English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Can conversational videos captured from multiple egocentric viewpoints revealthe map of a scene in a cost-efficient way? We seek to answer this question byproposing a new problem: efficiently building the map of a previously unseen 3Denvironment by exploiting shared information in the egocentric audio-visualobservations of participants in a natural conversation. Our hypothesis is thatas multiple people ("egos") move in a scene and talk among themselves, theyreceive rich audio-visual cues that can help uncover the unseen areas of thescene. Given the high cost of continuously processing egocentric visualstreams, we further explore how to actively coordinate the sampling of visualinformation, so as to minimize redundancy and reduce power use. To that end, wepresent an audio-visual deep reinforcement learning approach that works withour shared scene mapper to selectively turn on the camera to efficiently chartout the space. We evaluate the approach using a state-of-the-art audio-visualsimulator for 3D scenes as well as real-world video. Our model outperformsprevious state-of-the-art mapping methods, and achieves an excellentcost-accuracy tradeoff. Project: http://vision.cs.utexas.edu/projects/chat2map.

Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations