M&M Mix: A Multimodal Multiview Transformer Ensemble
This report describes the approach behind our winning solution to the 2022 Epic-Kitchens Action Recognition Challenge. Our approach builds upon our recent work, Multiview Transformer for Video Recognition (MTV), and adapts it to multimodal inputs. Our final submission consists of an ensemble of Multimodal MTV (M&M) models varying backbone sizes and input modalities. Our approach achieved 52.8% Top-1 accuracy on the test set in action classes, which is 4.1% higher than last year's winning entry.
PDF Abstract
Datasets
Kinetics
Kinetics 400
EPIC-KITCHENS-100
Results from the Paper
Ranked #2 on
Action Recognition
on EPIC-KITCHENS-100
(using extra training data)
