SOTAVerified

Active Speaker Detection

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 63 papers

TitleStatusHype
Audio-video fusion strategies for active speaker detection in meetings—0
Audio-visual child-adult speaker classification in dyadic interactions—0
Audio-Visual Talker Localization in Video for Spatial Sound Reproduction—0
Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection—0
Cross-modal Supervision for Learning Active Speaker Detection in Video—0
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function—0
Detection and Analysis of Content Creator Collaborations in YouTube Videos using Face- and Speaker-Recognition—0
Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization—0
End-To-End Audiovisual Feature Fusion for Active Speaker Detection—0
Enhancing Real-World Active Speaker Detection with Multi-Modal Extraction Pre-Training—0
FaVoA: Face-Voice Association Favours Ambiguous Speaker Detection—0
How to Squeeze An Explanation Out of Your Model—0
ICTCAS-UCAS-TAL Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2021—0
Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization—0
Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos—0
Learning Spatial-Temporal Graphs for Active Speaker Detection—0
Data standardization for robust lip sync—0
Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection—0
Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion—0
Robust Active Speaker Detection in Noisy Environments—0
Self-Supervised Vision-Based Detection of the Active Speaker as Support for Socially-Aware Language Acquisition—0
Spot the conversation: speaker diarisation in the wild—0
Understanding Co-speech Gestures in-the-wild—0
UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022—0
UniCon: Unified Context Network for Robust Active Speaker Detection—0
Show:102550
← PrevPage 2 of 3Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GestSyncAccuracy87—Unverified