AI Paper Atlas

Research map / Video / Action recognition

AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition

Yue Meng, Rameswar Panda, Chung-Ching Lin, Prasanna Sattigeri, Leonid Karlinsky, Kate Saenko, Aude Oliva, Rogerio Feris

ICLR 2021 · Video › Action recognition · approach: Disentangled action recognition · 21 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 adaptive temporal fusion to ResNet18 TSNTSN with ResNet18 · Something-Something V1Top1 accuracy: 14.8 -> 36.9Improved
Add adaptive temporal fusion to ResNet18 TSNTSN with ResNet18 · Something-Something V2Top1 accuracy: 27.3 -> 50.5Improved
Add adaptive temporal fusion to ResNet18 TSNTSN with ResNet18 · JesterTop1 accuracy: 82.6 -> 93.7Improved
Add adaptive temporal fusion to ResNet18 TSNTSN with ResNet18 · Mini-KineticsTop1 accuracy: 64.6 -> 67.5Improved
Add feature reuse to learned keep/skip policies (ablation)Ada. Skip with ResNet18 · Something-Something V1Top1 accuracy: 9.5 -> 36.9Improved
Add channel skipping to learned keep/reuse policies (ablation)Ada. Reuse with ResNet18 · Something-Something V1FLOPS: 13.8G -> 10.3GImproved
Add channel skipping to learned keep/reuse policies (ablation)Ada. Reuse with ResNet18 · Something-Something V1Top1 accuracy: 36.3 -> 36.9Improved
Replace random channel policy with an adaptive learned policy (ablation)Temporal fusion with ResNet18 · Something-Something V1Top1 accuracy: 27.5 -> 36.9Improved
Restrict adaptive fusion to the last three TSM blocks rather than all blocks (ablation)TSM with ResNet50 · Something-Something V1Top1 accuracy: 44.9 -> 46.8Improved
Increase policy hidden units from 1024 to 4096 (ablation)AdaFuse-TSM-Last · Something-Something V2Top1 accuracy: 59.40 -> 60.00Improved
Increase efficiency weight lambda from 0.050 to 0.100 (ablation)AdaFuse-TSM-Last with 1024 hidden units · Something-Something V2FLOPS: 31.53G -> 31.04GImproved
Increase efficiency weight lambda from 0.050 to 0.100 (ablation)AdaFuse-TSM-Last with 1024 hidden units · Something-Something V2Top1 accuracy: 59.71 -> 59.40Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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