AI Paper Atlas

Research map / Video / Video segmentation and tracking

Broaden Your Views for Self-Supervised Video Learning

Adrià Recasens, Pauline Luc, Jean-Baptiste Alayrac, Luyu Wang, Florian Strub, Corentin Tallec, Mateusz Malinowski, Viorica Pătrăucean, Florent Altché, Michal Valko, Jean-Bastien Grill, Aäron van den Oord and 1 more

ICCV 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 98 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
lengthen broad view from 1.3s to 10s (narrow 1.3s) (ablation)BraVe RGB+RC · HMDB51 linear (K600 ablation)top-1 accuracy: 59.8 -> 65.2Improved
use 10s narrow view as well as 10s broad view (ablation)BraVe RGB+RC · HMDB51 linear (K600 ablation)top-1 accuracy: 65.2 -> 58.0Hurt
sync narrow and broad view start for visual broad view (ablation)BraVe RGB+RC · UCF101 linear (K600 ablation)top-1 accuracy: 91.7 -> 87.5Hurt
use random convolutions in the broad view instead of plain RGB (ablation)BraVe · HMDB51 linear (K600 ablation)top-1 accuracy: 63.2 -> 65.2Improved
use optical flow instead of RGB+RC in the broad view (ablation)BraVe · HMDB51 linear (K600 ablation)top-1 accuracy: 65.2 -> 66.4Mixed
add a second and third RGB+RC broad view (ablation)BraVe · Kinetics-600 linear (K600 ablation)top-1 accuracy: 69.1 -> 70.8Improved
add both RGB+RC and flow broad views (1+1) (ablation)BraVe · HMDB51 linear (K600 ablation)top-1 accuracy: 65.2 -> 68.5Improved
share the projector between narrow and broad views (ablation)BraVe · HMDB51 linear (weight-sharing ablation, plain RGB broad)top-1 accuracy: 61.3 -> 61.7Improved
share projector and predictor in addition (separate backbones) (ablation)BraVe · HMDB51 linear (weight-sharing ablation, plain RGB broad)top-1 accuracy: 61.7 -> 63.2Improved
share the predictor on top of shared backbone and projector (ablation)BraVe · HMDB51 linear (weight-sharing ablation, plain RGB broad)top-1 accuracy: 63.7 -> 62.7Hurt
sync audio broad view at the start of the narrow view instead of async (ablation)BraVe audio · HMDB51 linear (AudioSet audio-broad ablation)top-1 accuracy: 67.4 -> 68.2Improved
extend audio broad view from 1.3s to 5s (ablation)BraVe audio · UCF101 linear (AudioSet)top-1 accuracy: 92.3 -> 92.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy