AI Paper Atlas

Research map / Video / Action recognition

VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text

Hassan Akbari, Liangzhe Yuan, Rui Qian, Wei-Hong Chuang, Shih-Fu Chang, Yin Cui, Boqing Gong

NeurIPS 2021 · Video › Action recognition · approach: Contrastive video representation learning · 333 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
Pre-train the vision Transformer with multimodal self-supervision rather than training from scratch (ablation)VATT vision backbone · ImageNettop-1 accuracy: 64.7 -> 78.7Improved
Share one Transformer backbone across video, audio, and text instead of using modality-specific backbones (ablation)VATT · Kinetics-400top-1 accuracy: 79.6 -> 79.9No clear effect
Share one Transformer backbone across video, audio, and text instead of using modality-specific backbones (ablation)VATT · AudioSetmAP: 39.4 -> 39.3No clear effect
Share one Transformer backbone across video, audio, and text (ablation)VATT · YouCook2R@10: 45.5 -> 40.6Hurt
Increase DropToken rate from 0% to 75% (ablation)VATT-MBS · HMDB51accuracy: 66.4 -> 62.5Hurt
Increase DropToken rate from 0% to 75% (ablation)VATT-MBS · UCF101accuracy: 87.6 -> 84.0Hurt
Use higher-resolution 32×320×320 inputs with 50% DropToken instead of 32×224×224 without dropping tokens (ablation)VATT video fine-tuning · Kinetics-400top-1 accuracy: 79.9 -> 80.2Improved
Increase sampled frames from 32 to 64 while using 5×16×16 patches (ablation)VATT video input · UCF101accuracy: 87.74 -> 86.57Hurt
Increase video patch size from 4×16×16 to 8×32×32 (ablation)VATT video input · UCF101accuracy: 87.8 -> 82.68Hurt
Increase waveform patch size from 128 to 256 (ablation)VATT audio input · ESC50accuracy: 87.75 -> 83.75Hurt
Replace raw waveform input with spectrogram input (ablation)VATT audio input · ESC50accuracy: 87.75 vs. 88No clear effect

Later papers that compared with this method

4 later accepted papers report VATT as a baseline in their results tables; 3 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