About myself

This is Yucheng Han’s Homepage and I am still improving it.

I am a senior student of Department of Automation in Tsinghua University. I am looking forward to pursuing a Ph.D. degree.

I have decided to join MReal Lab at Nanyang Technological University.

Any researcher is welcomed to contact me and I am eager to communicate with you. By now I can be contacted using email 758370661@qq.com or yuchenghan.listen2you@gmail.com.

Research experiences

CCVL Lab

Fast AdvProp
Advised by Professor Cihang Xie and Professor Alan Yuille.

• AdvProp reimplemented using PyTorch is open source.
• Still in progress

i-VisonGroup

I have finished two projects in i-VisionGroup and gotten two corresponding papers.

Hierarchical Graph with Relation Reduction for Video Summarization
Advised by Professor Jiwen Lu

• Designed a new video summarization method to extract the spatial-temporal representations by building a
  hierarchical graph and applying graph convolution and our proposed pooling module.
• Exceeded previous state-of-the-art method by 2.1% on SumMe dataset and 1.6% on TVSum dataset.
• Submitted to IEEE Transactions on Image Processing (TIP).

Learning Multiscale Hierarchical Attention for Video Summarization
Advised by Professor Jiwen Lu

• Designed a hierarchical attention model for video summarization extracting the multiscale features.
• Benchmarked the proposed attention model on the task of video summarization (as well as a variant of the
  attention model that was combined with optical flow) and improved the performance on SumMe and TVSum by
  1.4% (1.7%) and 0.4% (0.9%), respectively.
• Submitted to Pattern Recognition (PR).