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/mobiface/mobiface.github.io
공식 코드MobiFace: A Novel Dataset for Mobile Face Tracking in the Wild
https://github.com/mohamednagymostafa/dfr-fastmot
공식 코드https://github.com/mohamednagymostafa/kitti-mot.bench-evals
공식 코드https://github.com/mschwimmbeck/hola
공식 코드https://github.com/msight-tech/research-siamattn
공식 코드Deformable Siamese Attention Networks for Visual Object Tracking
https://github.com/msprITU/TDIOT
공식 코드TDIOT: Target-driven Inference for Deep Video Object Tracking
https://github.com/mumuqiao/mixcycle
공식 코드MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency
https://github.com/myfavouritekk/vdetlib
공식 코드Object Detection from Video Tubelets with Convolutional Neural Networks
https://github.com/nadezola/intothefog_mot17
공식 코드Into the Fog: Evaluating Robustness of Multiple Object Tracking
https://github.com/naivete5656/WSCTBFP
공식 코드Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation
https://github.com/nanh5837/lettucemots
공식 코드https://github.com/nathan-li123/lamot
공식 코드https://github.com/necla-ml/cater-h
공식 코드https://github.com/nesl/gdtm
공식 코드GDTM: An Indoor Geospatial Tracking Dataset with Distributed Multimodal Sensors
https://github.com/neufieldrobotics/neuflow
공식 코드NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices
https://github.com/nicholasli1995/pcp-mv
공식 코드https://github.com/nightwatch-fox11/cgtrack
공식 코드CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking
https://github.com/nii-satoh-lab/mot_fcg
공식 코드Multiple Object Tracking from appearance by hierarchically clustering tracklets
https://github.com/niraharon/bot-sort
공식 코드https://github.com/nju-pcalab/sttrack
공식 코드Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking
https://github.com/noahcao/OC_SORT
공식 코드Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking
https://github.com/noajshu/learning_irreps
공식 코드https://github.com/norahgreen/rtracker
공식 코드RTracker: Recoverable Tracking via PN Tree Structured Memory
https://github.com/noyzzz/emap
공식 코드Ego-Motion Aware Target Prediction Module for Robust Multi-Object Tracking
https://github.com/nttcom/wasb-sbdt
공식 코드Widely Applicable Strong Baseline for Sports Ball Detection and Tracking
https://github.com/nusneuromorphic/cEOT
공식 코드A Hybrid Neuromorphic Object Tracking and Classification Framework for Real-time Systems
https://github.com/nwojke/deep_sort
공식 코드Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/o-vigia/gma3d
공식 코드GMA3D: Local-Global Attention Learning to Estimate Occluded Motions of Scene Flow
https://github.com/ocetintas/mpntrackseg
공식 코드Multi-Object Tracking and Segmentation via Neural Message Passing
https://github.com/open-mmlab/mmtracking
공식 코드https://github.com/open-starlab/trackid3x3
공식 코드https://github.com/openat25/hiptrack-mls
공식 코드https://github.com/opencodegithub/h-dcpt
공식 코드https://github.com/opendr-eu/opendr
공식 코드VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images
https://github.com/opengvlab/internvideo
공식 코드InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.