Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Action Anticipation On Epic Kitchens 100

Metriken

Recall@5

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	Recall@5	Paper Title	Repository
TempAgg	14.73	Technical Report: Temporal Aggregate Representations
PlausiVL	27.60	Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models	-
UADT	23.0	Uncertainty-aware Action Decoupling Transformer for Action Anticipation	-
MeMViT-24	17.7	MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition
RU-LSTM	13.94	Rescaling Egocentric Vision
AVT+	15.9	Anticipative Video Transformer
InAViT	25.89	Interaction Region Visual Transformer for Egocentric Action Anticipation
S-GEAR	19.9	Semantically Guided Representation Learning For Action Anticipation
AFFT	18.5	Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation	-

0 of 9 row(s) selected.