Papers › Self-Supervised MultiModal Versatile Networks
Self-Supervised MultiModal Versatile Networks
Jean-Baptiste Alayrac, Adrià Recasens, Rosalia Schneider, Relja Arandjelović, Jason Ramapuram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, Andrew Zisserman
Videos are a rich source of multi-modal supervision. In this work, we learn representations using self-supervision by leveraging three modalities naturally present in videos: visual, audio and language streams. To this end, we introduce the notion of a multimodal versatile network -- a network that can ingest multiple modalities and whose representations enable downstream tasks in multiple modalities. In particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a common embedding. Driven by versatility, we also introduce a novel process of deflation, so that the networks can be effortlessly applied to the visual data in the form of video or a static image. We demonstrate how such networks trained on large collections of unlabelled video data can be applied on video, video-text, image and audio tasks. Equipped with these representations, we obtain state-of-the-art performance on multiple challenging benchmarks including UCF101, HMDB51, Kinetics600, AudioSet and ESC-50 when compared to previous self-supervised work. Our models are publicly available.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Audio Classification | AudioSet | MMV | Test mAP | 0.309 | #48 of 51 | Archive leaderboard | report |
| Self-Supervised Action Recognition | HMDB51 (finetuned) | MMV | Top-1 Accuracy | 70.1 | #2 of 14 | Archive leaderboard | report |
| Self-Supervised Action Recognition | Kinetics-600 | MMV | Top-1 Accuracy | 55.5 | #5 of 5 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | MMV TSM-50x2 | 3-fold Accuracy | 95.2 | #8 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | MMV TSM-50x2 | Frozen | false | #8 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 | MMV TSM-50x2 | Pre-Training Dataset | Audioset + Howto100M | #8 of 53 | Archive leaderboard | report |
| Self-Supervised Action Recognition | UCF101 (finetuned) | MMV | 3-fold Accuracy | 91.5 | #8 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Introduced by this paper: Deflation
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections