AI Paper Atlas

Research map / Video / Action recognition

LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition

Zuxuan Wu, Caiming Xiong, Yu-Gang Jiang, Larry S. Davis

NeurIPS 2019 · Video › Action recognition · approach: Contrastive video representation learning · 31 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
Use adaptive coarse-to-fine feature computation instead of uniform frame evaluationLiteEval · FCVIDGFLOPs: 195.5 -> 94.3Improved
Use adaptive coarse-to-fine feature computation instead of uniform frame evaluationLiteEval · ActivityNetmAP: 70.0% -> 72.7%Improved
Use adaptive coarse-to-fine feature computation instead of uniform frame evaluationLiteEval · ActivityNetGFLOPs: 195.5 -> 95.1Improved
Replace Gumbel-Softmax gating with REINFORCE policy learningLiteEval · FCVIDmAP: 80.0% -> 74.2%Hurt
Replace Gumbel-Softmax gating with REINFORCE policy learningLiteEval · ActivityNetGFLOPs: 95.1 -> 269.3Hurt
Add synchronization that transfers coarse LSTM information to the fine LSTM (ablation)LiteEval · FCVIDmAP: 65.7% -> 80.0%Improved
Set gamma to 0.01 rather than 0.05 (ablation)LiteEval · FCVIDmAP: 80.0% -> 78.8%Hurt
Set gamma to 0.03 rather than 0.05 (ablation)LiteEval · FCVIDmAP: 80.0% -> 79.7%Hurt
Set gamma to 0.10 rather than 0.05 (ablation)LiteEval · FCVIDGFLOPs: 94.3 -> 139.0Hurt
Use 64 cLSTM hidden units instead of 512 (ablation)LiteEval · FCVIDmAP: 80.0% -> 76.9%Hurt
Use 128 cLSTM hidden units instead of 512 (ablation)LiteEval · FCVIDmAP: 80.0% -> 77.3%Hurt
Use 256 cLSTM hidden units instead of 512 (ablation)LiteEval · FCVIDmAP: 80.0% -> 78.3%Hurt

Later papers that compared with this method

6 later accepted papers report LiteEval as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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