Few Shot Action Recognition On Moma Lrg

Activity Classification Accuracy (5-shot 5-way)

Subactivity Classification Accuracy (5-shot 5-way)

Results

Performance results of various models on this benchmark

			Paper Title
Name Tuning	97.9	78.2	Few-Shot Classification of Interactive Activities of Daily Living (InteractADL)
SG-VLM	92.5	32.70	MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing
OTAM	92.07	72.59	MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing
CMN	86.3	66.6	MOMA-LRG: Language-Refined Graphs for Multi-Object Multi-Actor Activity Parsing

0 of 4 row(s) selected.