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/emecercelik/Temp-Frustum-Net
공식 코드https://github.com/emirhanbayar/fast-deep-oc-sort
공식 코드When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking
https://github.com/emirhanbayar/fast-strongsort
공식 코드When to Extract ReID Features: A Selective Approach for Improved Multiple Object Tracking
https://github.com/erkara/trackingdroplets
공식 코드Deep Learning Based Object Tracking in Walking Droplet and Granular Intruder Experiments
https://github.com/eth-pbl/cr3dt
공식 코드https://github.com/ethz-asl/object_keypoints
공식 코드Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses
https://github.com/ethz-asl/tsdf-plusplus
공식 코드TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
https://github.com/event-ahu/adversarial_attack_defense
공식 코드Adversarial Attack for RGB-Event based Visual Object Tracking
https://github.com/event-ahu/awesome_modern_hopfield_networks
공식 코드Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline
https://github.com/event-ahu/coesot
공식 코드Revisiting Color-Event based Tracking: A Unified Network, Dataset, and Metric
https://github.com/event-ahu/cross_resolution_sot
공식 코드CRSOT: Cross-Resolution Object Tracking using Unaligned Frame and Event Cameras
https://github.com/event-ahu/eventvot_benchmark
공식 코드Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline
https://github.com/event-ahu/felt_sot_benchmark
공식 코드Long-term Frame-Event Visual Tracking: Benchmark Dataset and Baseline
https://github.com/event-ahu/mamba_fetrack
공식 코드Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking
https://github.com/event-ahu/mambaevt
공식 코드MambaEVT: Event Stream based Visual Object Tracking using State Space Model
https://github.com/event-ahu/slowfast_event_track
공식 코드Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach
https://github.com/exiawsh/streampetr
공식 코드Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
https://github.com/facebookresearch/DVDialogues
공식 코드DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue
https://github.com/facebookresearch/co-tracker
공식 코드https://github.com/facebookresearch/sam2
공식 코드https://github.com/facias914/A-Simple-Detector-is-a-Strong-Tracker
공식 코드https://github.com/fandulu/MPLT
공식 코드Using Panoramic Videos for Multi-person Localization and Tracking in a 3D Panoramic Coordinate
https://github.com/fandulu/asad
공식 코드Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
https://github.com/farazlotfi/underwater-object-tracking
공식 코드https://github.com/fatemehN/TrackPGD
공식 코드TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
https://github.com/fatemehN/entangled_representation
공식 코드$β$-Multivariational Autoencoder for Entangled Representation Learning in Video Frames
https://github.com/fatemehn/reproducibilitystudy
공식 코드Reproducibility Study on Adversarial Attacks Against Robust Transformer Trackers
https://github.com/favyen/uns20
공식 코드Self-Supervised Multi-Object Tracking with Cross-Input Consistency
https://github.com/feiaxyt/Winner_ECCV20_TAO
공식 코드1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking
https://github.com/florinshum/ulast
공식 코드https://github.com/flowerfan/trackron
공식 코드https://github.com/foolwood/DCFNet
공식 코드DCFNet: Discriminant Correlation Filters Network for Visual Tracking
https://github.com/foolwood/DaSiamRPN
공식 코드Distractor-aware Siamese Networks for Visual Object Tracking
https://github.com/fordevoted/uiess
공식 코드Domain Adaptation for Underwater Image Enhancement via Content and Style Separation
https://github.com/fpthink/stnet
공식 코드3D Siamese Transformer Network for Single Object Tracking on Point Clouds
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.