https://github.com/MCG-NJU/MixFormer
공식 코드MixFormer: End-to-End Tracking with Iterative Mixed Attention
Papers with Code 아카이브
Object Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 10
- 보존된 평가 기록
- 43
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
<span style="color:grey; opacity: 0.6">( Image credit: Towards-Realtime-MOT )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/MCG-NJU/SportsMOT
공식 코드SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes
https://github.com/MCG-NJU/TREG
공식 코드https://github.com/MIT-HAN-LAB/temporal-shift-module
공식 코드TSM: Temporal Shift Module for Efficient Video Understanding
https://github.com/ManOfStory/UncTrack
공식 코드UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network
https://github.com/MasterBin-IIAU/AlphaRefine
공식 코드Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation
https://github.com/MasterBin-IIAU/UNINEXT
공식 코드Universal Instance Perception as Object Discovery and Retrieval
https://github.com/MedChaabane/DEFT
공식 코드https://github.com/MegviiDetection/video_analyst
공식 코드SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines
https://github.com/MichiganCOG/Surgical_Hands_RELEASE
공식 코드Temporally Guided Articulated Hand Pose Tracking in Surgical Videos
https://github.com/NVlabs/BundleSDF
공식 코드BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
https://github.com/Nanyangny/CenterTrack-IOU
공식 코드Multi-object Tracking with Tracked Object Bounding Box Association
https://github.com/Nathan-Li123/SMOTer
공식 코드https://github.com/NissaFaber/Thesis_repo
공식 코드https://github.com/PaddlePaddle/PaddleDetection
공식 코드https://github.com/Paulkie99/imm-jhse
공식 코드One Homography is All You Need: IMM-based Joint Homography and Multiple Object State Estimation
https://github.com/PeizeSun/TransTrack
공식 코드https://github.com/Peterbotliang/NEBPMOT
공식 코드https://github.com/QiaoLiuHit/MMNet
공식 코드Multi-Task Driven Feature Models for Thermal Infrared Tracking
https://github.com/QiaoLiuHit/PTB-TIR_Evaluation_toolkit
공식 코드https://github.com/RadarCameraFusionTeam-BUPT/ES-EOT-real-nuscenes
공식 코드3D Extended Object Tracking by Fusing Roadside Sparse Radar Point Clouds and Pixel Keypoints
https://github.com/RalphMao/PatchNet
공식 코드PatchNet -- Short-range Template Matching for Efficient Video Processing
https://github.com/Robotmurlock/NODETracker
공식 코드Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Tracking
https://github.com/SAIL-GuoLab/Cell_Segmentation_and_Tracking
공식 코드https://github.com/SaadUllahAkram/CellTracker
공식 코드https://github.com/Sentient07/HeadHunter--T
공식 코드https://github.com/ShaohuaDong2021/LoReTrack
공식 코드LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
https://github.com/SilvioGiancola/ShapeCompletion3DTracking
공식 코드https://github.com/SonginCV/GMPHD-OGM_Tracker
공식 코드Online Multi-Object Tracking Framework with the GMPHD Filter and Occlusion Group Management
https://github.com/SonginCV/MAF_HDA
공식 코드Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
https://github.com/Spritea/GMOT40
공식 코드https://github.com/StanfordVL/JRMOT_ROS
공식 코드JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset
https://github.com/StarsThu2016/ApproxDet
공식 코드ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
https://github.com/StiphyJay/MVCTrack
공식 코드MVCTrack: Boosting 3D Point Cloud Tracking via Multimodal-Guided Virtual Cues
https://github.com/SwinTransformer/MIM-Depth-Estimation
공식 코드https://github.com/SysCV/bdd100k-models
공식 코드BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.