5 papers
Beyond Generative Decoding: Discriminative Hidden-State Readout from a Native Omni-Modal LLM for Multimodal Sentiment Analysis
Bin Wen, Tien-Ping Tan
Multimodal sentiment analysis (MSA) infers human affect from language, acoustic, and visual signals. Recent methods increasingly adapt large multimodal models (LMMs) via generative…
Chatting with Images for Introspective Visual Thinking
Junfei Wu, Jian Guan, Qiang Liu +4
Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual informat…
PGF-Net: A Progressive Gated-Fusion Framework for Efficient Multimodal Sentiment Analysis
Bin Wen, Tien-Ping Tan
We introduce PGF-Net (Progressive Gated-Fusion Network), a novel deep learning framework designed for efficient and interpretable multimodal sentiment analysis. Our framework incor…
EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
Bin Wen, Tien-Ping Tan
We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable con…
ESNERA: Empirical and semantic named entity alignment for named entity dataset merging
Xiaobo Zhang, Congqing He, Ying He +3
Named Entity Recognition (NER) is a fundamental task in natural language processing. It remains a research hotspot due to its wide applicability across domains. Although recent adv…