$C^3$ASD: Multi-level Consistency-Driven Representation Learning for Robust Active Speaker Detection
- 16 September 2026
- book chapter
- Published by Springer Nature
- p. 171-195
Abstract
No abstract availableKeywords
This publication has 28 references indexed in Scilit:
- LR-ASD: Lightweight and Robust Network for Active Speaker DetectionInternational Journal of Computer Vision, 2025
- A Light Weight Model for Active Speaker Detection2023
- End-to-End Active Speaker Detection2022
- Video Captioning Based on Both Egocentric and Exocentric Views of Robot Vision for Human-Robot InteractionInternational Journal of Social Robotics, 2021
- Turn-taking in Conversational Systems and Human-Robot Interaction: A ReviewComputer Speech & Language, 2021
- Active Speakers in Context2020
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Out of Time: Automated Lip Sync in the Wild2017
- Cross-Modal Supervision for Learning Active Speaker Detection in Video2016
- Microsoft COCO: Common Objects in Context2014