News

• [2021.07.15 Update] For Postgraduate Admissions，please click Postgraduate Admission。
• [2021.07.15 Update] For Undergraduate Internship，please click Undergraduate Internship。
• [2021.02.13 Update] For Post-Doc Positions，please click Post-Doc Recruitment。
• 2021.07.29：J. Yi's paper on recommendation system was accepted to IEEE TMM.
• 2021.07.19：X. Cheng's paper on video frame interpolation was accepted to IEEE TPAMI.
• 2021.06.11：N. Li's paper on blackbox attack was accepted to IEEE TIP.
• 2021.05.11：Our team won 3rd place in CVPR2021 AICity Track 4.
• 2021.03.19：F. Liu's paper on video coding was accepted to IEEE TIP.
• 2021.01.11：Joint work with Bell Labs et al. has been published as ITU-T P.919.
• 2020.09.09：Prof. Chen has become Associate Editor of IEEE TIP.

More news ...

Recent Achievements

• 20207.22
  Black Box Attack
  By Nannan Li
  Link: arxiv.org/abs/2007.10593
  In this work, we propose a novel black-box attack approach that can directly minimize the induced distortion by learning the noise distribution of the adversarial example, assuming only loss-oracle access to the black-box network. Our attack results in low distortion as validated on ImageNet. Read more...
• 20206.15
  Video Frame Interpolation
  By Xianhang Cheng
  Link: arxiv.org/abs/2006.08070
  In this paper, we propose an enhanced deformable separable convolution (EDSC) based network to obtain information from non-local neighborhood than is capable to produce multiple in-between frames. Experimental results show that our method performs favorably against the state-of-the-art methods. Read more...
• 20205.27
  6DoF Saliency
  By Xiaoyin Ding
  Link: arxiv.org/abs/2005.13127
  In this work, a novel 6DoF mesh saliency database is developed. We also propose a 6DoF mesh saliency detection algorithm together with an evaluation metric for 6DoF experiments accordingly. Moreover, some state-of-the-art saliency detection methods have been extended as benchmarks. Read more...
• 20203.28
  Micro-video Popularity
  By Yaochen Zhu / 谢嘉仪
  Link: arxiv.org/abs/2003.12724
  In this paper, we propose a multimodal variational encoder-decoder (MMVED) framework for micro-video popularity prediction tasks. MMVED learns a stochastic Gaussian embedding of a micro-video that is informative to its popularity level while preserves the inherent uncertainties simultaneously. Read more...
• 20203.24
  Refined AIRL
  By Nannan Li
  Link: arxiv.org/abs/2003.10925
  In this paper, we propose a refined Adversarial Inverse Reinforcement Learning (rAIRL) method to handle the reward ambiguity problem by disentangling reward for each word in a sentence, as well as achieve stable adversarial training by refining the loss function to shift the generator towards Nash equilibrium. Read more...