AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition

Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Shilei Wen

ICCV 2019 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Offline and networked MARL · 144 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
replace uniform 25-frame sampling with MARL samplingResNet-152 · ActivityNet v1.3 val (ResNet-152)mAP: 82.08 -> 83.81Improved
replace uniform sampling with MARL samplingResNet-152 · ActivityNet v1.2 val (ResNet-152)mAP: 83.71 -> 85.70Improved
replace uniform sampling with MARL sampling on C3DC3D · ActivityNet v1.3 val (C3D)mAP: 60.68 -> 62.00Improved
add context-aware observation (M=1 vs M=0) (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 82.99 -> 83.81Improved
increase context range from M=1 to M=4 (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 83.81 -> 83.72No clear effect
increase number of agents at test from 5 to 25 (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 80.19 -> 83.81Improved
increase test agents from 25 to 120 (all frames) (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 83.81 -> 83.72No clear effect
train with video-level labels only instead of instance-level (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 83.81 -> 82.98Hurt
transfer policy network trained on YouTube Birds to ActivityNet v1.3 (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 83.81 -> 82.70Mixed
transfer policy trained for ResNet-101 to ResNet-152 classifier (ablation)MARL (ResNet-152) · ActivityNet v1.3 val (ResNet-152)mAP: 83.81 -> 83.43Mixed
add MARL sampling to Inception-V3 on YouTube Birds vs RRARRA · YouTube Birdstop-1 accuracy: 73.205 -> 79.01Improved
add MARL sampling vs uniform sampling on YouTube CarsInception-V3 · YouTube Carstop-1 accuracy: 76.49 -> 79.77Improved

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