AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities

Baoxiong Jia, Yixin Chen, Siyuan Huang, Yixin Zhu, Song-Chun Zhu

ECCV 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Collaborative multi-agent perception

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
predict verbs and nouns separately (branching) instead of compositional action directlySlowFast · LEMMA FPV recognitioncompositional action Avg.F1: 27.3 -> 35.58Improved
predict verbs and nouns separately (branching) instead of compositional action directlyI3D · LEMMA FPV recognitioncompositional action Avg.F1: 17.30 -> 30.53Improved
use sequential inference instead of branching (ablation)SlowFast · LEMMA FPV recognitioncompositional action Avg.F1: 35.58 -> 31.57Hurt
predict verbs and nouns separately instead of compositional action directlySlowFast · LEMMA TPV recognitioncompositional action Avg.F1: 16.31 -> 10.01Hurt
predict verbs and nouns separately (branching) instead of directlyI3D · LEMMA TPV recognitioncompositional action Avg.F1: 10.64 -> 7.6No clear effect
use FPV view instead of TPV viewSlowFast · LEMMA recognitioncompositional action Avg.F1: 16.31 -> 27.3Improved
add long-term feature bank temporal context to segment features (ablation)SlowFast · LEMMA action anticipation 1x1compositional action Avg.F1: 22.82 -> 25.54Improved
add primary TPV features to LFB (ablation)LFB · LEMMA task anticipation 1x1task Avg.F1: 68.42 -> 69.54Improved
add primary TPV features to LFB (ablation)LFB · LEMMA action anticipation 1x1compositional action Avg.F1: 25.54 -> 29.01Improved
add other agent's TPV-fused features to LFB (ablation)LFB · LEMMA task anticipation 2x1task Avg.F1: 44.56 -> 51.23Improved
add other agent's TPV-fused features to LFB (ablation)LFB · LEMMA task anticipation 2x2task Avg.F1: 55.19 -> 56.67Improved
add other agent's FPV features to SF (ablation)SF · LEMMA task anticipation 2x1task Avg.F1: 46.49 -> 48.08Improved

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