End-to-End Learning of Visual Representations from Uncurated Instructional Videos - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2020

End-to-End Learning of Visual Representations from Uncurated Instructional Videos

Résumé

Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video models still rely on manually annotated data. With the recent introduction of the HowTo100M dataset, narrated videos now offer the possibility of learning video representations without manual supervision. In this work we propose a new learning approach, MIL-NCE, capable of addressing misalignments inherent to narrated videos. With this approach we are able to learn strong video representations from scratch, without the need for any manual annotation. We evaluate our representations on a wide range of four downstream tasks over eight datasets: action recognition (HMDB-51, UCF-101, Kinetics-700), text-to-video retrieval (YouCook2, MSR-VTT), action localization (YouTube-8M Segments, CrossTask) and action segmentation (COIN). Our method outperforms all published self-supervised approaches for these tasks as well as several fully supervised baselines.

Dates et versions

hal-02433504 , version 1 (09-01-2020)

Identifiants

Citer

Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev, Josef Sivic, et al.. End-to-End Learning of Visual Representations from Uncurated Instructional Videos. 2020. ⟨hal-02433504⟩
44 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More