Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Unsupervised Flow Refinement near Motion Boundaries


Aug 03, 2022
Shuzhi Yu, Hannah Halin Kim, Shuai Yuan, Carlo Tomasi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Cross-Attention Transformer for Video Interpolation


Jul 08, 2022
Hannah Halin Kim, Shuzhi Yu, Shuai Yuan, Carlo Tomasi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TDT: Teaching Detectors to Track without Fully Annotated Videos


May 11, 2022
Shuzhi Yu, Guanhang Wu, Chunhui Gu, Mohammed E. Fathy

* Workshop on Learning with Limited Labelled Data for Image and Video Understanding (L3D-IVU), CVPR2022 Workshop 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Optical Flow Training under Limited Label Budget via Active Learning


Mar 09, 2022
Shuai Yuan, Xian Sun, Hannah Kim, Shuzhi Yu, Carlo Tomasi


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Joint Detection of Motion Boundaries and Occlusions


Nov 01, 2021
Hannah Halin Kim, Shuzhi Yu, Carlo Tomasi

* The British Machine Vision Conference (BMVC), 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Identity Connections in Residual Nets Improve Noise Stability


May 27, 2019
Shuzhi Yu, Carlo Tomasi

* ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning, additional analysis on a property called Dominant Gradient Flow of Residual Nets in Appendix D 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email