AI Paper Atlas

Research map / Video / Video segmentation and tracking

Space-Time Crop & Attend: Improving Cross-Modal Video Representation Learning

Mandela Patrick, Po-Yao Huang, Ishan Misra, Florian Metze, Andrea Vedaldi, Yuki M. Asano, João F. Henriques

ICCV 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 28 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
replace two RGB crops with feature crops (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 58.6 -> 60.4Improved
add feature crops in space (ablation)avg-pooled baseline · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 54.0 -> 59.9Improved
add more feature crops in space and time (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 59.9 -> 60.4Improved
add temporal feature crops (2x3 + 1x2 sizes only, fewer spatial) (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 59.9 -> 58.4Hurt
use transformer pooling in both pretraining and finetuning (ablation)avg pooling · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 54.0 -> 60.3Improved
transformer pooling only at finetuning (ablation)avg-pooled pretraining · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 54.0 -> 54.6No clear effect
transformer pooling only at pretraining (ablation)avg-pooled finetuning · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 54.0 -> 52.1Hurt
increase transformer layers from 2 to 4 (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 60.3 -> 58.3Hurt
add 2-layer transformer versus parameter-matched model (ablation)R(2+1)D-18 · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 57.3 -> 60.3Improved
add transformer pooling to space+time feature crops (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 60.4 -> 62.0Improved
add cross-modal loss to within-modal baseline (ablation)SimCLR-style video · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 43.3 -> 54.0Improved
add within-modal loss to cross-modal loss (ablation)STiCA · HMDB-51 fold 1 (ablation, 100 epochs, 30 frames)top-1 accuracy (%): 54.0 -> 58.6Improved

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