4 papers
Towards Fine-Grained and Verifiable Concept Bottleneck Models
Yingying Fang, Haijie Xu, Shuang Wu +2
Concept Bottleneck Models (CBMs) offer interpretable alternatives to black-box predictors by introducing human-relatable concepts before the final output. However, existing CBMs st…
Sync-TVA: A Graph-Attention Framework for Multimodal Emotion Recognition with Cross-Modal Fusion
Zeyu Deng, Yanhui Lu, Jiashu Liao +2
Multimodal emotion recognition (MER) is crucial for enabling emotionally intelligent systems that perceive and respond to human emotions. However, existing methods suffer from limi…
DiffExplainer: Unveiling Black Box Models Via Counterfactual Generation
Yingying Fang, Shuang Wu, Zihao Jin +4
In the field of medical imaging, particularly in tasks related to early disease detection and prognosis, understanding the reasoning behind AI model predictions is imperative for a…
Dynamic Multimodal Information Bottleneck for Multimodality Classification
Yingying Fang, Shuang Wu, Sheng Zhang +5
Effectively leveraging multimodal data such as various images, laboratory tests and clinical information is gaining traction in a variety of AI-based medical diagnosis and prognosi…