A pose-conditioned large-margin contrastive encoder isolates persistent biometric identity cues from transmitted latents in talking-head videoconferencing to flag impersonation attacks via cosine similarity without inspecting the output video.
Latent image animator: Learning to animate images via latent space navigation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
DirectAnimator bypasses pose extraction using a Driving Cue Triplet and Same2X training strategy to achieve state-of-the-art human animation quality and robustness from raw videos.
PCMECL improves speech-preserving facial expression manipulation by learning personalized prompts from individual visuals and using feature differencing to align visual and semantic changes from VLMs.
AUHead uses audio-language models to generate Action Unit sequences from speech and feeds them into a controllable diffusion model to synthesize realistic emotional talking-head videos.
citing papers explorer
-
Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing
A pose-conditioned large-margin contrastive encoder isolates persistent biometric identity cues from transmitted latents in talking-head videoconferencing to flag impersonation attacks via cosine similarity without inspecting the output video.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
Beyond Skeletons: Learning Animation Directly from Driving Videos with Same2X Training Strategy
DirectAnimator bypasses pose extraction using a Driving Cue Triplet and Same2X training strategy to achieve state-of-the-art human animation quality and robustness from raw videos.
-
Personalized Cross-Modal Emotional Correlation Learning for Speech-Preserving Facial Expression Manipulation
PCMECL improves speech-preserving facial expression manipulation by learning personalized prompts from individual visuals and using feature differencing to align visual and semantic changes from VLMs.
-
AUHead: Realistic Emotional Talking Head Generation via Action Units Control
AUHead uses audio-language models to generate Action Unit sequences from speech and feeds them into a controllable diffusion model to synthesize realistic emotional talking-head videos.