AI Paper Atlas

Research map / Video / Action recognition

Learning Video Representations by Transforming Time

Simon Jenni, Givi Meishvili, Paolo Favaro

ECCV 2020 · Video › Action recognition · approach: Contrastive video representation learning

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 speed-type classification loss (ablation)Speed+Random+Periodic+Warp · UCF101 (conv frozen, UCF101 pre-training)accuracy: 54.2 -> 60.6Improved
add speed-type classification loss (ablation)Speed+Random · UCF101 (conv frozen, UCF101 pre-training)accuracy: 44.5 -> 55.1Improved
add speed-type classification loss (ablation)Speed+Periodic · UCF101 (conv frozen, UCF101 pre-training)accuracy: 40.6 -> 56.5Improved
add speed-type classification loss (ablation)Speed+Random+Warp · HMDB51 (fine-tuned, UCF101 pre-training)accuracy: 36.6 -> 39.2Improved
add Warp transformation (ablation)Speed+Random with speed loss · UCF101 (conv frozen, UCF101 pre-training)accuracy: 55.1 -> 60.4Improved
add Random transformation (ablation)Speed+Periodic+Warp with speed loss · UCF101 (conv frozen, UCF101 pre-training)accuracy: 59.5 -> 60.6Improved
add Random transformation (ablation)Speed+Periodic+Warp with speed loss · HMDB51 (fine-tuned, UCF101 pre-training)accuracy: 39.0 -> 38.0Hurt
add Periodic transformation (ablation)Speed+Random+Warp with speed loss · HMDB51 (fine-tuned, UCF101 pre-training)accuracy: 39.2 -> 38.0Hurt
use all four transformations instead of speed only (ablation)speed-type classification · UCF101 (conv frozen, UCF101 pre-training)accuracy: 49.3 -> 60.6Improved
pre-train on Kinetics instead of UCF101 (ablation)3D-ResNet18 transfer · UCF101accuracy: 77.3 -> 79.3Improved
pre-train on Kinetics instead of UCF101 (ablation)C3D transfer · UCF101accuracy: 68.3 -> 69.9Improved
replace supervised pre-training with temporal transformation pre-trainingC3D · HMDB51 (fine-tuned, UCF101 pre-training)accuracy: 28.8 -> 38.0Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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