17 papers
Visual Token Compression Enhances Robustness of MLLMs
Shishen Gu, Jiequan Cui, Wenbo Hu +3
In this paper, we show for the first time that visual token pruning enhances the robustness of Multimodal Large Language Models (MLLMs), mitigating vulnerabilities such as jailbrea…
Missing-Token Prompted Reliability-Aware Fusion for Robust Polyglot Speaker Identification
Peng Jia, Li Dai, Jia Li +3
Accurate and robust multimodal speaker identification is essential for multimedia understanding and biometric authentication. However, real-world polyglot scenarios pose two key ch…
Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment
Jia Li, Qian Chen, Wei Wang +5
Personality assessment aims to infer stable personality traits from dynamic behaviors across language, voice, and facial cues. Since different personality dimensions are revealed t…
SDTalk: Structured Facial Priors and Dual-Branch Motion Fields for Generalizable Gaussian Talking Head Synthesis
Peng Jia, Zhen Xiao, Jia Li +3
High-quality, real-time talking head synthesis remains a fundamental challenge in computer vision. Existing reconstruction- and rendering-based methods typically rely on identity-s…
To Fuse or to Drop? Dual-Path Learning for Resolving Modality Conflicts in Multimodal Emotion Recognition
Yangchen Yu, Qian Chen, Jia Li +5
Multimodal emotion recognition (MER) benefits from combining text, audio, and vision, yet standard fusion often fails when modalities conflict. Crucially, conflicts differ in resol…
Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets
Jia Li, Yu Zhang, Yin Chen +5
Facial action unit (AU) detection and facial expression (FE) recognition can be jointly viewed as affective facial behavior tasks, representing fine-grained muscular activations an…