AI Paper Atlas

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

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition

Rameswar Panda, Chun-Fu (Richard) Chen, Quanfu Fan, Ximeng Sun, Kate Saenko, Aude Oliva, Rogerio Feris

ICCV 2021 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 61 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 LSTM to policy network (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 86.82 -> 88.17Improved
make per-modality decisions instead of joint decision (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 88.02 -> 88.17Improved
add efficiency loss (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 88.82 -> 88.17Mixed
use cost-based weights (lambda_audio 0.05) instead of equal cost weights (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 86.82 -> 88.17Improved
learned policy instead of random test-time selection (ablation)AdaMML · ActivityNet (RGB+Audio)mAP: 58.31 -> 73.91Improved
learned policy instead of random train+test selection (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 86.28 -> 88.17Improved
anneal temperature with factor 0.965 instead of 0 (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracy: 87.40 -> 88.17Improved
vary penalty factor gamma over 0, 2, 5, 10 (ablation)AdaMML · Kinetics-Sounds (RGB+Audio)top-1 accuracyNo clear effect
use adaptive modality selection instead of weighted fusion of all modalitiesweighted fusion · Kinetics-Sounds (RGB+Audio)GFLOPs: 145.17 -> 76.45Improved
use adaptive modality selection instead of weighted fusion of all modalitiesweighted fusion · ActivityNet (RGB+Audio)mAP: 72.88 -> 73.91Improved
use RGBDiff instead of flow in policy networkAdaMML · Kinetics-Sounds (RGB+Flow+Audio)top-1 accuracy: 88.54 -> 89.06Improved
use AdaMML instead of LiteEvalLiteEval · Kinetics-Sounds (vs LiteEval)top-1 accuracy: 72.02 -> 88.17Improved

Later papers that compared with this method

1 later accepted paper reports AdaMML as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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