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/insomnia94/FTMU
공식 코드Fast Template Matching and Update for Video Object Tracking and Segmentation
https://github.com/introlab/dotmask
공식 코드https://github.com/ireneperezsalesa/event_tracking
공식 코드https://github.com/ismarou/How_to_track_your_Dragon
공식 코드https://github.com/isosnovik/SiamSE
공식 코드https://github.com/it3dego/it3dego
공식 코드https://github.com/iyybpatrick/MKCF
공식 코드Multiple Object Tracking with Kernelized Correlation Filters in Urban Mixed Traffic
https://github.com/jackwoo0831/depthmot
공식 코드https://github.com/james128333/HarDNet-MSEG
공식 코드https://github.com/jaraxxus-me/pvt_pp
공식 코드PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
https://github.com/jasonkks/pttr
공식 코드PTTR: Relational 3D Point Cloud Object Tracking with Transformer
https://github.com/javiribera/locating-objects-without-bboxes
공식 코드https://github.com/jeanollion/distnet
공식 코드https://github.com/jerryx1110/robust-video-object-segmentation
공식 코드Towards Robust Video Object Segmentation with Adaptive Object Calibration
https://github.com/jhl-hust/trasw
공식 코드Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
https://github.com/jianglongye/implicit-tracking
공식 코드Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
https://github.com/jiaweihe1996/GMTracker
공식 코드https://github.com/jiawen-zhu/hqtrack
공식 코드https://github.com/jiawen-zhu/trackgpt
공식 코드https://github.com/jiawen-zhu/vipt
공식 코드https://github.com/jimmy-dq/dmt
공식 코드A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
https://github.com/jimmy-dq/dropmae
공식 코드DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks
https://github.com/jinyanglii/ovtr
공식 코드OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer
https://github.com/joe-rabbit/videoqa_pilot_study
공식 코드https://github.com/jongwon20000/TRACA
공식 코드Context-aware Deep Feature Compression for High-speed Visual Tracking
https://github.com/jovanavidenovic/dam4sam
공식 코드A Distractor-Aware Memory for Visual Object Tracking with SAM2
https://github.com/jp-lan/procontext
공식 코드ProContEXT: Exploring Progressive Context Transformer for Tracking
https://github.com/jubiotech/pyuat
공식 코드PyUAT: Open-source Python framework for efficient and scalable cell tracking
https://github.com/julianolagana/mt3v2
공식 코드Can Deep Learning be Applied to Model-Based Multi-Object Tracking?
https://github.com/jumabek/lite
공식 코드LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration
https://github.com/junjie18/cmt
공식 코드Cross Modal Transformer: Towards Fast and Robust 3D Object Detection
https://github.com/jzhang2008/L1CFT_ACLKS
공식 코드https://github.com/kalyan0510/totem
공식 코드https://github.com/kangben258/MCITrack
공식 코드Exploring Enhanced Contextual Information for Video-Level Object Tracking
https://github.com/kemo-huang/bitrack
공식 코드BiTrack: Bidirectional Offline 3D Multi-Object Tracking Using Camera-LiDAR Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.