies

Large Margin Object Tracking with Circulant Feature Maps

DCFNet: Discriminant Correlation Filters Network for Visual Tracking

End-to-end representation learning for Correlation Filter based tracking

Context-Aware Correlation Filter Tracking

Robust Multi-view Pedestrian Tracking Using Neural Networks

Re3 : Real-Time Recurrent Regression Networks for Object Tracking

Robust Tracking Using Region Proposal Networks

Hierarchical Attentive Recurrent Tracking

Siamese Learning Visual Tracking: A Survey

Robust Visual Tracking via Hierarchical Convolutional Features

CREST: Convolutional Residual Learning for Visual Tracking

Learning Policies for Adaptive Tracking with Deep Feature Cascades

Recurrent Filter Learning for Visual Tracking

Correlation Filters with Weighted Convolution Responses

Semantic Texture for Robust Dense Tracking

Learning Multi-frame Visual Representation for Joint Detection and Tracking of Small Objects

Differentiating Objects by Motion: Joint Detection and Tracking of Small Flying Objects

Tracking Persons-of-Interest via Unsupervised Representation Adaptation

End-to-end Flow Correlation Tracking with Spatial-temporal Attention

UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking

Pixel-wise object tracking

MAVOT: Memory-Augmented Video Object Tracking

Learning Hierarchical Features for Visual Object Tracking with Recursive Neural Networks

Parallel Tracking and Verifying

Saliency-Enhanced Robust Visual Tracking

A Twofold Siamese Network for Real-Time Object Tracking

Learning Dynamic Memory Networks for Object Tracking

Context-aware Deep Feature Compression for High-speed Visual Tracking

VITAL: VIsual Tracking via Adversarial Learning

Unveiling the Power of Deep Tracking

A Novel Low-cost FPGA-based Real-time Object Tracking System

MV-YOLO: Motion Vector-aided Tracking by Semantic Object Detection

Information-Maximizing Sampling to Promote Tracking-by-Detection

Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks

Stochastic Channel Decorrelation Network and Its Application to Visual Tracking

Fast Dynamic Convolutional Neural Networks for Visual Tracking

DeepTAM: Deep Tracking and Mapping

Distractor-aware Siamese Networks for Visual Object Tracking

Multi-Branch Siamese Networks with Online Selection for Object Tracking

Real-Time MDNet

Towards a Better Match in Siamese Network Based Visual Object Tracker

DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking

Deformable Object Tracking with Gated Fusion

Deep Attentive Tracking via Reciprocative Learning

Online Visual Robot Tracking and Identification using Deep LSTM Networks

  • intro: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017. IROS RoboCup Best Paper Award
  • arxiv:

Detect or Track: Towards Cost-Effective Video Object Detection/Tracking

Deep Siamese Networks with Bayesian non-Parametrics for Video Object Tracking

Fast Online Object Tracking and Segmentation: A Unifying Approach

Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking

Handcrafted and Deep Trackers: A Review of Recent Object Tracking Approaches

SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks

Deeper and Wider Siamese Networks for Real-Time Visual Tracking

SiamVGG: Visual Tracking using Deeper Siamese Networks

TrackNet: Simultaneous Object Detection and Tracking and Its Application in Traffic Video Analysis

Target-Aware Deep Tracking

  • intro: CVPR 2019
  • intro: 1Harbin Institute of Technology & Shanghai Jiao Tong University & Tencent AI Lab & University of California & Google Cloud AI
  • arxiv:

Unsupervised Deep Tracking

Generic Multiview Visual Tracking

SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking

A Strong Feature Representation for Siamese Network Tracker

Visual Tracking via Dynamic Memory Networks

Multi-Adapter RGBT Tracking

Teacher-Students Knowledge Distillation for Siamese Trackers

Tell Me What to Track

Learning to Track Any Object

ROI Pooled Correlation Filters for Visual Tracking

D3S – A Discriminative Single Shot Segmentation Tracker

Visual Tracking by TridentAlign and Context Embedding

Transformer Tracking

Face Tracking

Mobile Face Tracking: A Survey and Benchmark

Multi-Object Tracking (MOT)

Virtual Worlds as Proxy for Multi-Object Tracking Analysis

Multi-Class Multi-Object Tracking using Changing Point Detection

POI: Multiple Object Tracking with High Performance Detection and Appearance Feature

Simple Online and Realtime Tracking with a Deep Association Metric

Multiple Object Tracking: A Literature Review

Deep Network Flow for Multi-Object Tracking

Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism

Recurrent Autoregressive Networks for Online Multi-Object Tracking


Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project

Multiple Target Tracking by Learning Feature Representation and Distance Metric Jointly

Tracking Noisy Targets: A Review of Recent Object Tracking Approaches

Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking

Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World

Features for Multi-Target Multi-Camera Tracking and Re-Identification

High Performance Visual Tracking with Siamese Region Proposal Network

Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking

Automatic Adaptation of Person Association for Multiview Tracking in Group Activities

Improving Online Multiple Object tracking with Deep Metric Learning

Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking

Multiple Object Tracking in Urban Traffic Scenes with a Multiclass Object Detector

Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers

Deep Affinity Network for Multiple Object Tracking

Exploit the Connectivity: Multi-Object Tracking with TrackletNet

Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification

Online Multi-Object Tracking with Dual Matching Attention Networks

Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment

Tracking without bells and whistles

Spatial-Temporal Relation Networks for Multi-Object Tracking

Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking

State-aware Re-identification Feature for Multi-target Multi-camera Tracking

DeepMOT: A Differentiable Framework for Training Multiple Object Trackers

Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking

End-to-End Learning Deep CRF models for Multi-Object Tracking

End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning

Robust Multi-Modality Multi-Object Tracking

Learning Multi-Object Tracking and Segmentation from Automatic Annotations

Learning a Neural Solver for Multiple Object Tracking

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

Refinements in Motion and Appearance for Online Multi-Object Tracking

A Unified Object Motion and Affinity Model for Online Multi-Object Tracking

A Simple Baseline for Multi-Object Tracking

MOPT: Multi-Object Panoptic Tracking

SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking

Multi-Object Tracking with Siamese Track-RCNN

TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model

Quasi-Dense Similarity Learning for Multiple Object Tracking

imultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking

MAT: Motion-Aware Multi-Object Tracking

SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure

GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization

Rethinking the competition between detection and ReID in Multi-Object Tracking

GMOT-40: A Benchmark for Generic Multiple Object Tracking

Multi-object Tracking with a Hierarchical Single-branch Network

Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking

Learning a Proposal Classifier for Multiple Object Tracking

Track to Detect and Segment: An Online Multi-Object Tracker

Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking

Multiple Object Tracking with Correlation Learning


TransTrack: Multiple-Object Tracking with Transformer

TrackFormer: Multi-Object Tracking with Transformers

TransCenter: Transformers with Dense Queries for Multiple-Object Tracking

Looking Beyond Two Frames: End-to-End Multi-Object Tracking UsingSpatial and Temporal Transformers

TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking

Multiple People Tracking

Multi-Person Tracking by Multicut and Deep Matching

Joint Flow: Temporal Flow Fields for Multi Person Tracking

Multiple People Tracking by Lifted Multicut and Person Re-identification

Tracking by Prediction: A Deep Generative Model for Mutli-Person localisation and Tracking

Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking

Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification

Multi-person Articulated Tracking with Spatial and Temporal Embeddings

Instance-Aware Representation Learning and Association for Online Multi-Person Tracking

  • intro: Pattern Recognition
  • intro: Sun Yat-sen University & Guangdong University of Foreign Studies & Carnegie Mellon University & University of California & Guilin University of Electronic Technology & WINNER Technology
  • arxiv:

Online Multiple Pedestrian Tracking using Deep Temporal Appearance Matching Association

Detecting Invisible People


MOTS: Multi-Object Tracking and Segmentation

Segment as Points for Efficient Online Multi-Object Tracking and Segmentation

PointTrack++ for Effective Online Multi-Object Tracking and Segmentation

Multi-target multi-camera tracking (MTMCT)

Traffic-Aware Multi-Camera Tracking of Vehicles Based on ReID and Camera Link Model


A Baseline for 3D Multi-Object Tracking

Probabilistic 3D Multi-Object Tracking for Autonomous Driving

JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset

Real-time 3D Deep Multi-Camera Tracking

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

PnPNet: End-to-End Perception and Prediction with Tracking in the Loop

GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning

1st Place Solutions for Waymo Open Dataset Challenges – 2D and 3D Tracking

Graph Neural Networks for 3D Multi-Object Tracking

Learnable Online Graph Representations for 3D Multi-Object Tracking

Single Stage Joint Detection and Tracking

Bridging the Gap Between Detection and Tracking: A Unified Approach

Towards Real-Time Multi-Object Tracking

RetinaTrack: Online Single Stage Joint Detection and Tracking

Tracking Objects as Points

Fully Convolutional Online Tracking

Accurate Anchor Free Tracking

Ocean: Object-aware Anchor-free Tracking

Joint Detection and Multi-Object Tracking with Graph Neural Networks

Joint Multiple-Object Detection and Tracking

Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking

SMOT: Single-Shot Multi Object Tracking

DEFT: Detection Embeddings for Tracking

Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking

Tracking with Reinforcement Learning

Deep Reinforcement Learning for Visual Object Tracking in Videos

Visual Tracking by Reinforced Decision Making

End-to-end Active Object Tracking via Reinforcement Learning

Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning

Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning

Detect to Track and Track to Detect



  • intro: OpenMMLab Video Perception Toolbox. It supports Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Detection (VID) with a unified framework.
  • github: