M&M Mix: A Multimodal Multiview Transformer Ensemble

Anurag Arnab; Arsha Nagrani; Cordelia Schmid; Xuehan Xiong

M&M Mix: A Multimodal Multiview Transformer Ensemble

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.09852 v1 pith:4K7JUGKW submitted 2022-06-20 cs.CV

Xuehan Xiong , Anurag Arnab , Arsha Nagrani , Cordelia Schmid This is my paper

classification cs.CV

keywords approachmultimodalactionensemblemultiviewrecognitiontransformerwinning

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

Improving Keystep Recognition in Ego-Video via Dexterous Focus
cs.CV 2025-06 conditional novelty 6.0 of 10

Hand-focused, stabilized cropping of ego-video improves Ego-Exo4D fine-grained keystep recognition accuracy from 39.18% to 45.81% (hands only) and 47.75% (hands plus ego).

Pith tools