Masking Modalities for Cross-modal Video Retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2022

Masking Modalities for Cross-modal Video Retrieval

Abstract

Pre-training on large scale unlabelled datasets has shown impressive performance improvements in the fields of computer vision and natural language processing. Given the advent of large-scale instructional video datasets, a common strategy for pre-training video encoders is to use the accompanying speech as weak supervision. However, as speech is used to supervise the pre-training, it is never seen by the video encoder, which does not learn to process that modality. We address this drawback of current pre-training methods, which fail to exploit the rich cues in spoken language. Our proposal is to pre-train a video encoder using all the available video modalities as supervision, namely, appearance, sound, and transcribed speech. We mask an entire modality in the input and predict it using the other two modalities. This encourages each modality to collaborate with the others, and our video encoder learns to process appearance and audio as well as speech. We show the superior performance of our 'modality masking' pre-training approach for video retrieval on the How2R, YouCook2 and Condensed Movies datasets.
Fichier principal
Vignette du fichier
MMCVR.pdf (5.23 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03420133 , version 1 (09-11-2021)

Identifiers

Cite

Valentin Gabeur, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid. Masking Modalities for Cross-modal Video Retrieval. WACV 2022 - Winter Conference on Applications of Computer Vision, Jan 2022, Waikoloa, United States. pp.1-10. ⟨hal-03420133⟩
218 View
78 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More