Weibo Zhang — accepted AI-conference papers

2022

AMOA: Global Acoustic Feature Enhanced Modal-Order-Aware Network for Multimodal Sentiment Analysis

Ziming Li, Yan Zhou, Weibo Zhang, Yaxin Liu, Chuanpeng Yang, Zheng Lian +1

COLING 2022main

In recent years, multimodal sentiment analysis (MSA) has attracted more and more interest, which aims to predict the sentiment polarity expressed in a video. Existing methods typically 1) treat three modal features (textual, acoustic, visual) equally, without distinguishing the importance of differe…

Cited by 25 Source ↗PDF ↗Scholar ↗

2022

Cross-Layer Aggregation with Transformers for Multi-Label Image Classification

Weibo Zhang, Fuqing Zhu, Jizhong Han, Tao Guo, Songlin Hu

ICASSP 2022accepted

Multi-label image classification task aims to predict multiple object labels in a given image and faces the challenge of variable-sized objects. Limited by the size of CNN convolution kernels, existing CNN-based methods have difficulty capturing global dependencies and effectively fusing multiple la…

Cited by 0 Source ↗Scholar ↗