Sponsored by


Jose Alvarez



13:00 Opening
13:05 Pierre Sermanet (Google) Deep Learning and Computer Vision
14:00 Sijin Li, Zhi-Qiang LIU, Antoni B. ChanHeterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
14:15 Wei Wang, Yan Huang, Yizhou Wang, Liang WangGeneralized Auto-encoder: A Neural Network Framework for Dimensionality Reduction
14:30 Carlo Gatta, Adriana Romero, Joost van de Weijer Unrolling loopy top-down semantic feedback in convolutional deep networks
14:45 Ali Sharif Razavian, Hossein Azizpour, Josephine Sullivan, Stefan Carlsson CNN Features off-the-shelf: an Astounding Baseline for Recognition
15:00 Lior Wolf, Yair Hanani, Tal Hassner A Piggyback Representation for Action Recognition
15:15 Poster Session
15:55 Awards
16:00 Chang Huang (Baidu)
16:50 Concluding Remarks

Best Paper Award

NVIDIA sponsored the following awards:


Organizing Commitee

Description of the workshop

The goal of the DeepVision Workshop 2014 is to accelerate the study of deep learning algorithms in computer vision problems. With the increase of acceleration of digital photography and the advances in storage devices over the last decade, we have seen explosive growth in the available amount of visual data and equally explosive growth in the computational capacities for image understanding. Instead of hand crafting features, recent advancement in deep learning suggests an emerging approach to extracting useful representations for many computer vision tasks. We encourage researchers to formulate innovative learning theories, feature representations, and end-to-end vision systems based on deep learning. We also encourage new theories and processes for dealing with large scale image datasets through deep learning architectures. We are soliciting original contributions that address a wide range of theoretical and practical issues including, but not limited to:

  1. Supervised and unsupervised algorithms in computer vision,
  2. Deep learning hardware and software architecture,
  3. Advancements in deep learning,
  4. Large scale computer vision problems including object recognition, scene analysis, industrial and medical applications.

Invited Speakers

  1. Chang Huang, Baidu
  2. Pierre Sermanet, Google

Important Dates

  1. Paper Submission (extended): March 22nd, 2014
  2. Notification of acceptance: April 28th, 2014
  3. Camera-ready paper: May 5th, 2014
  4. Workshop (half day): 28th of June 2014

Paper Submission

Program Committee