Introduces the LDD task, ListenForge dataset built from five listening head generation methods, and MANet model that detects listening forgeries via motion inconsistencies guided by audio semantics.
In Proceedings of the 28th ACM international conference on multimedia
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
EAD-Net uses a diffusion model with new spatio-temporal attention, graph-based temporal reasoning, and LLM-derived semantic descriptions to generate emotionally expressive talking head videos with improved lip-sync and coherence over prior methods.
Pixel-level protective perturbations for portrait privacy are ineffective against common image transformations, and a low-cost purification framework can strip them out.
citing papers explorer
-
Listening Deepfake Detection: A New Perspective Beyond Speaking-Centric Forgery Analysis
Introduces the LDD task, ListenForge dataset built from five listening head generation methods, and MANet model that detects listening forgeries via motion inconsistencies guided by audio semantics.
-
EAD-Net: Emotion-Aware Talking Head Generation with Spatial Refinement and Temporal Coherence
EAD-Net uses a diffusion model with new spatio-temporal attention, graph-based temporal reasoning, and LLM-derived semantic descriptions to generate emotionally expressive talking head videos with improved lip-sync and coherence over prior methods.
-
Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?
Pixel-level protective perturbations for portrait privacy are ineffective against common image transformations, and a low-cost purification framework can strip them out.