AI Paper Atlas

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

Multi-Target Embodied Question Answering

Licheng Yu, Xinlei Chen, Georgia Gkioxari, Mohit Bansal, Tamara L. Berg, Dhruv Batra

CVPR 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 90 citations (OpenAlex)

Check 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
fine-tune the navigator with RL (ablation)Nav+Ctrl+cVQA · MT-EQA testoverall EQA accuracy (%): 54.44 -> 61.45Improved
add the controller (ablation)Nav(RL)+cVQA · MT-EQA testoverall EQA accuracy (%): 57.40 -> 61.45Improved
use compositional VQA instead of attention-based VQA (ablation)MT-EQA oracle with BestView images · MT-EQA oracleoverall EQA accuracy (%): 60.50 -> 74.14Improved
use controller hidden-state features instead of raw CNN features (ablation)MT-EQA oracle with shortest paths and best-view positions · MT-EQA oracleoverall EQA accuracy (%): 74.14 -> 82.88Improved
select target-relevant frames with the controller instead of using the final state over the full sequence (ablation)MT-EQA oracle with shortest paths · MT-EQA oracleoverall EQA accuracy (%): 52.36 -> 69.77Improved
use predicted SELECT moments rather than oracle moments (ablation)Controller + cVQA · MT-EQA oracleoverall EQA accuracy (%): 82.88 -> 69.77Hurt
use learned navigation instead of oracle shortest paths and best-view images (ablation)Controller + cVQA · MT-EQAoverall EQA accuracy (%): 82.88 -> 61.45Hurt
answer using question-only or prior-only predictions instead of exploring the environmentMT-EQA test · MT-EQA testaccuracy (%): 53.74 -> 61.45Hurt
answer questions with shorter ground-truth paths rather than longer pathsNav(RL)+Ctrl+cVQA · MT-EQA test, easy vs hardEQA accuracy (%): 72.22% over 54.92%Improved

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