no code implementations • 26 Oct 2021 • Tianran Wu, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima, Haruo Takemura
Video question answering (VideoQA) is designed to answer a given question based on a relevant video clip.
no code implementations • 18 Sep 2020 • Jiaqi Lv, Tianran Wu, Chenglun Peng, Yun-Peng Liu, Ning Xu, Xin Geng
In this paper, we present a compact learning (CL) framework to embed the features and labels simultaneously and with mutual guidance.