no code implementations • TMM 2022 • Bin Wang, Chunsheng Liu, Faliang Chang, Wenqian Wang and Nanjun Li
Action recognition in video understanding is a challenging task, largely because of the complexity and difficulty in temporal modeling, making it suffer from motion information loss and misalignment of temporal attention in spatial dimensions.
Ranked #28 on Action Recognition on Something-Something V1
no code implementations • 20 Dec 2020 • Xiao Zhang, Chunsheng Liu, Faliang Chang
In this paper, we present a novel architecture which introduces a guidance module to encourage the encoder-decoder model to generate words related to the past and future words in a caption.
no code implementations • 9 Jul 2019 • Chunsheng Liu, Hong Shan, Chunlei Chen
In particular, it can be proved that p-TNN is a better approximation of the tensor average rank than the tensor nuclear norm when p < 1.
no code implementations • 8 Apr 2019 • Chunsheng Liu
Many practical problems involve the recovery of a binary matrix from partial information, which makes the binary matrix completion (BMC) technique received increasing attention in machine learning.