AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

See, Hear, Explore: Curiosity via Audio-Visual Association

Victoria Dean, Shubham Tulsiani, Abhinav Gupta

NeurIPS 2020 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual source localization · 24 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 audio-visual association novelty as intrinsic reward instead of visual future-prediction errorexploration policy on Atari · Atari (12 games)games outperforming future prediction curiosity: 8 of 12Improved
use audio-visual association novelty as intrinsic reward instead of disagreementexploration policy on Atari · Atari (12 games)games outperforming disagreement: 9 of 12Improved
use audio-visual association novelty for explorationexploration policy in Habitat, Apartment 0 · Habitat, Apartment 0time to full state coverage: 3 times fasterImproved
use audio-visual association novelty for explorationexploration policy in Habitat, Apartment 0 · Habitat, Apartment 0visits to rare states: about 8 times more frequentlyImproved
combine SHE and future-prediction intrinsic rewards (ablation)Atari exploration policy · Atari (12 games)games outperforming future prediction curiosity: 10 of 12Improved
combine SHE and future-prediction intrinsic rewards (ablation)Atari exploration policy · Alienaverage final reward: 359 -> 593Improved
add audio-visual inputs to the future-prediction baseline (ablation)future prediction curiosity · Atariextrinsic rewardNo clear effect
add audio-visual inputs to the RND baseline (ablation)RND · Gravitarextrinsic rewardNo clear effect
use audio-visual association rather than future prediction (ablation)curiosity-driven exploration under noisy audio and visual inputs · Asterix, SpaceInvaders, and MsPacmanextrinsic reward under noiseMixed
use audio-visual association curiosity in sticky-action Atari environments (ablation)SHE · Atari sticky-action environmentsexploration performanceNo clear effect

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