Imperial College London > Talks@ee.imperial > Featured talks > Fast object detection with binary feature representation (Fujiyoshi) & Facial Analysis and Human Understanding with Deep Learning (Yamashita)

Fast object detection with binary feature representation (Fujiyoshi) & Facial Analysis and Human Understanding with Deep Learning (Yamashita)

Add to your list(s) Download to your calendar using vCal

  • UserHironobu Fujiyoshi & Takayoshi Yamashita, Chubu University
  • ClockThursday 03 September 2015, 10:30-12:00
  • HouseEEE Department, Room 503.

If you have a question about this talk, please contact Patrick Kelly.

Fast object detection with binary feature representation | Hironobu Fujiyoshi (Chubu University)

[Abstract] Object detection involves classification of a huge number of detection windows obtained by raster scanning of an input image. In this talk, we introduce an approximate computation of linear SVM with binary feature representation to object detection to increase the speed of raster scanning. We will show that the proposed method is about 16 times faster than the conventional HOG and linear SVM and improves the classification accuracy by about 6%.

[Bio.] Dr. Fujiyoshi received his Ph.D. in Electrical Engineering from Chubu University, Japan, in 1997. From 1997 to 2000 he was a postdoctoral fellow at the Robotics Institute of Carnegie Mellon University, Pittsburgh, PA, USA , working on the DARPA Video Surveillance and Monitoring (VSAM) effort and the humanoid vision project for the HONDA Humanoid Robot. He is now a professor of the Department of Computer Science, Chubu University, Japan. From 2005 to 2006, he was a visiting researcher at Robotics Institute, Carnegie Mellon University. His research interests include computer vision, video understanding and pattern recognition. He is a member of the IEEE , the IEICE , and the IPSJ .

_

Facial Analysis and Human Understanding with Deep Learning | Takayoshi Yamashita (Chubu University)

[Abstract] Deep learning is significantly attracting attention in computer vision. We have researched two aspects about deep learning. 1) application of deep learning, and 2) efficient training manner. We have applied deep learning to facial point detection and age and gender estimation. In addition, we have considered the way to obtain efficient initial parameters of the network with Curriculum learning. In this talk, we will briefly introduce these researches.

[Bio.] Dr. Yamashita received his Ph.D degree from Department of Computer Science, Chubu University, Japan in 2011. He worked in OMRON Corporation from 2002 to 2014. He is a lecturer of the Department of Computer Science, Chubu University, Japan since 2014. His current research interests include object detection, object tracking, human activity understanding, pattern recognition and machine learning. He is a member of the IEEE , the IEICE and the IPSJ .

This talk is part of the Featured talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Changes to Talks@imperial | Privacy and Publicity