Jing Cai
Jing Cai has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Cunxiang Yin
Tencent Inc
3 shared publications - Yancheng He
Tencent Inc
3 shared publications - Zhongyu Wei
Fudan University, Shanghai, China
3 shared publications - Guoqiang Xu
Tencent Inc
2 shared publications - Yuncong Li
Tencent Inc
2 shared publications - Jinhua Fu
Tencent
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by China Science Publishing & Media Ltd. in Data Intelligence
Bridging the Domain Gap in Grounded Situation Recognition via Unifying Event Extraction across Modalities
Event extraction extracts event frames from text, while grounded situation recognition detectsevents in images. As real-world applications frequently encounter a multitude of unforeseenevents, certain researchers have introduced cross-domain and in-domain event extraction, whilegrounded situation recognition primarily explores in-domain scenarios. Therefore, in this paper,we propose cross-domain grounded situation recognition and establish a new benchmark SWiGXD. In this more challenging setting, we deepen the connection between the two tasks based ontheir underlying unity in two different modalities and explore how to transfer the generalizationability from text to images. Firstly, we utilize ChatGPT to automatically generate textual data,which can be divided into two categories. One category is directly matched with images, establishing a direct connection with the images. The other category encompasses all event types andpossesses greater generalization. Then we employ a uniffed model framework to establish theassociation between textual concepts and local image features and achieve cross-domain generalization transfer across modalities through modality-shared prompts and self-attention mechanism. Furthermore, we incorporate textual data with higher generalization to further assist inimproving generalization on images. The experimental results on the newly constructed benchmark demonstrate the effectiveness of our method.
- 1 January 2025
- Published by China Science Publishing & Media Ltd. in Data Intelligence
Open AccessBridging the Domain Gap in Grounded Situation Recognition via Unifying Event Extraction across Modalities
Event extraction extracts event frames from text, while grounded situation recognition detectsevents in images. As real-world applications frequently encounter a multitude of unforeseenevents, certain researchers have introduced cross-domain and in-domain event extraction, whilegrounded situation recognition primarily explores in-domain scenarios. Therefore, in this paper,we propose cross-domain grounded situation recognition and establish a new benchmark SWiGXD. In this more challenging setting, we deepen the connection between the two tasks based ontheir underlying unity in two different modalities and explore how to transfer the generalizationability from text to images. Firstly, we utilize ChatGPT to automatically generate textual data,which can be divided into two categories. One category is directly matched with images, establishing a direct connection with the images. The other category encompasses all event types andpossesses greater generalization. Then we employ a uniffed model framework to establish theassociation between textual concepts and local image features and achieve cross-domain generalization transfer across modalities through modality-shared prompts and self-attention mechanism. Furthermore, we incorporate textual data with higher generalization to further assist inimproving generalization on images. The experimental results on the newly constructed benchmark demonstrate the effectiveness of our method.
- 10 May 2022
- Published by Springer Nature
- p. 200-211
Learning Discriminative Representation Base on Attention for Uplift
- 10 May 2022
- Published by Springer Nature
- p. 200-211
Learning Discriminative Representation Base on Attention for Uplift