Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310632057> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4310632057 abstract "Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality. The two primary sources of information to derive such a speech-face relationship are i) visual activity and its interaction with the speech signal and ii) co-occurrences of speakers' identities across modalities in the form of face and speech. The two approaches have their limitations: the audio-visual activity models get confused with other frequently occurring vocal activities, such as laughing and chewing, while the speakers' identity-based methods are limited to videos having enough disambiguating information to establish a speech-face association. Since the two approaches are independent, we investigate their complementary nature in this work. We propose a novel unsupervised framework to guide the speakers' cross-modal identity association with the audio-visual activity for active speaker detection. Through experiments on entertainment media videos from two benchmark datasets, the AVA active speaker (movies) and Visual Person Clustering Dataset (TV shows), we show that a simple late fusion of the two approaches enhances the active speaker detection performance." @default.
- W4310632057 created "2022-12-13" @default.
- W4310632057 creator A5010028928 @default.
- W4310632057 creator A5041314566 @default.
- W4310632057 date "2022-12-01" @default.
- W4310632057 modified "2023-10-16" @default.
- W4310632057 title "Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection" @default.
- W4310632057 doi "https://doi.org/10.48550/arxiv.2212.00539" @default.
- W4310632057 hasPublicationYear "2022" @default.
- W4310632057 type Work @default.
- W4310632057 citedByCount "0" @default.
- W4310632057 crossrefType "posted-content" @default.
- W4310632057 hasAuthorship W4310632057A5010028928 @default.
- W4310632057 hasAuthorship W4310632057A5041314566 @default.
- W4310632057 hasBestOaLocation W43106320571 @default.
- W4310632057 hasConcept C121332964 @default.
- W4310632057 hasConcept C13280743 @default.
- W4310632057 hasConcept C133892786 @default.
- W4310632057 hasConcept C138885662 @default.
- W4310632057 hasConcept C142853389 @default.
- W4310632057 hasConcept C144024400 @default.
- W4310632057 hasConcept C149838564 @default.
- W4310632057 hasConcept C154945302 @default.
- W4310632057 hasConcept C15744967 @default.
- W4310632057 hasConcept C185592680 @default.
- W4310632057 hasConcept C185798385 @default.
- W4310632057 hasConcept C188027245 @default.
- W4310632057 hasConcept C205649164 @default.
- W4310632057 hasConcept C24890656 @default.
- W4310632057 hasConcept C2778355321 @default.
- W4310632057 hasConcept C2779304628 @default.
- W4310632057 hasConcept C2779903281 @default.
- W4310632057 hasConcept C2780226545 @default.
- W4310632057 hasConcept C28490314 @default.
- W4310632057 hasConcept C36289849 @default.
- W4310632057 hasConcept C41008148 @default.
- W4310632057 hasConcept C41895202 @default.
- W4310632057 hasConcept C542102704 @default.
- W4310632057 hasConcept C71139939 @default.
- W4310632057 hasConcept C94124525 @default.
- W4310632057 hasConceptScore W4310632057C121332964 @default.
- W4310632057 hasConceptScore W4310632057C13280743 @default.
- W4310632057 hasConceptScore W4310632057C133892786 @default.
- W4310632057 hasConceptScore W4310632057C138885662 @default.
- W4310632057 hasConceptScore W4310632057C142853389 @default.
- W4310632057 hasConceptScore W4310632057C144024400 @default.
- W4310632057 hasConceptScore W4310632057C149838564 @default.
- W4310632057 hasConceptScore W4310632057C154945302 @default.
- W4310632057 hasConceptScore W4310632057C15744967 @default.
- W4310632057 hasConceptScore W4310632057C185592680 @default.
- W4310632057 hasConceptScore W4310632057C185798385 @default.
- W4310632057 hasConceptScore W4310632057C188027245 @default.
- W4310632057 hasConceptScore W4310632057C205649164 @default.
- W4310632057 hasConceptScore W4310632057C24890656 @default.
- W4310632057 hasConceptScore W4310632057C2778355321 @default.
- W4310632057 hasConceptScore W4310632057C2779304628 @default.
- W4310632057 hasConceptScore W4310632057C2779903281 @default.
- W4310632057 hasConceptScore W4310632057C2780226545 @default.
- W4310632057 hasConceptScore W4310632057C28490314 @default.
- W4310632057 hasConceptScore W4310632057C36289849 @default.
- W4310632057 hasConceptScore W4310632057C41008148 @default.
- W4310632057 hasConceptScore W4310632057C41895202 @default.
- W4310632057 hasConceptScore W4310632057C542102704 @default.
- W4310632057 hasConceptScore W4310632057C71139939 @default.
- W4310632057 hasConceptScore W4310632057C94124525 @default.
- W4310632057 hasLocation W43106320571 @default.
- W4310632057 hasLocation W43106320572 @default.
- W4310632057 hasOpenAccess W4310632057 @default.
- W4310632057 hasPrimaryLocation W43106320571 @default.
- W4310632057 hasRelatedWork W1521049138 @default.
- W4310632057 hasRelatedWork W2096647984 @default.
- W4310632057 hasRelatedWork W2162158162 @default.
- W4310632057 hasRelatedWork W2949074159 @default.
- W4310632057 hasRelatedWork W2952745240 @default.
- W4310632057 hasRelatedWork W3176765321 @default.
- W4310632057 hasRelatedWork W3198037411 @default.
- W4310632057 hasRelatedWork W4298715519 @default.
- W4310632057 hasRelatedWork W4301143707 @default.
- W4310632057 hasRelatedWork W4386721968 @default.
- W4310632057 isParatext "false" @default.
- W4310632057 isRetracted "false" @default.
- W4310632057 workType "article" @default.