HyperAI초신경

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

한국어

HyperAI초신경

Video Classification On Breakfast

평가 지표

Accuracy (%)

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy (%)	Paper Title	Repository
D-Sprv.	89.9	Learning To Recognize Procedural Activities with Distant Supervision
Timeception	71.3	Timeception for Complex Action Recognition
MA-LMM	93.0	MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
GHRM	75.5	Graph-Based High-Order Relation Modeling for Long-Term Action Recognition	-
ViS4mer	88.2	Long Movie Clip Classification with State-Space Video Models
S5	90.7	Selective Structured State-Spaces for Long-Form Video Understanding	-
VideoGraph	69.5	VideoGraph: Recognizing Minutes-Long Human Activities in Videos	-
HERMES	95.2	HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
TranS4mer	90.27	Efficient Movie Scene Detection using State-Space Transformers

0 of 9 row(s) selected.

Video Classification On Breakfast | SOTA | HyperAI초신경