End-to-End Learning of Visual Representations from Uncurated Instructional Videos - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

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

Abstract

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.
Fichier principal
Vignette du fichier
miech17ICCV.pdf (3.17 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01569540 , version 1 (27-07-2017)
hal-01569540 , version 2 (28-07-2017)

Identifiers

Cite

Antoine Miech, Jean-Baptiste Alayrac, Piotr Bojanowski, Ivan Laptev, Josef Sivic. End-to-End Learning of Visual Representations from Uncurated Instructional Videos. CVPR 2020 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2020, Seattle / Virtual, United States. ⟨hal-01569540v2⟩
310 View
1421 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More