Search Results for author: Zhifan Feng

Found 7 papers, 0 papers with code

Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering

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.

Question Answering Video Question Answering +1

Improving Video Retrieval by Adaptive Margin

no code implementations9 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.

Retrieval Video Retrieval

CLOP: Video-and-Language Pre-Training with Knowledge Regularizations

no code implementations7 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.

Contrastive Learning Retrieval +1

A CLIP-Enhanced Method for Video-Language Understanding

no code implementations14 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).

Cannot find the paper you are looking for? You can Submit a new open access paper.