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/lpmp/bdd
공식 코드https://github.com/lpxtt/simtrack
공식 코드Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
https://github.com/lql-team/TSDM
공식 코드TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator
https://github.com/lvsn/rgbde_tracking
공식 코드RGB-D-E: Event Camera Calibration for Fast 6-DOF Object Tracking
https://github.com/malga-vision/fastervideo
공식 코드FasterVideo: Efficient Online Joint Object Detection And Tracking
https://github.com/malikaratnayake/polytrack2.0
공식 코드Spatial Monitoring and Insect Behavioural Analysis Using Computer Vision for Precision Pollination
https://github.com/marc1198/chat-hsr
공식 코드LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics
https://github.com/mark12ding/sam2long
공식 코드SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree
https://github.com/martin-danelljan/Continuous-ConvOp
공식 코드Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
https://github.com/masqm/Faster-Mean-Shift
공식 코드https://github.com/masterbin-iiau/unicorn
공식 코드https://github.com/mattiasegu/darth
공식 코드DARTH: Holistic Test-time Adaptation for Multiple Object Tracking
https://github.com/mbzuai-oryx/videomolmo
공식 코드https://github.com/mcg-nju/memotr
공식 코드MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
https://github.com/medicinetoken/medical-sam2
공식 코드Medical SAM 2: Segment medical images as video via Segment Anything Model 2
https://github.com/megvii-model/MOTR
공식 코드https://github.com/megvii-research/MOTRv2
공식 코드The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
https://github.com/megvii-research/mctrack
공식 코드MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving
https://github.com/megvii-research/motr
공식 코드https://github.com/mehmetaygun/4d-pls
공식 코드https://github.com/mehta-lab/viscy
공식 코드Contrastive learning of cell state dynamics in response to perturbations
https://github.com/melax/hand_tracking_samples
공식 코드https://github.com/memoryunreal/rgbd-tracking-review
공식 코드https://github.com/mengting2023/lg-track
공식 코드https://github.com/meyerls/fruitnerf
공식 코드FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework
https://github.com/mhnasseri/for_tracking
공식 코드https://github.com/mhnasseri/sort_oh
공식 코드Simple online and real-time tracking with occlusion handling
https://github.com/miagrouput/implicit-cell-surfaces
공식 코드Generative modeling of living cells with SO(3)-equivariant implicit neural representations
https://github.com/minghanli/univs
공식 코드UniVS: Unified and Universal Video Segmentation with Prompts as Queries
https://github.com/mit-han-lab/bevfusion
공식 코드BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
https://github.com/miv-xjtu/artrack
공식 코드ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
https://github.com/mlvlab/drone_ai_challenge
공식 코드https://github.com/mlvlab/drone_task1
공식 코드https://github.com/mlvlab/drone_task4
공식 코드https://github.com/mlvlab/rony2_task3
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.