新闻

  • [2021.10.07更新] 实验室定向招募本科实习生若干名,详情请点击 本科生招生说明
  • 2021.10.12:谢嘉仪短视频流行度预测论文被IEEE TMM接收。
  • 2021.10.07:丁冠辰、周霖、丁丁等人团队在ICCV2021 VisDrone比赛人群计数赛道获得总分第二,单项指标分列MAE第二/MSE第一。
  • 2021.07.29:易静推荐系统论文被IEEE TMM接收。
  • 2021.07.19:程先航视频插帧论文被IEEE TPAMI接收。
  • 2021.06.11:李楠楠黑盒攻击论文被IEEE TIP接收。
  • 2021.05.11:实验室陈境远,丁冠辰,杨雨辰等人团队在CVPR2021 AICity比赛Track 4以较小分差排名百度,字节跳动之后位列第三。
  • 2021.03.19:柳费洋视频编码论文被IEEE TIP接收。
  • 2021.01.11:实验室与诺基亚贝尔实验室等单位共同制定的虚拟现实国际标准ITU-T P.919正式发布。
  • 2020.12.04:陈震中教授受邀为《遥感学报》第六届编委。
  • 2020.09.09:陈震中教授受邀为SCI一区/CCF A类期刊IEEE TIP编委(AE)(影响因子9.34)。

更多新闻 ...

最新成果

  • 202110.15
    In this paper, we propose Optical-Flow-Reuse-Based Bidirectional Recurrent Network for Space-Time Video Super-Resolution. Our proposed method could considerably reduce the computation burden of frame alignment compared with traditional LSTM-based designs. Extensive experiments demonstrate that our method is superior to the state-of-the-art methods in terms of both accuracy and efficiency. Read more...
  • 202110.15
    In this work, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the two problems of the semantic overlap between different predicates and the long-tailed data distribution. The proposed method is evaluated on Visual Genome benchmark, where the performance of the tail classes is significantly improved when built on the existing methods. Read more...
  • 20203.24
    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...