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/vision4robotics/SiameseTracking4UAV
공식 코드Siamese Object Tracking for Unmanned Aerial Vehicle: A Review and Comprehensive Analysis
https://github.com/vision4robotics/TACF-Tracker
공식 코드Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters
https://github.com/vision4robotics/TSD-Tracker
공식 코드https://github.com/vision4robotics/ad2attack
공식 코드Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking
https://github.com/vision4robotics/ldenhancer
공식 코드Enhancing Nighttime UAV Tracking with Light Distribution Suppression
https://github.com/vision4robotics/lpat
공식 코드https://github.com/vision4robotics/prl-track
공식 코드Progressive Representation Learning for Real-Time UAV Tracking
https://github.com/vision4robotics/sct
공식 코드Tracker Meets Night: A Transformer Enhancer for UAV Tracking
https://github.com/vision4robotics/sgdvit
공식 코드SGDViT: Saliency-Guided Dynamic Vision Transformer for UAV Tracking
https://github.com/vision4robotics/siamsa
공식 코드Siamese Object Tracking for Vision-Based UAM Approaching with Pairwise Scale-Channel Attention
https://github.com/vision4robotics/udat
공식 코드Unsupervised Domain Adaptation for Nighttime Aerial Tracking
https://github.com/visionml/pytracking
공식 코드https://github.com/visipedia/caltech-fish-counting
공식 코드The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting
https://github.com/vislearn/libct
공식 코드https://github.com/vukasin-stanojevic/BoostTrack
공식 코드BoostTrack++: using tracklet information to detect more objects in multiple object tracking
https://github.com/wangbiao2/r1-track
공식 코드R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning
https://github.com/wangdongdut/Long-term-Visual-Tracking
공식 코드https://github.com/wangjk666/omnivid
공식 코드OmniVid: A Generative Framework for Universal Video Understanding
https://github.com/wangxiao5791509/DeepMTA_PyTorch
공식 코드Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking
https://github.com/wangxiao5791509/LGSearch_DDGAN_PyTorch
공식 코드Tracking by Joint Local and Global Search: A Target-aware Attention based Approach
https://github.com/wangxiao5791509/RGB-DVS-SOT-Baselines
공식 코드VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
https://github.com/wangxiao5791509/Single_Object_Tracking_Paper_List
공식 코드Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
https://github.com/wangxiao5791509/TNL2K_evaluation_toolkit
공식 코드Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
https://github.com/wangxiao5791509/VisEvent_SOT_Benchmark
공식 코드VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows
https://github.com/wangxiyang2022/DeepFusionMOT
공식 코드https://github.com/wangxiyang2022/YONTD-MOT
공식 코드You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
https://github.com/wangyc2000/pd_sort
공식 코드PD-SORT: Occlusion-Robust Multi-Object Tracking Using Pseudo-Depth Cues
https://github.com/wassimea/thermalmot
공식 코드https://github.com/weigertlab/trackastra
공식 코드Trackastra: Transformer-based cell tracking for live-cell microscopy
https://github.com/weihaosky/CycleSiam
공식 코드Self-supervised Object Tracking with Cycle-consistent Siamese Networks
https://github.com/weiliu89/caffe
공식 코드https://github.com/wenbowen123/BundleTrack
공식 코드BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models
https://github.com/wenbowen123/catgrasp
공식 코드You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration
https://github.com/wenbowen123/iros20-6d-pose-tracking
공식 코드Vision-driven Compliant Manipulation for Reliable, High-Precision Assembly Tasks
https://github.com/wencheng256/SiamBAN-ACM
공식 코드Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.