AI Paper Atlas

Research map / Video / Action recognition

Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization

Chen Zhao, Shuming Liu, Karttikeya Mangalam, Bernard Ghanem

CVPR 2023 · Video › Action recognition · approach: Weakly supervised temporal action localization · 34 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
Train end to end instead of training on pre-extracted features (ablation)Re²Vswin-tiny with VSGN · ActivityNet-v1.3average mAP (%): 34.47 -> 36.38Improved
Train end to end instead of training on pre-extracted features (ablation)Re²Slowfast-101 with VSGN · ActivityNet-v1.3average mAP (%): 35.24 -> 36.82Improved
Add Kinetics-400-pretrained initialization rather than training from scratch (ablation)Re²Vswin-Base · ActivityNet-v1.3average mAP (%): 28.68 -> 35.73Improved
Use Kinetics-600 rather than Kinetics-400 pretrained initialization (ablation)Re²Vswin-Base · ActivityNet-v1.3average mAP (%): 35.73 -> 36.28Improved
Replace VSGN with ActionFormer (ablation)Re²Vswin-tiny · ActivityNet-v1.3average mAP (%): 36.38 -> 36.80Improved
Replace VSGN with ActionFormer (ablation)Re²Slowfast-101 · ActivityNet-v1.3average mAP (%): 36.82 -> 37.01Improved
Rewire the pretrained backbone and reuse its weights instead of using the original backbone (ablation)Vswin-tiny feature extraction with VSGN · ActivityNet-v1.3average mAP (%): 34.36 -> 34.47Improved
Rewire the pretrained backbone and reuse its weights instead of using the original backbone (ablation)Slowfast-101 feature extraction with VSGN · ActivityNet-v1.3average mAP (%): 35.04 -> 35.24Improved
Add spatial cropping, flipping, temporal jittering, rotation, and color jittering (ablation)Re²Vswin-tiny · ActivityNet-v1.3average mAP: 35.25 -> 36.38Improved
Add random spatial cropping and flipping (ablation)Re²Vswin-tiny · ActivityNet-v1.3average mAP: 35.25 -> 35.87Improved
Add temporal jittering to spatial cropping and flipping (ablation)Re²Vswin-tiny · ActivityNet-v1.3average mAP: 35.87 -> 35.98Improved
Add random rotation to spatial cropping and flipping (ablation)Re²Vswin-tiny · ActivityNet-v1.3average mAP: 35.87 -> 36.20Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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