https://github.com/MasterBin-IIAU/UNINEXT
공식 코드Universal Instance Perception as Object Discovery and Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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 )
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Universal Instance Perception as Object Discovery and Retrieval
Online Multi-Object Tracking and Segmentation with GMPHD Filter and Mask-based Affinity Fusion
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
Do Different Tracking Tasks Require Different Appearance Models?
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
Multi-Object Tracking and Segmentation via Neural Message Passing
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
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.