Profile cover photo
Profile photo
Shikhar Sharma
307 followers
307 followers
About
Shikhar's posts

Post has shared content
Check out papers/posters from our lab at ICLR 2016! We are also releasing our code publicly for most of them.

Too bad I wouldn't get my visa in time.
If you are going to ICLR, check out these posters/papers, and more importantly, check out (some of the) associated code -- I am trying to encourage all my students to release their code!


Importance Weighted Autoencoders, Yuri Burda, Roger Grosse, Ruslan Salakhutdinov, ICLR 2016
http://arxiv.org/abs/1509.00519
Code: https://github.com/yburda/iwae

Generating Images from Captions with Attention, Elman Mansimov, Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov, ICLR 2016
http://arxiv.org/abs/1511.02793
Code: https://github.com/emansim/text2image

Action Recognition using Visual Attention, Shikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov, ICLR workshop 2016
http://arxiv.org/abs/1511.04119
Code: https://github.com/kracwarlock/action-recognition-visual-attention

Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning, Emilio Parisotto, Jimmy Lei Ba, Ruslan Salakhutdinov, ICLR 2016
http://arxiv.org/abs/1511.06342
Code: coming soon.

Data-Dependent Path Normalization in Neural Networks, Behnam Neyshabur, Ryota Tomioka, Ruslan Salakhutdinov, Nathan Srebro, ICLR 2016
http://arxiv.org/abs/1511.06747

Post has shared content
The code and paper for the work I presented at NIPS Time Series Workshop 2015 - "Action Recognition using Visual Attention" is available:

Project Website: http://www.cs.toronto.edu/~shikhar/projects/action-recognition-attention
GitHub: https://github.com/kracwarlock/action-recognition-visual-attention
Workshop Paper: https://sites.google.com/site/nipsts2015/accepted-papers
Full paper on arXiv: http://arxiv.org/abs/1511.04119
Shikhar Sharma is releasing the code for performing action recognition in videos using visual attention. Check it out:

http://shikharsharma.com/projects/action-recognition-attention/

work with Shikhar Sharma and Ryan Kiros
http://arxiv.org/abs/1511.04119

Post has shared content
Video lectures from the Montreal Deep Learning Summer School are now available

Post has attachment
See how computer vision helps us in getting some "Insight" on our friends' "Perspectives" - Perspective Projection and Image Homography
Wait while more posts are being loaded