Ji Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ji Wang has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Liqiang Nie
Harbin Institute of Technology (Shenzhen), Shenzhen, China
1 shared publication - Peiguang Jing
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
1 shared publication - Xianyi Liu
Tianjin University, Tianjin, China
1 shared publication - Yinwei Wei
Shandong University
1 shared publication - Yuting Su
Tianjin University, Tianjin, China
1 shared publication
Latest Publications
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 853-861
StyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning
Emotion distribution learning has gained increasing attention with the tendency to express emotions through images. As for emotion ambiguity arising from humans' subjectivity, substantial previous methods generally focused on learning appropriate representations from the holistic or significant part of images. However, they rarely consider establishing connections with the stylistic information although it can lead to a better understanding of images. In this paper, we propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL, which interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. Specifically, we consider exploring the intra- and inter-layer correlations among GRAM-based stylistic representations, and meanwhile exploit an adversary-constrained high-order attention mechanism to capture potential interactions between subtle visual parts. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations to benefit the final emotion distribution learning. Extensive experiments conducted on several benchmark datasets demonstrate the effectiveness of our proposed StyleEDL compared to state-of-the-art methods. The implementation is released at: https://github.com/liuxianyi/StyleEDL.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 853-861
Open AccessStyleEDL: Style-Guided High-order Attention Network for Image Emotion Distribution Learning
Emotion distribution learning has gained increasing attention with the tendency to express emotions through images. As for emotion ambiguity arising from humans' subjectivity, substantial previous methods generally focused on learning appropriate representations from the holistic or significant part of images. However, they rarely consider establishing connections with the stylistic information although it can lead to a better understanding of images. In this paper, we propose a style-guided high-order attention network for image emotion distribution learning termed StyleEDL, which interactively learns stylistic-aware representations of images by exploring the hierarchical stylistic information of visual contents. Specifically, we consider exploring the intra- and inter-layer correlations among GRAM-based stylistic representations, and meanwhile exploit an adversary-constrained high-order attention mechanism to capture potential interactions between subtle visual parts. In addition, we introduce a stylistic graph convolutional network to dynamically generate the content-dependent emotion representations to benefit the final emotion distribution learning. Extensive experiments conducted on several benchmark datasets demonstrate the effectiveness of our proposed StyleEDL compared to state-of-the-art methods. The implementation is released at: https://github.com/liuxianyi/StyleEDL.