https://github.com/SysCV/pcan
공식 코드Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
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/SysCV/qdtrack
공식 코드Quasi-Dense Similarity Learning for Multiple Object Tracking
https://github.com/SysCV/tet
공식 코드https://github.com/TRI-ML/permatrack
공식 코드https://github.com/TomG008/SkyNet
공식 코드SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
https://github.com/TrackerLB/SPSTracker
공식 코드SPSTracker: Sub-Peak Suppression of Response Map for Robust Object Tracking
https://github.com/TrackingLaboratory/CAMELTrack
공식 코드CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking
https://github.com/TripleJoy/SAM2MOT
공식 코드SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentation
https://github.com/TuSimple/LiDAR_SOT
공식 코드Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences
https://github.com/UARK-AICV/TrackGUI
공식 코드TrackMe:A Simple and Effective Multiple Object Tracking Annotation Tool
https://github.com/UMich-BipedLab/LiDARTag
공식 코드https://github.com/UMich-BipedLab/global_pose_estimation_for_optimal_shape
공식 코드https://github.com/VISION-SJTU/IoUattack
공식 코드IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
https://github.com/VisDrone/VisDrone-Dataset
공식 코드https://github.com/WesleyHsieh0806/TAO-Amodal
공식 코드https://github.com/XU-TIANYANG/GFS-DCF
공식 코드Joint Group Feature Selection and Discriminative Filter Learning for Robust Visual Object Tracking
https://github.com/XU-TIANYANG/LADCF
공식 코드https://github.com/XuChenLong/LMTrack
공식 코드Less is More: Token Context-aware Learning for Object Tracking
https://github.com/YihengZhang-CV/SeCo-Sequence-Contrastive-Learning
공식 코드SeCo: Exploring Sequence Supervision for Unsupervised Representation Learning
https://github.com/YilmazKadir/Mask4Former
공식 코드https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker
공식 코드Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers
https://github.com/ZekuiQin/SiamKPN
공식 코드Siamese Keypoint Prediction Network for Visual Object Tracking
https://github.com/Zhongdao/Towards-Realtime-MOT
공식 코드https://github.com/Zhongdao/UniTrack
공식 코드Do Different Tracking Tasks Require Different Appearance Models?
https://github.com/ZwwWayne/mmMOT
공식 코드https://github.com/abewley/sort
공식 코드https://github.com/abhineet123/deep_mdp
공식 코드https://github.com/adnanb97/opencv-multiple-object-tracking
공식 코드https://github.com/aharley/pips
공식 코드Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories
https://github.com/aifarms/multi-camera-pig-tracking
공식 코드Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras
https://github.com/ailovejinx/gsot3d
공식 코드GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
https://github.com/akosiorek/hart
공식 코드https://github.com/aktgpt/vq-nnf
공식 코드Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour Fields
https://github.com/alanlukezic/csr-dcf
공식 코드Discriminative Correlation Filter with Channel and Spatial Reliability
https://github.com/alanlukezic/d3s
공식 코드https://github.com/alanzty/mo3tr
공식 코드Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.