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/carrell-ncl/windscreen2
공식 코드Identification of Driver Phone Usage Violations via State-of-the-Art Object Detection with Tracking
https://github.com/celltrackingchallenge/py-ctcmetrics
공식 코드https://github.com/chaoma99/lct-tracker
공식 코드Adaptive Correlation Filters with Long-Term and Short-Term Memory for Object Tracking
https://github.com/chaytonmin/occupancy-mae
공식 코드https://github.com/chaytonmin/voxel-mae
공식 코드https://github.com/chen-si-jia/Trajectory-Long-tail-Distribution-for-MOT
공식 코드Delving into the Trajectory Long-tail Distribution for Muti-object Tracking
https://github.com/chen-si-jia/crmot
공식 코드https://github.com/chen-si-jia/reamot
공식 코드ReaMOT: A Benchmark and Framework for Reasoning-based Multi-Object Tracking
https://github.com/chengche6230/rest
공식 코드ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking
https://github.com/chenshihfang/GOT
공식 코드https://github.com/chenxin-dlut/TransT
공식 코드https://github.com/chenxin-dlut/seqtrackv2
공식 코드Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking
https://github.com/chenxin-dlut/sutrack
공식 코드https://github.com/chisyliu/GnnPmbTracker
공식 코드GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles
https://github.com/chkim403/blstm-mtp
공식 코드Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking
https://github.com/chongweiliu/putr
공식 코드PuTR: A Pure Transformer for Decoupled and Online Multi-Object Tracking
https://github.com/claudiacuttano/sansa
공식 코드SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation
https://github.com/cliffordlab/edgecameratracking
공식 코드https://github.com/clips/clicr
공식 코드CliCR: A Dataset of Clinical Case Reports for Machine Reading Comprehension
https://github.com/clovermini/WPU-Net
공식 코드WPU-Net: Boundary Learning by Using Weighted Propagation in Convolution Network
https://github.com/cmpute/mmdetection3d
공식 코드Uncertainty-Aware Voxel based 3D Object Detection and Tracking with von-Mises Loss
https://github.com/cogsys-tuebingen/CBMOT
공식 코드Score refinement for confidence-based 3D multi-object tracking
https://github.com/coo1sea/ovt-b-dataset
공식 코드OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
https://github.com/corfyi/ucmctrack
공식 코드UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation
https://github.com/cst-group/cst
공식 코드Incremental procedural and sensorimotor learning in cognitive humanoid robots
https://github.com/cswaynecool/LSART
공식 코드https://github.com/ctralie/SlidingWindowVideoTDA
공식 코드(Quasi)Periodicity Quantification in Video Data, Using Topology
https://github.com/cuppp1998/360_object_tracking
공식 코드Multiple Object Detection and Tracking in Panoramic Videos for Cycling Safety Analysis
https://github.com/custommetrics-sst/sst_customevaluationmetrics
공식 코드SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing
https://github.com/cvbubbles/nonlocal-3dtracking
공식 코드Large-displacement 3D Object Tracking with Hybrid Non-local Optimization
https://github.com/cvlab-epfl/mvflow
공식 코드Multi-view Tracking Using Weakly Supervised Human Motion Prediction
https://github.com/cvlab-kaist/SOLA
공식 코드Referring Video Object Segmentation via Language-aligned Track Selection
https://github.com/cvlablums/cvgl-camera-calibration
공식 코드Camera Calibration through Geometric Constraints from Rotation and Projection Matrices
https://github.com/cwhgn/EGTracker
공식 코드An equalised global graphical model-based approach for multi-camera object tracking
https://github.com/cycelslab/mtloopresolve
공식 코드KnotResolver: Tracking self-intersecting filaments in microscopy using directed graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.