CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets

preprint OA: closed CC-BY-4.0

Abstract

Challenges in cross-learning involve inhomogeneous or even inadequate amount of training data and lack of resources for retraining large pretrained models. Inspired by transfer learning techniques in NLP, adapters and prefix tuning, this paper presents a new model-agnostic plugin architecture for cross-learning, called CM3T, that adapts transformer-based models to new or missing information. We introduce two adapter blocks: multi-head vision adapters for transfer learning and cross-attention adapters for multimodal learning. Training becomes substantially efficient as the backbone and other plugins do not need to be finetuned along with these additions. Comparative and ablation studies on three datasets Epic-Kitchens-100, MPIIGroupInteraction and UDIVA v0.5 show efficacy of this framework on different recording settings and tasks. With only 12.8% trainable parameters compared to the backbone to process video input and only 22.3% trainable parameters for two additional modalities, we achieve comparable and even better results than the state-of-the-art. CM3T has no specific requirements for training or pretraining and is a step towards bridging the gap between a general model and specific practical applications of video classification.
Full text 621 characters · extracted from oa-doi-fallback · click to expand
There is a newer version available for this {{ publicationType }}. View latest version {{ publication.field_name }} {{ publication.subfield_name }} Copyright: © {{ publicationYear }} {{ publication.presentation_authors[0].full_name + (publication.presentation_authors.length > 1 ? ' et al' : '') }}. This is an open access publication distributed under the terms of the CC BY 4.0 License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Check the {{ publicationType | capitalize }} Source for copyright and license information. Listen on

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: oa-doi-fallback

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-06-04T02:00:05.705006+00:00
License: CC-BY-4.0