DC Field | Value | Language |
---|---|---|
dc.contributor.author | Senocak, Arda | ko |
dc.contributor.author | Ryu, Hyeonggon | ko |
dc.contributor.author | Kim, Junsik | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2022-11-17T07:00:24Z | - |
dc.date.available | 2022-11-17T07:00:24Z | - |
dc.date.created | 2022-09-27 | - |
dc.date.created | 2022-09-27 | - |
dc.date.issued | 2022-05 | - |
dc.identifier.citation | 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022, pp.4863 - 4867 | - |
dc.identifier.issn | 1520-6149 | - |
dc.identifier.uri | http://hdl.handle.net/10203/299804 | - |
dc.description.abstract | The objective of this work is to localize the sound sources in visual scenes. Existing audio-visual works employ contrastive learning by assigning corresponding audio-visual pairs from the same source as positives while randomly mismatched pairs as negatives. However, these negative pairs may contain semantically matched audio-visual information. Thus, these semantically correlated pairs, “hard positives”, are mistakenly grouped as negatives. Our key contribution is showing that hard positives can give similar response maps to the corresponding pairs. Our approach incorporates these hard positives by adding their response maps into a contrastive learning objective directly. We demonstrate the effectiveness of our approach on VGG-SS and SoundNet-Flickr test sets, showing favorable performance to the state-of-the-art methods. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | LEARNING SOUND LOCALIZATION BETTER FROM SEMANTICALLY SIMILAR SAMPLES | - |
dc.type | Conference | - |
dc.identifier.wosid | 000864187905031 | - |
dc.identifier.scopusid | 2-s2.0-85127066533 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 4863 | - |
dc.citation.endingpage | 4867 | - |
dc.citation.publicationname | 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Virtual, Online | - |
dc.identifier.doi | 10.1109/ICASSP43922.2022.9747867 | - |
dc.contributor.localauthor | Kweon, In-So | - |
dc.contributor.nonIdAuthor | Ryu, Hyeonggon | - |
dc.contributor.nonIdAuthor | Kim, Junsik | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.