no code implementations • NAACL 2022 • Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu, Yong Zhu
Then, it performs multistep reasoning for better answer decision between the representations of the question and the video, and dynamically integrate the reasoning results.
no code implementations • 9 Mar 2023 • Feng He, Qi Wang, Zhifan Feng, Wenbin Jiang, Yajuan Lv, Yong Zhu, Xiao Tan
While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue.
no code implementations • 7 Nov 2022 • Guohao Li, Hu Yang, Feng He, Zhifan Feng, Yajuan Lyu, Hua Wu, Haifeng Wang
To this end, we propose a Cross-modaL knOwledge-enhanced Pre-training (CLOP) method with Knowledge Regularizations.
no code implementations • 28 Oct 2022 • Wei Li, Xue Xu, Xinyan Xiao, Jiachen Liu, Hu Yang, Guohao Li, Zhanpeng Wang, Zhifan Feng, Qiaoqiao She, Yajuan Lyu, Hua Wu
Diffusion generative models have recently greatly improved the power of text-conditioned image generation.
no code implementations • 14 Oct 2021 • Guohao Li, Feng He, Zhifan Feng
This technical report summarizes our method for the Video-And-Language Understanding Evaluation (VALUE) challenge (https://value-benchmark. github. io/challenge\_2021. html).
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Zhifan Feng, Qi Wang, Wenbin Jiang, Yajuan Lyu, Yong Zhu
Named entity disambiguation is an important task that plays the role of bridge between text and knowledge.
no code implementations • 9 Mar 2020 • Xianpei Han, Zhichun Wang, Jiangtao Zhang, Qinghua Wen, Wenqi Li, Buzhou Tang, Qi. Wang, Zhifan Feng, Yang Zhang, Yajuan Lu, Haitao Wang, Wenliang Chen, Hao Shao, Yubo Chen, Kang Liu, Jun Zhao, Taifeng Wang, Kezun Zhang, Meng Wang, Yinlin Jiang, Guilin Qi, Lei Zou, Sen Hu, Minhao Zhang, Yinnian Lin
Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks.