13 papers
EviDep: Trustworthy Multimodal Depression Estimation via Disentangled Evidential Learning
Fangyuan Liu, Sirui Zhao, Zeyu Zhang +6
Automated multimodal depression estimation in unconstrained environments is inherently challenged by naturalistic noise and complex behavioral variability. Prevailing deterministic…
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Yubo Huang, Hailong Guo, Fangtai Wu +9
Audio-driven avatar interaction demands real-time, streaming, and infinite-length generation -- capabilities fundamentally at odds with the sequential denoising and long-horizon dr…
Tango: Taming Visual Signals for Efficient Video Large Language Models
Shukang Yin, Sirui Zhao, Hanchao Wang +4
Token pruning has emerged as a mainstream approach for developing efficient Video Large Language Models (Video LLMs). This work revisits and advances the two predominant token-prun…
ActFER: Agentic Facial Expression Recognition via Active Tool-Augmented Visual Reasoning
Shifeng Liu, Zhengye Zhang, Sirui Zhao +7
Recent advances in Multimodal Large Language Models (MLLMs) have created new opportunities for facial expression recognition (FER), moving it beyond pure label prediction toward re…
DMP-TTS: Disentangled multi-modal Prompting for Controllable Text-to-Speech with Chained Guidance
Kang Yin, Chunyu Qiang, Sirui Zhao +6
Controllable text-to-speech (TTS) systems face significant challenges in achieving independent manipulation of speaker timbre and speaking style, often suffering from entanglement…
MELLM: A Flow-Guided Large Language Model for Micro-Expression Understanding
Sirui Zhao, Zhengye Zhang, Shifeng Liu +5
Micro-expressions (MEs), brief and low-intensity facial movements revealing concealed emotions, are crucial for affective computing. Despite notable progress in ME recognition, exi…