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/siyuanliii/slack
공식 코드SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking
https://github.com/sjc042/gta-link
공식 코드GTA: Global Tracklet Association for Multi-Object Tracking in Sports
https://github.com/skyesong38/cswintt
공식 코드https://github.com/skyoung/MemTrack
공식 코드https://github.com/smaityumich/concept-drift
공식 코드Predictor-corrector algorithms for stochastic optimization under gradual distribution shift
https://github.com/smartroboticslab/deep_prob_feature_track
공식 코드https://github.com/smartroboticslab/vimid
공식 코드Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation
https://github.com/soccernet/sn-calibration
공식 코드https://github.com/soccernet/sn-grounding
공식 코드https://github.com/soccernet/sn-reid
공식 코드https://github.com/soccernet/sn-spotting
공식 코드https://github.com/soccernet/sn-tracking
공식 코드https://github.com/songguocode/TADAM
공식 코드https://github.com/songheony/AAA-journal
공식 코드AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee
https://github.com/sparktempest/bat
공식 코드https://github.com/spirka3/master-cnn
공식 코드Evaluating the Significance of Outdoor Advertising from Driver's Perspective Using Computer Vision
https://github.com/ssspc333/tenet
공식 코드https://github.com/stevenwudi/KMC_cvprw_2017
공식 코드https://github.com/stiphyjay/pillartrack
공식 코드https://github.com/stmstmstm/stm
공식 코드https://github.com/sukjunhwang/set_classifier
공식 코드https://github.com/supertyd/XTrack
공식 코드XTrack: Multimodal Training Boosts RGB-X Video Object Trackers
https://github.com/surgical-vision/colmap-match-converter
공식 코드Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks
https://github.com/sydney0zq/PTSNet
공식 코드Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
https://github.com/synsin0/srcn3d
공식 코드SRCN3D: Sparse R-CNN 3D for Compact Convolutional Multi-View 3D Object Detection and Tracking
https://github.com/szabogergely0419/ppcu_ifom_yeasttracker
공식 코드Enhancing Cell Tracking with a Time-Symmetric Deep Learning Approach
https://github.com/szcf-weiya/TriMatchMOT
공식 코드Appearance-free Tripartite Matching for Multiple Object Tracking
https://github.com/t-montes/viqagent
공식 코드ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation
https://github.com/tacju/axial-vs
공식 코드A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
https://github.com/tacju/maxtron
공식 코드A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
https://github.com/talbenha/cell-tracker-gnn
공식 코드https://github.com/tankowa/consistencytrack
공식 코드ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model
https://github.com/taohan10200/drnet
공식 코드DR.VIC: Decomposition and Reasoning for Video Individual Counting
https://github.com/tchuanm/avitmp
공식 코드AViTMP: A Tracking-Specific Transformer for Single-Branch Visual Tracking
https://github.com/tchuanm/sftranst
공식 코드Learning Spatial-Frequency Transformer for Visual Object Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.