Papers with Code 아카이브
Multi-Object Tracking and Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 9
Multiple object tracking and segmentation requires detecting, tracking, and segmenting objects belonging to a set of given classes.
(Image and definition credit: Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation, NeurIPS 2021, Spotlight )
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation
Deep Learning Techniques for Video Instance Segmentation: A Survey
Universal Instance Perception as Object Discovery and Retrieval
Track Targets by Dense Spatio-Temporal Position Encoding
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Multi-Object Tracking and Segmentation via Neural Message Passing
Towards Grand Unification of Object Tracking
PolyTrack: Tracking with Bounding Polygons
Multi-Object Tracking and Segmentation with a Space-Time Memory Network
DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception
MeNToS: Tracklets Association with a Space-Time Memory Network
Do Different Tracking Tasks Require Different Appearance Models?
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
MOTS R-CNN: Cosine-margin-triplet loss for multi-object tracking
Weakly Supervised Multi-Object Tracking and Segmentation
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation
PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Learning Multi-Object Tracking and Segmentation from Automatic Annotations
MOTS: Multi-Object Tracking and Segmentation
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.