AI Paper Atlas

Research map / Video / Action recognition

Spatio-Temporal Crop Aggregation for Video Representation Learning

Sepehr Sameni, Simon Jenni, Paolo Favaro

ICCV 2023 · Video › Action recognition · approach: Contrastive video representation learning · 2 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
add SCALE aggregation of clip features on top of frozen backbone (linear probe)SVT backbone · SSv2top-1 accuracy: 20.30 -> 25.26Improved
add SCALE aggregation (linear probe) on Kinetics-400SVT, rhoBYOL, VMAE · Kinetics-400top-1 accuracy: 71.71 -> 71.78 (SVT)No clear effect
initialize transformer head with SCALE pretraining instead of random initSCALE_ft · Kinetics-400 (SVT)top-1 accuracy: 72.18 -> 72.38Improved
SCALE k-NN probing on MAE-based VMAE-BVMAE-B · UCF-101k-NN accuracy: 35.05 -> 65.63Improved
SCALE k-NN probing on rhoBYOLrhoBYOL · UCF-101k-NN accuracy: 85.19 -> 83.47Hurt
SCALE_ft in low-shot 10% Kinetics-400SCALE_ft · Kinetics-400 10%top-1 accuracy: 66.43 -> 67.01 (SVT linear vs SCALE_ft)Improved
add SCALE to long-form video (LVU Relation, SVT)SVT · LVU Relationaccuracy: 64.70 -> 76.47Improved
use both SET and MCM losses instead of one (ablation)SCALE_ft · UCF-101 (SVT)accuracy: 91.80 -> 93.20Improved
masking ratio 0.25 versus 0.45 (ablation)SCALE_ft · HMDB-51 (SVT)accuracy: 63.39 -> 65.49Improved
use 2 transformer layers instead of 1 (ablation)SCALE_ft · HMDB-51 (rhoBYOL)accuracy: 64.39 -> 65.62Improved
increase views per set from 4 to 8 (ablation)SCALE_ft · UCF-101 (SVT, batch 512)accuracy: 92.67 -> 93.20Improved
increase batch size from 512 to 1024 (ablation)SCALE_ft · UCF-101 (SVT, 6x2 views)accuracy: 93.18 -> 92.96Hurt

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