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/wenruicai/spmtrack
공식 코드https://github.com/wenwenzju/TGRMPT
공식 코드https://github.com/weslee88524/lg-mot
공식 코드https://github.com/westgate458/xb-net
공식 코드https://github.com/wish44165/ReynoldsFlow
공식 코드ReynoldsFlow: Exquisite Flow Estimation via Reynolds Transport Theorem
https://github.com/wizaca23/BBBC006-Instance-Segmentation
공식 코드https://github.com/wjn922/referformer
공식 코드https://github.com/wongkinyiu/yolov7
공식 코드YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
https://github.com/wq2012/DecisionForest
공식 코드https://github.com/wqw123wqw/pftrack
공식 코드Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approach
https://github.com/wudongming97/rmot
공식 코드https://github.com/wwsource/scenetracker
공식 코드https://github.com/xavier-lin/trackssm
공식 코드https://github.com/xiaozai/det
공식 코드https://github.com/xifen523/omnitrack
공식 코드https://github.com/xingyizhou/CenterTrack
공식 코드https://github.com/xingyizhou/GTR
공식 코드https://github.com/xinliu20/mec
공식 코드https://github.com/xinshuoweng/AB3DMOT
공식 코드3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
https://github.com/xinshuoweng/GNN3DMOT
공식 코드GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
https://github.com/xl-sr/THOR
공식 코드https://github.com/xmm-prio/bevtrack
공식 코드BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye View
https://github.com/xuboyue1999/mmtrack
공식 코드Visual and Memory Dual Adapter for Multi-Modal Object Tracking
https://github.com/xuefeng-zhu5/RGBD1K
공식 코드RGBD1K: A Large-scale Dataset and Benchmark for RGB-D Object Tracking
https://github.com/xuqingyu26/hgtmt
공식 코드Heterogeneous Graph Transformer for Multiple Tiny Object Tracking in RGB-T Videos
https://github.com/xvjiarui/VFS
공식 코드Rethinking Self-supervised Correspondence Learning: A Video Frame-level Similarity Perspective
https://github.com/yangchris11/samurai
공식 코드SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
https://github.com/yanhaowu/stssl
공식 코드Spatiotemporal Self-supervised Learning for Point Clouds in the Wild
https://github.com/yaomufeng/mmtracker
공식 코드MM-Tracker: Motion Mamba with Margin Loss for UAV-platform Multiple Object Tracking
https://github.com/yashbhalgat/contrastive-lift
공식 코드Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
https://github.com/yblei/CloudTrack
공식 코드https://github.com/ydhcg-bobo/stcmot
공식 코드STCMOT: Spatio-Temporal Cohesion Learning for UAV-Based Multiple Object Tracking
https://github.com/yfzhang1214/tcbtrack
공식 코드https://github.com/yihongXU/TransCenter
공식 코드TransCenter: Transformers with Dense Representations for Multiple-Object Tracking
https://github.com/yihongXU/deepMOT
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.