多目标跟踪综述、论文、数据集大汇总 Awesome Multiple object Tracking

Awesome Multiple object Tracking(持续更新)

    • 综述
    • 论文
      • 2022
      • 2021
      • 2020
      • 2019
      • 2018
      • 2017
      • 2016
    • 数据集

综述

Multiple Object Tracking: A Literature Review [paper]
Deep Learning in Video Multi-Object Tracking: A Survey [paper]
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking [paper]
Machine Learning Methods for Data Association in Multi-Object Tracking [paper]
MOTChallenge: A Benchmark for Single-camera Multiple Target Tracking [paper]

论文

2022

SLTtrack: Towards Sequence-Level Training for Visual Tracking [code] [paper] ECCV2022
FEAR: Fast, Efficient, Accurate and Robust Visual Tracker [code] [paper] ECCV2022
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking? [code] [paper] ECCV2022
AiATrack: Attention in Attention for Transformer Visual Tracking [code] [paper] ECCV2022
Unicorn: Towards Grand Unification of Object Tracking [code] [paper] ECCV2022
MeMOT: Multi-Object Tracking with Memory [code] [paper] CVPR2022
GTR: Global Tracking Transformers [code] [paper] CVPR2022
TCTrack: Temporal Contexts for Aerial Tracking [code] [paper] CVPR2022
UTT: Unified Transformer Tracker for Object Tracking [code] [paper] CVPR2022
LPT: Learning of Global Objective for Network Flow in Multi-Object Tracking [code] [paper] CVPR2022
Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking [code] [paper] CVPR2022
TR-MOT: Multi-Object Tracking by Reference [code] [paper] CVPR2022

2021

ByteTrack: Multi-Object Tracking by Associating Every Detection Box [code] [paper] ECCV2022
PermaTrack: Learning to Track with Object Permanence [code] [paper] ICCV2021
SOTMOT: Improving Multiple Object Tracking with Single Object Tracking [code] [paper] CVPR2021
LPC_MOT: Learning a Proposal Classifier for Multiple Object Tracking [code] [paper] CVPR2021
MTP: Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking [code] [paper] CVPR2021
TADAM: Online Multiple Object Tracking with Cross-Task Synergy [code] [paper] CVPR2021
RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation [code] [paper]
MOTR: End-to-End Multiple-Object Tracking with TRansformer [code] [paper] ECCV2022
CSTrackV2/RCNet: One More Check: Making “Fake Background” Be Tracked Again [code] [paper]
QDTrack: Quasi-Dense Similarity Learning for Multiple Object Tracking [code] [paper] CVPR2021
SiamMOT: Siamese Multi-Object Tracking [code] [paper] CVPR2021
GMTracker: Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking [code] [paper] CVPR2021
ArTIST: Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking [code] [paper] CVPR2021
CorrTracker/TLR: Multiple Object Tracking with Correlation Learning [code] [paper] CVPR2021
TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking [code] [paper]
TransCenter: Transformers with Dense Queries for Multiple-Object Tracking [code] [paper]
GCNet: Global Correlation Network: End-to-End Joint Multi-Object Detection and Tracking [code] [paper]
TraDes: Track to Detect and Segment: An Online Multi-Object Tracker [code] [paper] CVPR2021
DEFT: Detection Embeddings for Tracking [code] [paper]
TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking [code] [paper]
TrackFormer: Multi-Object Tracking with Transformers [code] [paper] CVPR2022

2020

PointTrack: Segment as Points for Efficient Online Multi-Object Tracking and Segmentation [code] [paper] ECCV2020
PointTrack++: PointTrack++ for Effective Online Multi-Object Tracking and Segmentation [code] [paper] ECCV2020
JDE: Towards Real-Time Multi-Object Tracking [code] [paper] ECCV2020
GNMOT: Graph Networks for Multiple Object Tracking [code] [paper] WACV2020
EDA_GNN: Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking [code] [paper]
MIFT: Refinements in Motion and Appearance for Online Multi-Object Tracking [code] [paper]
FFT: Multiple Object Tracking by Flowing and Fusing [code] [paper]
Lif_T: Lifted Disjoint Paths with Application in Multiple Object Tracking [code] [paper] ICML2020
CenterTrack: Tracking Objects as Points [code] [paper] ECCV2020
TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model [code] [paper] CVPR2020
FairMOT: A Simple Baseline for Multi-Object Tracking [code] [paper] IJCV2021
RetinaTrack: Online Single Stage Joint Detection and Tracking [code] [paper] CVPR2020
UMA: A Unified Object Motion and Affinity Model for Online Multi-Object Tracking [code] [paper] CVPR2020
MPNTracker: Learning a Neural Solver for Multiple Object Tracking [code] [paper] CVPR2020
CTracker: Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking [code] [paper] ECCV2020
SoDA: Multi-Object Tracking with Soft Data Association [code] [paper]
DMM-Net: Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking [code] [paper] ECCV2020
UnsupTrack: Simple Unsupervised Multi-Object Tracking [code] [paper]
MAT: Motion-Aware Multi-Object Tracking [code] [paper]
CSTrack: Rethinking the competition between detection and ReID in Multi-Object Tracking [code] [paper] IEEE TIP2020
SMOT: Single-Shot Multi Object Tracking [code] [paper]
GSDT: Joint Object Detection and Multi-Object Tracking with Graph Neural Networks [code] [paper] ICRA2021
MLT: Multiplex Labeling Graph for Near-Online Tracking in Crowded Scenes [code] [paper]
TPAGT: Tracklets Predicting Based Adaptive Graph Tracking [code] [paper]
TransTrack: Multiple-Object Tracking with Transformer [code] [paper]
PANDA: A Gigapixel-level Human-centric Video Dataset [code] [paper] CVPR2020

2019

FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking [code] [paper] ICCV2019
FANTrack: 3D Multi-Object Tracking with Feature Association Network [code] [paper] IV2019
MOTS: Multi-Object Tracking and Segmentation [code] [paper] CVPR2019
DeepMOT: How To Train Your Deep Multi-Object Tracker [code] [paper] CVPR2019
Tracktor: Tracking without bells and whistles [code] [paper] ICCV2019

2018

V-IOU: Extending IOU Based Multi-Object Tracking by Visual Information [code] [paper] AVSS2018
DetTA: Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline [code] [paper]
MOTDT: Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification [code] [paper] ICME2018
MOTBeyondPixels: Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking [code] [paper] ICRA2018
DMAN: Online Multi-Object Tracking with Dual Matching Attention Networks [code] [paper] ECCV2018
DAN: Deep Affinity Network for Multiple Object Tracking [code] [paper]
SADF: Online Multi-Object Tracking with Historical Appearance Matching and Scene Adaptive Detection Filtering [code] [paper] AVSS2018
DeepCC: Features for Multi-Target Multi-Camera Tracking and Re-Identification [code] [paper] CVPR2018

2017

CIWT: Combined image-and world-space tracking in traffic scenes [code] [paper] ICRA 2017
towards-reid-tracking: Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters [code] [paper] CVPRW2017
RCMSS: Online multi-object tracking via robust collaborative model and sample selection [code] [paper]
D2T: Detect to Track and Track to Detect [code] [paper] ICCV2017
IOUTracker: High-Speed tracking-by-detection without using image information [code] [paper] AVSS2017
NMGC-MOT: Non-Markovian Globally Consistent Multi-Object Tracking [code] [paper] ICCV2017
DeepSORT: Simple Online and Realtime Tracking with a Deep Association Metric [code] [paper] ICIP2017

2016

SORT: Simple online and realtime tracking [code] [paper] ICIP2016
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature [code] [paper] ECCVW2016
RNN_LSTM: Online Multi-Target Tracking Using Recurrent Neural Networks [code] [paper] AAAI2016

数据集

  • Surveillance Scenarios
    PETS 2009 Benchmark Data [url]
    MOT Challenge [url]
    UA-DETRAC [url]
    WILDTRACK [url]
    NVIDIA AI CITY Challenge [url]
    VisDrone [url]
    JTA Dataset [url]
    Path Track [url]
    TAO [url]
    GMOT40 [url]
    PANDA [url]
  • Surveillance Scenarios
    KITTI-Tracking [url]
    APOLLOSCAPE [url]
    APOLLO MOTS [url]
    Omni-MOT [url]
    BDD100K [url]
    Waymo [url]

你可能感兴趣的:(深度学习,目标跟踪,人工智能,计算机视觉,深度学习,python)