AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition

Xinyu Gong, Sreyas Mohan, Naina Dhingra, Jean-Charles Bazin, Yilei Li, Zhangyang Wang, Rakesh Ranjan

CVPR 2023 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add cross-modal contrastive alignment loss (ablation)MMG-Ego4D · MMG-Ego4D supervised zero-shot cross-modal, train audio+IMU, test videoTop-1 accuracy: 2.37 -> 25.03Improved
Add cross-modal contrastive alignment loss (ablation)MMG-Ego4D · MMG-Ego4D few-shot zero-shot cross-modal, support audio+IMU, query video5-way 5-shot accuracy: 33.93 -> 51.40Improved
Add cross-modal contrastive alignment loss (ablation)MMG-Ego4D · MMG-Ego4D supervised regularTop-1 accuracy: 52.18 -> 55.66Improved
Use attention-based Transformer fusion instead of MLP fusion (ablation)MMG-Ego4D · MMG-Ego4D supervised regularTop-1 accuracy: 52.79 -> 55.66Improved
Use attention-based Transformer fusion instead of MLP fusion (ablation)MMG-Ego4D · MMG-Ego4D supervised missing modality, test audio+IMUTop-1 accuracy: 32.89 -> 37.07Improved
Use attention-based Transformer fusion instead of MLP fusion (ablation)MMG-Ego4D · MMG-Ego4D few-shot zero-shot cross-modal, support audio+IMU, query video5-way 5-shot accuracy: 51.08 -> 51.40Improved
Add cross-modal prototypical loss (ablation)MMG-Ego4D · MMG-Ego4D few-shot regular5-way 5-shot accuracy: 62.37 -> 63.00Improved
Add cross-modal prototypical loss (ablation)MMG-Ego4D · MMG-Ego4D few-shot missing modality, query audio+IMU5-way 5-shot accuracy: 50.03 -> 50.77Improved
Add cross-modal prototypical loss (ablation)MMG-Ego4D · MMG-Ego4D few-shot zero-shot cross-modal, support audio+IMU, query video5-way 5-shot accuracy: 50.80 -> 51.40Improved
Use modality dropout during fusion training (ablation)MMG-Ego4D · MMG-Ego4D generalization tasksaccuracyNo clear effect
Average all fusion output tokens rather than use the CLS token (ablation)MMG-Ego4D · MMG-Ego4D action recognitionaccuracyImproved
Add modality-specific embeddings before fusion (ablation)MMG-Ego4D · MMG-Ego4D action recognitionaccuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy