Home

Awesome

Refer to SpyderXu with some supplements

Online

NameSourcePublicationNotes
Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking[pdf]ECCV2020-
Towards Real-Time Multi-Object Tracking[pdf] [code]ECCV2020-
Tracking Objects as Points[pdf] [code]ECCV 2020-
Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking[pdf]ECCV2020-
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation[pdf] [code]ECCV2020 oralmots
MAT: Motion-Aware Multi-Object Tracking[pdf]arXiv2020.9.18
Adopting Tubes to Track Multi-Object in a One-Step Training Model[pdf] [code]CVPR2020TubeTK
Joint Detection and Multi-Object Tracking with Graph Neural Networks[pdf]arxiv(2020)JDMOT_GNN
Graph Networks for Multiple Object Tracking[pdf] [code]WACV2020GNMOT
Deep association: End-to-end graph-based learning for multiple object tracking with conv-graph neural network[pdf]ICMR2019DAN
SQE: a Self Quality Evaluation Metric for Parameters Optimization in Multi-Object Tracking[pdf]arxiv(2020)SQE
Autoregressive Trajectory Inpainting and Scoring for Tracking[pdf]CVPR2020ArTIST
Multiple Object Tracking with Siamese Track-RCNN[pdf]arxiv(2020)Siamese Track-RCNN
Online Single Stage Joint Detection and Tracking[pdf]CVPR2020RetinaTrack
A Simple Baseline for Multi-Object Tracking[pdf][code]arXiv(2019)FairMOT
Tracking Objects as Points[pdf] [code]arXiv(2019)CenterTrack
Refinements in Motion and Appearance for Online Multi-Object Tracking[pdf] [code]arXiv(2019)MIFT
Multiple Object Tracking by Flowing and Fusing[pdf]arXiv(2019)FFT
A Unified Object Motion and Affinity Model for Online Multi-Object Tracking[pdf][code]CVPR2020UMA
DeepMOT:A Differentiable Framework for Training Multiple Object Trackers[pdf] [code]CVPR2020DeepMOT
Online multiple pedestrian tracking using deep temporal appearance matching association[pdf] [code]arXiv(2019)DD_TAMA19
Spatial-temporal relation networks for multi-object tracking[pdf]ICCV2019STRN
Towards Real-Time Multi-Object Tracking[pdf] [code]arXiv(2019)JDE(private)
Multi-object tracking with multiple cues and switcher-aware classification[pdf]arXiv(2019)LSST
FAMNet: Joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking[pdf]ICCV2019FAMNet
Online multi-object tracking with instance-aware tracker and dynamic model refreshment[pdf]WACV2019KCF
Tracking without bells and whistles[pdf] [code]ICCV2019Tracktor
MOTS: Multi-Object Tracking and Segmentation[pdf] [code]CVPR2019Track R-CNN
Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking[pdf] [code]CVPR2019SAS_MOT17
Deep affinity network for multiple object tracking[pdf] [code]PAMI(2019)DAN
Recurrent autoregressive networks for online multi-object tracking[pdf]WACV2018RAN
Real-time multiple people tracking with deeply learned candidate selection and person re-identification[pdf] [code]ICME2018MOTDT
Online multi-object tracking with dual matching attention networks[pdf] [code]ECCV2018DMAN
Extending IOU Based Multi-Object Tracking by Visual Information[pdf] [code]AVSS2018V-IOU
Online Multi-target Tracking using Recurrent Neural Networks[pdf] [code]AAAI2017MOT-RNN
Detect to Track and Track to Detect[pdf] [code]ICCV2017D&T(private)
Online multi-object tracking using CNN-based single object tracker with spatial-temporal attention mechanism[pdf]ICCV2017STAM
Tracking the untrackable: Learning to track multiple cues with long-term dependencies[pdf]ICCV2017AMIR
Simple online and realtime tracking with a deep association metric[pdf] [code]ICIP2017DeepSort
High-speed tracking-by-detection without using image information[pdf] [code]AVSS2017IOU Tracker
Simple online and realtime tracking[pdf] [code]ICIP2016Sort
Temporal dynamic appearance modeling for online multi-person tracking[pdf]CVIU(2016)TDAM
Online multi-object tracking via structural constraint event aggregation[pdf]CVPR2016SCEA
Online Multi-Object Tracking Via Robust Collaborative Model and Sample Selection[pdf] [code]CVIU2016RCMSS
Learning to Track: Online Multi-Object Tracking by Decision Making[pdf] [code]ICCV2015MDP
Learning to Divide and Conquer for Online Multi-Target Tracking[pdf] [code]ICCV2015LDCT
Robust online multi-object tracking based on tracklet confidence and online discriminative appearance learning[pdf] [code]CVPR2014CMOT
The Way They Move: Tracking Targets with Similar Appearance[pdf] [code]ICCV2013SMOT
Online Multi-Person Tracking by Tracker Hierarchy[pdf] [code]AVSS2012OMPTTH

Batch

NameSourcePublicationNotes
Lifted Disjoint Paths with Application in Multiple Object Tracking[pdf] [code]ICML2020Lif_T
Learning non-uniform hypergraph for multi-object tracking[pdf]AAAI2019NT
Learning a Neural Solver for Multiple Object Tracking[pdf] [code]CVPR2020MPNTracker
Deep learning of graph matching[pdf]CVPR2018深度图匹配
muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking[pdf] [code]NIPS(2019)muSSP
Exploit the connectivity: Multi-object tracking with trackletnet[pdf] [code]ACM mm 2019TNT(eTC)
Multiple people tracking using body and joint detections[pdf]CVPRW2019JBNOT
Aggregate Tracklet Appearance Features for Multi-Object Tracking[pdf]SPL(2019)NOTA
Customized multi-person tracker[pdf]ACCV2018HCC
Multi-object tracking with neural gating using bilinear lstm[pdf]ECCV2018MHT_bLSTM
Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Tracking[pdf]ICME2018GCRE
Multiple People Tracking with Lifted Multicut and Person Re-identification[pdf]CVPR2017LMP
Deep network flow for multi-object tracking[pdf]CVPR2017-
Non-markovian globally consistent multi-object tracking[pdf] [code]ICCV2017-
Multi-Object Tracking with Quadruplet Convolutional Neural Networks[pdf]CVPR2017Quad-CNN
Enhancing detection model for multiple hypothesis tracking[pdf]CVPRW2017EDMT
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature[pdf]ECCV2016KNDT
Multiple hypothesis tracking revisited[pdf] [code]ICCV2015MHT-DAM
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor[pdf]ICCV2015NOMT
On Pairwise Costs for Network Flow Multi-Object Tracking[pdf] [code]CVPR2015-
Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph[pdf] [code]CVPR2014H2T
Continuous Energy Minimization for Multi-Target Tracking[pdf] [code]CVPR2014CEM
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs[pdf] [code]ECCV2012GMCP
Multiple Object Tracking using K-Shortest Paths Optimization[pdf] [code]PAMI2011KSP
Global data association for multi-object tracking using network flows[pdf] [code]CVPR2008-

MTMC

NameSourcePublicationNotes
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking[pdf] codeCVPR2019 WorkshopLAAM
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification[pdf]CVPR2019CityFlow
Features for multi-target multi-camera tracking and re-identification[pdf] [code]CVPR2018DeepCC(MTMC)
Rolling Shutter and Radial Distortion Are Features for High Frame Rate Multi-Camera Tracking[pdf]CVPR2018-
Towards a Principled Integration of Multi-Camera Re-Identification andTracking through Optimal Bayes Filters[pdf] [code]CVPR2017towards-reid-tracking

3D&Multi-Modality

NameSourcePublicationNotes
Joint 3D Tracking and Forecasting with Graph Neural Network and Diversity Sampling[pdf] [code]arxivGNNTrkForecast
Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning[pdf] [code]CVPR2020GNN3DMOT
Robust Multi-Modality Multi-Object Tracking[pdf] [code]ICCV2019mmMOT
A baseline for 3D Multi-Object Tracking[pdf] [code]arXiv-
3D Object Detection and Tracking Based on Streaming Data[pdf]ICRA2020DODT
Factor Graph based 3D Multi-Object Tracking in Point Clouds[pdf] [video]IROS2020DODT
DeepTracking-Net: 3D Tracking with Unsupervised Learning of Continuous Flow[pdf]arXiv2020.6.24
Center-based 3D Object Detection and Tracking[pdf] [code]arXiv2020.6.19
1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking[pdf]arXivtechnical report

Review

Multiple Object Tracking: A Literature Review

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

Deep Learning in Video Multi-Object Tracking_ A Survey

Globally-Optimal Greedy Algorithms for Tracking a Variable Number of Objects

Datasets

MOT:包含2D MOT2015、3D MOT2015、MOT16、MOT17和MOT17Det等多个子数据集,提供了ACF、DPM、Faster RCNN、SDP等多个检测器输入。包含不同的相机视角、相机运动、场景和时间变化以及密集场景。

KITTI:提供了汽车和行人的标注,场景较稀疏。

TUD Stadtmitte:包含3D人体姿态识别、多视角行人检测和朝向检测、以及行人跟踪的标注,相机视角很低,数据集不大。

ETHZ:由手机拍摄的多人跟踪数据集,包含三个场景。

EPFL:多摄像头采集的行人检测和跟踪数据集,每隔摄像头离地2米,实验人员就是一个实验室的,分为实验室、校园、平台、通道、篮球场这5个场景,每个场景下都有多个摄像头,每个摄像头拍摄2分钟左右。

KIT AIS:空中拍摄的,只有行人的头

PETS:比较早期的视频,有各式各样的行人运动。

DukeMTMC:多摄像头多行人跟踪。

MOTS:多目标跟踪与分割。

Evaluation

ClearMOT

IDF1

Code: pythonmatlab