Papers › Learning Audio-Video Modalities from Image Captions

Learning Audio-Video Modalities from Image Captions

1 Apr 2022arXiv:2204.00679archive 2025-07-28

Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold, Anja Hauth, Santiago Manen, Chen Sun, Cordelia Schmid

A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a new video mining pipeline which involves transferring captions from image captioning datasets to video clips with no additional manual effort. Using this pipeline, we create a new large-scale, weakly labelled audio-video captioning dataset consisting of millions of paired clips and captions. We show that training a multimodal transformed based model on this data achieves competitive performance on video retrieval and video captioning, matching or even outperforming HowTo100M pretraining with 20x fewer clips. We also show that our mined clips are suitable for text-audio pretraining, and achieve state of the art results for the task of audio retrieval.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image CaptioningRetrievalVideo CaptioningVideo RetrievalZero-Shot Video RetrievalZero-shot Text to Audio Retrieval

Datasets

Introduced by this paper, per the archive.

VideoCC3M

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Video Retrieval MSR-VTT A. Nagrani et. al. text-to-video R@1 19.4 #33 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT A. Nagrani et. al. text-to-video R@10 50.3 #33 of 41 Archive leaderboard report
Zero-Shot Video Retrieval MSR-VTT A. Nagrani et. al. text-to-video R@5 39.5 #33 of 41 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.

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