# CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction Datasets

arXiv: https://arxiv.org/abs/2501.03332 · HTML: https://mlsanity.com/paper/2501.03332/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 40 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Compacter: Efficient Low-Rank Hypercomplex Adapter Layers](https://mlsanity.com/paper/2106.04647/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [PPT: Pre-trained Prompt Tuning for Few-shot Learning](https://mlsanity.com/paper/2109.04332/) (2021)
- [Training Neural Networks with Fixed Sparse Masks](https://mlsanity.com/paper/2111.09839/) (2021)
- [ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2206.13559/) (2022)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning](https://mlsanity.com/paper/2110.07577/) (2021)
- [Multiview Transformers for Video Recognition](https://mlsanity.com/paper/2201.04288/) (2022)
- [A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis](https://mlsanity.com/paper/2006.15955/) (2020)
- [Dual-path Adaptation from Image to Video Transformers](https://mlsanity.com/paper/2303.09857/) (2023)
- [Context-Aware Personality Inference in Dyadic Scenarios: Introducing the UDIVA Dataset](https://mlsanity.com/paper/2012.14259/) (2020)
- [Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation](https://mlsanity.com/paper/2002.08267/) (2020)
- [M&M Mix: A Multimodal Multiview Transformer Ensemble](https://mlsanity.com/paper/2206.09852/) (2022)

## Abstract (arXiv)

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.