这是资源索引仓库,不是可直接运行的工具,没有安装步骤;部分论文和笔记以 PDF 链接形式提供,需自行下载;研究数据部分依赖 DavidRM Journal 8 软件导入,且需先导入用户偏好再导入数据
Deep-Learning-for-Tracking-and-Detection
abhineet123更新放缓汇总深度学习目标跟踪与检测的论文、数据集和代码资源,方便快速查找该领域的模型与实现。
Collection of papers, datasets, code and other resources for object tracking and detection using deep learning
深度学习目标检测与跟踪的论文、数据集和代码资源合集,适合按方向快速查资料
汇总深度学习目标跟踪与检测的论文、数据集和代码资源,方便快速查找该领域的模型与实现。
核心能力
- 按静态检测、视频检测、单目标跟踪、多目标跟踪分类整理论文
- 汇总各方向对应的公开数据集与评测指标
- 收集各类开源代码实现与框架链接
- 提供论文 PDF 与个人阅读笔记的直达链接
- 附带教程、博客和资源合集等延伸阅读
容易踩的坑
暂无 release 数据(可能没有发版,或尚未同步)。
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
Collection of papers, datasets, code and other resources for object detection and tracking using deep learning
- Research Data
- Papers
- Datasets
- Code
- Collections
- Tutorials
- Blogs
Research Data
I use DavidRM Journal for managing my research data for its excellent hierarchical organization, cross-linking and tagging capabilities.
I make available a Journal entry export file that contains tagged and categorized collection of papers, articles, tutorials, code and notes about computer vision and deep learning that I have collected over the last few years.
This is what the topic cloud looks like:
![]()
It needs Jounal 8 and can be imported using following steps:
- Import my user preferences using File -> Import -> Import User Preferences
- Import research data using File -> Import -> Sync from The Journal Export File
Note that my user preferences must be imported before the research data for the tagged topics to work correctly.
(optional) My global options file is also provided for those interested in a dark theme and can be imported using File -> Import -> Import Global Options
Updated: 2026-03-09
Papers
Static Detection
Region Proposal
- Scalable Object Detection Using Deep Neural Networks [cvpr14] [pdf] [notes]
- Selective Search for Object Recognition [ijcv2013] [pdf] [notes]
RCNN
- Faster R-CNN Towards Real-Time Object Detection with Region Proposal Networks [tpami17] [pdf] [notes]
- RFCN - Object Detection via Region-based Fully Convolutional Networks [nips16] [Microsoft Research] [pdf] [notes]
- Mask R-CNN [iccv17] [Facebook AI Research] [pdf] [notes] [arxiv] [code (keras)] [code (tensorflow)]
- SNIPER Efficient Multi-Scale Training [ax1812/nips18] [pdf] [notes] [code]
YOLO
- You Only Look Once Unified, Real-Time Object Detection [ax1605] [pdf] [notes]
- YOLO9000 Better, Faster, Stronger [ax1612] [pdf] [notes]
- YOLOv3 An Incremental Improvement [ax1804] [pdf] [notes]
- YOLOv4 Optimal Speed and Accuracy of Object Detection [ax2004] [pdf] [notes] [code]
SSD
- SSD Single Shot MultiBox Detector [ax1612/eccv16] [pdf] [notes]
- DSSD Deconvolutional Single Shot Detector [ax1701] [pdf] [notes]
RetinaNet
- Feature Pyramid Networks for Object Detection [ax1704] [pdf] [notes]
- Focal Loss for Dense Object Detection [ax180207/iccv17] [pdf] [notes]
Anchor Free
- FoveaBox: Beyond Anchor-based Object Detector [ax1904] [pdf] [notes] [code]
- CornerNet: Detecting Objects as Paired Keypoints [ax1903/ijcv19] [pdf] [notes] [code]
- FCOS Fully Convolutional One-Stage Object Detection [ax1908/iccv19] [pdf] [notes] [code] [code/FCOS_PLUS] [code/VoVNet] [code/HRNet] [code/NAS]
- Feature Selective Anchor-Free Module for Single-Shot Object Detection [ax1903/cvpr19] [pdf] [notes] [code]
- Bottom-up object detection by grouping extreme and center points [ax1901] [pdf] [notes] [code]
- Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection [ax1912/cvpr20] [pdf] [notes] [code]
- End-to-end object detection with Transformers [ax200528] [pdf] [notes] [code]
- Objects as Points [ax1904] [pdf] [notes] [code]
- RepPoints Point Set Representation for Object Detection [iccv19] [pdf] [notes] [code]
Misc
- OverFeat Integrated Recognition, Localization and Detection using Convolutional Networks [ax1402/iclr14] [pdf] [notes]
- LSDA Large scale detection through adaptation [ax1411/nips14] [pdf] [notes]
- Acquisition of Localization Confidence for Accurate Object Detection [ax1807/eccv18] [pdf] [notes] [code]
- EfficientDet: Scalable and Efficient Object Detection [cvpr20] [pdf]
- Generalized Intersection over Union A Metric and A Loss for Bounding Box Regression [ax1902/cvpr19] [pdf] [notes] [code] [project]
Video Detection
Tubelet
- Object Detection from Video Tubelets with Convolutional Neural Networks [cvpr16] [pdf] [notes]
- Object Detection in Videos with Tubelet Proposal Networks [ax1704/cvpr17] [pdf] [notes]
FGFA
- Deep Feature Flow for Video Recognition [cvpr17] [Microsoft Research] [pdf] [arxiv] [code]
- Flow-Guided Feature Aggregation for Video Object Detection [ax1708/iccv17] [pdf] [notes]
- Towards High Performance Video Object Detection [ax1711] [Microsoft] [pdf] [notes]
RNN
- Online Video Object Detection using Association LSTM [iccv17] [pdf] [notes]
- Context Matters Refining Object Detection in Video with Recurrent Neural Networks [bmvc16] [pdf] [notes]
Multi Object Tracking
Joint-Detection
Identity Embedding
-
MOTS Multi-Object Tracking and Segmentation [cvpr19] [pdf] [notes] [code] [project/data]
-
Towards Real-Time Multi-Object Tracking [ax1909] [pdf] [notes]
-
A Simple Baseline for Multi-Object Tracking [ax2004] [pdf] [notes] [code]
-
Integrated Object Detection and Tracking with Tracklet-Conditioned Detection [ax1811] [pdf] [notes]
Association
Deep Learning
-
Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism [ax1708/iccv17] [pdf] [arxiv] [notes]
-
Online multi-object tracking with dual matching attention networks [ax1902/eccv18] [pdf] [arxiv] [notes] [code]
-
FAMNet Joint Learning of Feature, Affinity and Multi-Dimensional Assignment for Online Multiple Object Tracking [iccv19] [pdf] [notes]
-
Exploit the Connectivity: Multi-Object Tracking with TrackletNet [ax1811/mm19] [pdf] [notes]
-
Tracking without bells and whistles [ax1903/iccv19] [pdf] [notes] [code] [pytorch]
RNN
- Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies [ax1704/iccv17] [Stanford] [pdf] [notes] [arxiv] [project],
- Multi-object Tracking with Neural Gating Using Bilinear LSTM [eccv18] [pdf] [notes]
- Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking [cvpr19] [pdf] [notes] [code]
Unsupervised Learning
- Unsupervised Person Re-identification by Deep Learning Tracklet Association [ax1809/eccv18] [pdf] [notes]
- Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers [ax1809/cvpr19] [pdf] [arxiv] [notes] [code]
- Simple Unsupervised Multi-Object Tracking [ax2006] [pdf] [notes]
Reinforcement Learning
- Learning to Track: Online Multi-object Tracking by Decision Making [iccv15] [Stanford] [pdf] [notes] [code (matlab)] [project]
- Collaborative Deep Reinforcement Learning for Multi-Object Tracking [eccv18] [pdf] [notes]
Network Flow
- Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor [iccv15] [NEC Labs] [pdf] [author] [notes]
- Deep Network Flow for Multi-Object Tracking [cvpr17] [NEC Labs] [pdf] [supplementary] [notes]
- Learning a Neural Solver for Multiple Object Tracking [ax1912/cvpr20] [pdf] [notes] [code]
Graph Optimization
- A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects [ax1607] [highest MT on MOT2015] [University of Freiburg, Germany] [pdf] [arxiv] [author] [notes]
Baseline
- Simple Online and Realtime Tracking [icip16] [pdf] [notes] [code]
- High-Speed Tracking-by-Detection Without Using Image Information [avss17] [pdf] [notes] [code]
Metrics
Single Object Tracking
Reinforcement Learning
- Deep Reinforcement Learning for Visual Object Tracking in Videos [ax1704] [USC-Santa Barbara, Samsung Research] [pdf] [arxiv] [author] [notes]
- Visual Tracking by Reinforced Decision Making [ax1702] [Seoul National University, Chung-Ang University] [pdf] [arxiv] [author] [notes]
- Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning [cvpr17] [Seoul National University] [pdf] [supplementary] [project] [notes] [code]
- End-to-end Active Object Tracking via Reinforcement Learning [ax1705] [Peking University, Tencent AI Lab] [pdf] [arxiv]
Siamese
- Fully-Convolutional Siamese Networks for Object Tracking [eccv16] [pdf] [project] [notes]
- High Performance Visual Tracking with Siamese Region Proposal Network [cvpr18] [pdf] [author] [notes]
- Siam R-CNN Visual Tracking by Re-Detection [cvpr20] [pdf] [notes] [project] [code]
Correlation
- ATOM Accurate Tracking by Overlap Maximization [cvpr19] [pdf] [notes] [code]
- DiMP Learning Discriminative Model Prediction for Tracking [iccv19] [pdf] [notes] [code]
- D3S – A Discriminative Single Shot Segmentation Tracker [cvpr20] [pdf] [notes] [code]
Misc
Deep Learning
Synthetic Gradients
- Decoupled Neural Interfaces using Synthetic Gradients [ax1608] [pdf] [notes]
- Understanding Synthetic Gradients and Decoupled Neural Interfaces [ax1703] [pdf] [notes]
Efficient
Unsupervised Learning
Interpolation
- Video Frame Interpolation via Adaptive Convolution [cvpr17 / iccv17] [pdf (cvpr17)] [pdf (iccv17)] [ppt]
Autoencoder
Variational
- beta-VAE Learning Basic Visual Concepts with a Constrained Variational Framework [iclr17] [pdf] [notes]
- Disentangling by Factorising [ax1806] [pdf] [notes]
Datasets
Multi Object Tracking
- IDOT
- UA-DETRAC Benchmark Suite
- GRAM Road-Traffic Monitoring [paper]
- Ko-PER Intersection Dataset
- TRANCOS
- Urban Tracker
- DARPA VIVID / PETS 2005 [Non stationary camera]
- KIT-AKS [No ground truth]
- CBCL StreetScenes Challenge Framework [No top down viewpoint]
- MOT 2015 [mostly street level viewpoint]
- MOT 2016 [mostly street level viewpoint]
- MOT 2017 [mostly street level viewpoint]
- MOT 2020 [mostly top down viewpoint]
- MOTS: Multi-Object Tracking and Segmentation [MOT and KITTI]
- CVPR 2019 [mostly street level viewpoint]
- PETS 2009 [No vehicles]
- PETS 2017 [Low density] [mostly pedestrians]
- DukeMTMC [multi camera] [static background] [pedestrians] [above-street level viewpoint] [website not working]
- KITTI Tracking Dataset [No top down viewpoint] [non stationary camera]
- The WILDTRACK Seven-Camera HD Dataset [pedestrian detection and tracking]
- 3D Traffic Scene Understanding from Movable Platforms [intersection traffic] [stereo setup] [moving camera]
- LOST : Longterm Observation of Scenes with Tracks [top down and street level viewpoint] [no ground truth]
- JTA [top down and street level viewpoint] [synthetic/GTA 5] [pedestrian] [3D annotations]
- PathTrack: Fast Trajectory Annotation with Path Supervision [top down and street level viewpoint] [iccv17] [pedestrian]
- CityFlow [pole mounted] [intersections] [vehicles] [re-id] [cvpr19]
- JackRabbot Dataset [RGBD] [head-on][indoor/outdoor][stanford]
- TAO: A Large-Scale Benchmark for Tracking Any Object [eccv20] [code]
- Edinburgh office monitoring video dataset [indoors][long term][mostly static people]
- Waymo Open Dataset [outdoors][vehicles]
UAV
- Stanford Drone Dataset
- UAVDT - The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking [uav] [intersections/highways] [vehicles] [eccv18]
- VisDrone
Synthetic
- MNIST-MOT / MNIST-Sprites [script generated] [cvpr19]
- TUB Multi-Object and Multi-Camera Tracking Dataset [avss16]
- Virtual KITTI [arxiv] [cvpr16] [link seems broken]
Microscopy / Cell Tracking
- Cell Tracking Challenge [nature methods/2017]
- CTMC: Cell Tracking with Mitosis Detection Dataset Challenge [cvprw20] [MOT]
Single Object Tracking
- TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild [eccv18]
- LaSOT: Large-scale Single Object Tracking [cvpr19]
- Need for speed: A benchmark for higher frame rate object tracking [iccv17]
- Long-term Tracking in the Wild A Benchmark [eccv18]
- UAV123: A benchmark and simulator for UAV tracking [eccv16] [project]
- Sim4CV A Photo-Realistic Simulator for Computer Vision Applications [ijcv18]
- CDTB: A Color and Depth Visual Object Tracking and Benchmark [iccv19] [RGBD]
- Temple Color 128 - Color Tracking Benchmark [tip15]
Video Detection
Video Understanding / Activity Recognition
- YouTube-8M
- AVA: A Video Dataset of Atomic Visual Action
- VIRAT Video Dataset
- Kinetics Action Recognition Dataset
Static Detection
- PASCAL Visual Object Classes
- A Large-Scale Dataset for Vehicle Re-Identification in the Wild [cvpr19]
- Object Detection-based annotations for some frames of the VIRAT dataset
- MIO-TCD: A new benchmark dataset for vehicle classification and localization [tip18]
- Tiny ImageNet
Animals
- Wildlife Image and Localization Dataset (species and bounding box labels) [wacv18]
- Stanford Dogs Dataset [cvpr11]
- Oxford-IIIT Pet Dataset [cvpr12]
- Caltech-UCSD Birds 200 [rough segmentation] [attributes]
- Gold Standard Snapshot Serengeti Bounding Box Coordinates
Boundary Detection
Static Segmentation
- COCO - Common Objects in Context
- Open Images
- ADE20K [cvpr17]
- SYNTHIA [cvpr16]
- UC Berkeley Computer Vision Group - Contour Detection and Image Segmentation
Video Segmentation
- DAVIS: Densely Annotated VIdeo Segmentation
- Mapillary Vistas Dataset [street scenes] [semi-free]
- BDD100K [street scenes] [autonomous driving]
- ApolloScape [street scenes] [autonomous driving]
- Cityscapes [street scenes] [instance-level]
- YouTube-VOS [iccv19]
Classification
- ImageNet Large Scale Visual Recognition Competition 2012
- Animals with Attributes 2
- CompCars Dataset
- ObjectNet [only test set]
Optical Flow
Motion Prediction
Code
General Vision
- Gluon CV Toolkit [mxnet] [pytorch]
- OpenMMLab Computer Vision Foundation [pytorch]
Multi Object Tracking
Frameworks
General
- Globally-optimal greedy algorithms for tracking a variable number of objects [cvpr11] [matlab] [author]
- Continuous Energy Minimization for Multitarget Tracking [cvpr11 / iccv11 / tpami 2014] [matlab]
- Discrete-Continuous Energy Minimization for Multi-Target Tracking [cvpr12] [matlab] [project]
- The way they move: Tracking multiple targets with similar appearance [iccv13] [matlab]
- 3D Traffic Scene Understanding from Movable Platforms [2d_tracking] [pami14/kit13/iccv13/nips11] [c++/matlab]
- Multiple target tracking based on undirected hierarchical relation hypergraph [cvpr14] [C++] [author]
- Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning [cvpr14] [matlab] (project)
- Learning to Track: Online Multi-Object Tracking by Decision Making [iccv15] [matlab]
- Joint Tracking and Segmentation of Multiple Targets [cvpr15] [matlab]
- Multiple Hypothesis Tracking Revisited [iccv15] [highest MT on MOT2015 among open source trackers] [matlab]
- Combined Image- and World-Space Tracking in Traffic Scenes [icra 2017] [c++]
- Online Multi-Target Tracking with Recurrent Neural Networks [aaai17] [lua/torch7]
- Real-Time Multiple Object Tracking - A Study on the Importance of Speed [ax1710/masters thesis] [c++]
- Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking [icra18] [matlab]
- Online Multi-Object Tracking with Dual Matching Attention Network [eccv18] [matlab/tensorflow]
- TrackR-CNN - Multi-Object Tracking and Segmentation [cvpr19] [tensorflow] [project]
- Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking [cvpr19] [tensorflow]
- Robust Multi-Modality Multi-Object Tracking [iccv19] [pytorch]
- Towards Real-Time Multi-Object Tracking / Joint Detection and Embedding [ax1909] [pytorch] [CMU]
- Deep Affinity Network for Multiple Object Tracking [tpami19] [pytorch]
- Tracking without bells and whistles [iccv19] [pytorch]
- Lifted Disjoint Paths with Application in Multiple Object Tracking [icml20] [matlab] [mot15#1,mot16 #3,mot17#2]
- Learning a Neural Solver for Multiple Object Tracking [cvpr20] [pytorch] [mot15#2]
- Tracking Objects as Points [ax2004] [pytorch]
- Quasi-Dense Similarity Learning for Multiple Object Tracking [ax2006] [pytorch]
- DEFT: Detection Embeddings for Tracking [ax2102] [pytorch]
- How To Train Your Deep Multi-Object Tracker [ax1906/cvpr20] [pytorch] [traktor/gitlab]
- Track To Detect and Segment: An Online Multi-Object Tracker [cvpr21] [pytorch] [project]
- MOTR: End-to-End Multiple-Object Tracking with Transformer [ax2202] [pytorch]
Baseline
- Simple Online and Realtime Tracking [icip 2016] [python]
- Deep SORT : Simple Online Realtime Tracking with a Deep Association Metric [icip17] [python]
- High-Speed Tracking-by-Detection Without Using Image Information [avss17] [python]
- A simple baseline for one-shot multi-object tracking [ax2004] [pytorch] [winner of mot15,16,17,20]
Siamese
- SiamMOT: Siamese Multi-Object Tracking [ax2105] [pytorch]
Unsupervised
- Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers [cvpr19] [python/c++/pytorch]
Re-ID
- Torchreid: Deep learning person re-identification in PyTorch [ax1910] [pytorch]
- SMOT: Single-Shot Multi Object Tracking [ax2010] [pytorch] [gluon-cv]
- FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking [ax2004] [pytorch] [microsoft] [BDD100K] [face tracking]
- Rethinking the competition between detection and ReID in Multi-Object Tracking [ax2010] [pytorch]
Frameworks
Graph NN
- Joint Object Detection and Multi-Object Tracking with Graph Neural Networks [ax2006/ icra21] [pytorch]
Microscopy / cell tracking
- Baxter Algorithms / Viterbi Tracking [tmi14] [matlab]
- Deepcell: Accurate cell tracking and lineage construction in live-cell imaging experiments with deep learning [biorxiv1910] [tensorflow]
3D
- 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics [iros20/eccvw20] [pytorch]
- GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning [iros20/eccvw20] [pytorch]
Metrics
- HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking [cvpr20] [python]
Single Object Tracking
- A collection of common tracking algorithms (2003-2012) [c++/matlab]
- SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask [pytorch]
- In Defense of Color-based Model-free Tracking [cvpr15] [c++]
- Hierarchical Convolutional Features for Visual Tracking [iccv15] [matlab]
- Visual Tracking with Fully Convolutional Networks [iccv15] [matlab]
- Hierarchical Convolutional Features for Visual Tracking [iccv15] [matlab]
- DeepTracking: Seeing Beyond Seeing Using Recurrent Neural Networks [aaai16] [torch 7]
- Learning Multi-Domain Convolutional Neural Networks for Visual Tracking [cvpr16] [vot2015 winner] [matlab/matconvnet] [pytorch]
- Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking [eccv 2016] [matlab]
- Fully-Convolutional Siamese Networks for Object Tracking [eccvw 2016] [matlab/matconvnet] [project] [pytorch] [pytorch (only training)]
- DCFNet: Discriminant Correlation Filters Network for Visual Tracking [ax1704] [matlab/matconvnet] [pytorch]
- End-to-end representation learning for Correlation Filter based tracking [cvpr17] [matlab/matconvnet] [tensorflow/inference_only] [project]
- Dual Deep Network for Visual Tracking [tip1704] [caffe]
- SiameseX: A simplified PyTorch implementation of Siamese networks for tracking: SiamFC, SiamRPN, SiamRPN++, SiamVGG, SiamDW, SiamRPN-VGG [pytorch]
- RATM: Recurrent Attentive Tracking Model [cvprw17] [python]
- ROLO : Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking [iscas 2017] [tensorfow]
- ECO: Efficient Convolution Operators for Tracking [cvpr17] [matlab] [python/cuda] [pytorch]
- Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning [cvpr17] [tensorflow]
- Detect to Track and Track to Detect [iccv17] [matlab]
- Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers [eccv18] [pytorch]
- Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking [cvpr18] [matlab]
- High Performance Visual Tracking with Siamese Region Proposal Network [cvpr18] [pytorch/195] [pytorch/313] [pytorch/no_train/104] [pytorch/177]
- Distractor-aware Siamese Networks for Visual Object Tracking [eccv18] [vot18 winner] [pytorch]
- VITAL: VIsual Tracking via Adversarial Learning [cvpr18] [matlab] [pytorch] [project]
- Fast Online Object Tracking and Segmentation: A Unifying Approach (SiamMask) [cvpr19] [pytorch] [project]
- PyTracking: A general python framework for training and running visual object trackers, based on PyTorch [ECO/ATOM/DiMP/PrDiMP] [cvpr17/cvpr19/iccv19/cvpr20] [pytorch]
- Unsupervised Deep Tracking [cvpr19] [matlab/matconvnet] [pytorch]
- Deeper and Wider Siamese Networks for Real-Time Visual Tracking [cvpr19] [pytorch]
- [GradNet: Gradient-Guided Network for Visual Object Tracking](https://github.c