HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Multi Object Tracking On 2024 Ai City

평가 지표

AssA

DetA

HOTA

LocA

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	AssA	DetA	HOTA	LocA	Paper Title	Repository
Asilla	32.50	53.80	40.34	89.57	Efficient online multi-camera tracking with memory-efficient accumulated appearance features and trajectory validation	-
UW-ETRI	54.80	59.88	57.14	91.24	An Online Approach and Evaluation Method for Tracking People Across Cameras in Extremely Long Video Sequence	-
ARV	48.07	54.85	51.06	89.61	Online Multi-camera People Tracking with Spatial-temporal Mechanism and Anchor-feature Hierarchical Clustering
Yachiyo	71.81	72.10	71.94	88.39	Overlap Suppression Clustering for Offline Multi-Camera People Tracking	-
SJTU-Lenovo	55.06	84.03	67.22	93.82	A Robust Online Multi-Camera People Tracking System With Geometric Consistency and State-aware Re-ID Correction
FraunhoferIOSB	55.20	69.54	60.88	87.97	OCMCTrack: Online Multi-Target Multi-Camera Tracking with Corrective Matching Cascade	-
Nota	54.96	68.37	60.93	90.62	Cluster Self-Refinement for Enhanced Online Multi-Camera People Tracking
BEV-SUSHI	76.19	86.94	81.22	95.67	MCBLT: Multi-Camera Multi-Object 3D Tracking in Long Videos	-

0 of 8 row(s) selected.

Multi Object Tracking On 2024 Ai City | SOTA | HyperAI초신경