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/alexhang212/dataset-3dpop
공식 코드https://github.com/ali2500/burst-benchmark
공식 코드BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
https://github.com/alibaba/u2mot
공식 코드https://github.com/alibaba/uvosam
공식 코드UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model
https://github.com/alversafa/chokepoint-bbs
공식 코드Attentive Deep Regression Networks for Real-Time Visual Face Tracking in Video Surveillance
https://github.com/amazon-research/siam-mot
공식 코드https://github.com/amazon-science/object-centric-multiple-object-tracking
공식 코드https://github.com/amazon-science/path-consistency
공식 코드https://github.com/amitgalor18/stc_tracker
공식 코드Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations
https://github.com/andycao1125/spikeslicer
공식 코드https://github.com/angus-apps/AEMOT
공식 코드https://github.com/arbellea/LSTM-UNet
공식 코드Microscopy Cell Segmentation via Convolutional LSTM Networks
https://github.com/argoai/argoverse-api
공식 코드https://github.com/aron-lin/seqtrack3d
공식 코드SeqTrack3D: Exploring Sequence Information for Robust 3D Point Cloud Tracking
https://github.com/asankagp/UAV-GESTURE
공식 코드UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition
https://github.com/augcog/dttd2
공식 코드Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
https://github.com/augcog/dttdv1
공식 코드https://github.com/augcog/robust-digital-twin-tracking
공식 코드Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
https://github.com/austin2wwzx/eotnet
공식 코드EOTNet: Deep Memory Aided Bayesian Filter for Extended Object Tracking
https://github.com/autonomousvision/kitti360labeltool
공식 코드KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
https://github.com/autonomousvision/kitti360scripts
공식 코드KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D
https://github.com/aybora/Semi-Automatic-Video-Annotation-OGAM
공식 코드https://github.com/ayesha-ishaq/open3dtrack
공식 코드Open3DTrack: Towards Open-Vocabulary 3D Multi-Object Tracking
https://github.com/balabooooo/aed
공식 코드Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown
https://github.com/baoxinchen/siammask_e
공식 코드https://github.com/basitalawode/uwvot400
공식 코드Improving Underwater Visual Tracking With a Large Scale Dataset and Image Enhancement
https://github.com/bdd100k/bdd100k
공식 코드BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
https://github.com/believeinlain/asynch-cv
공식 코드Real-Time Event-Based Tracking and Detection for Maritime Environments
https://github.com/bertinetto/siamese-fc
공식 코드https://github.com/bismex/RLT-DIMP
공식 코드Robust Long-Term Object Tracking via Improved Discriminative Model Prediction
https://github.com/bit-ml/sftrackpp
공식 코드SFTrack++: A Fast Learnable Spectral Segmentation Approach for Space-Time Consistent Tracking
https://github.com/bjoern-andres/graph
공식 코드Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications
https://github.com/botaoye/ostrack
공식 코드Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework
https://github.com/byminji/SLTtrack
공식 코드https://github.com/camma-public/cholectrack20
공식 코드CholecTrack20: A Dataset for Multi-Class Multiple Tool Tracking in Laparoscopic Surgery
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.