← Search

Guanghao Yin

2 accepted papers

2023

Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis

EMNLP 2023long main

Though Multimodal Sentiment Analysis (MSA) proves effective by utilizing rich information from multiple sources (*e.g.,* language, video, and audio), the potential sentiment-irrelevant and conflicting information across modalities may hinder the performance from being further improved. To alleviate…

Cited by 0SourcecodeScholar
2022

Content-Variant Reference Image Quality Assessment via Knowledge Distillation

AAAI 2022technical

Generally, humans are more skilled at perceiving differences between high-quality (HQ) and low-quality (LQ) images than directly judging the quality of a single LQ image. This situation also applies to image quality assessment (IQA). Although recent no-reference (NR-IQA) methods have made great prog…