BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Turkey
BEGIN:DAYLIGHT
DTSTART:20380119T061407
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=3TU;BYMONTH=1
TZNAME:+03
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20160907T000000
TZOFFSETFROM:+0300
TZOFFSETTO:+0300
RRULE:FREQ=YEARLY;BYDAY=1WE;BYMONTH=9
TZNAME:+03
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20190311T203130Z
UID:B1FE0754-8BD6-4520-BBA5-E44FF124B154
DTSTART;TZID=Turkey:20190301T133000
DTEND;TZID=Turkey:20190301T153000
DESCRIPTION:Speaker: Asst. Prof. Emre Akbaş\, Middle East Technical Univer
 sity\n\nTopic: "Object Detection Through Search with a Foveated Visual Sys
 tem"\n\nLocation: Middle East Technical University\, Ankara\, Turkey\n\nAb
 stract: In this talk\, I will present a foveated object detector (FOD) as 
 a biologically-inspired alternative to the sliding window (SW) approach wh
 ich is the dominant method of search in computer vision object detection. 
 Similar to the human visual system\, the FOD has higher resolution at the 
 fovea and lower resolution at the visual periphery. Consequently\, more co
 mputational resources are allocated at the fovea and relatively fewer at t
 he periphery. The FOD processes the entire scene\, uses retino-specific ob
 ject detection classifiers to guide eye movements\, aligns its fovea with 
 regions of interest in the input image and integrates observations across 
 multiple fixations. Our approach combines object detectors from computer v
 ision with a recent model of peripheral pooling regions found at the V1 la
 yer of the human visual system. We assessed various eye movement strategie
 s on the PASCAL VOC 2007 dataset and show that the FOD performs on par wit
 h the SW detector while bringing significant computational cost savings.\n
 \nBio: Dr. Emre Akbas is an assistant professor at the Department of Compu
 ter Engineering\, Middle East Technical University (METU). Prior to joinin
 g METU\, he was a postdoctoral research associate at the Department of Psy
 chological and Brain Sciences\, University of California Santa Barbara. He
  received his PhD degree from the Department of Electrical and Computer En
 gineering\, University of Illinois at Urbana-Champaign in 2011. His BS and
  MS degrees are from the Department of Computer Engineering\, METU.\n\nSpe
 aker(s): Asst. Prof. Emre Akbaş\, \n\nAnkara\, Ankara\, Türkiye
LOCATION:Ankara\, Ankara\, Türkiye
ORGANIZER:ozergul@metu.edu.tr
SEQUENCE:1
SUMMARY:IEEE AP/MTT/EMC/ED TURKEY CHAPTER SEMINAR SERIES -- SEMINAR 44
URL;VALUE=URI:https://events.vtools.ieee.org/m/194919
X-ALT-DESC:Description: <br /><p class="p1">Speaker: Asst. Prof. Emre Akba
 ş\, Middle East Technical University</p>\n<p>Topic: "Object Detection Thr
 ough Search with a Foveated Visual System"</p>\n<p>Location:&nbsp\;Middle 
 East Technical University\, Ankara\, Turkey</p>\n<p>Abstract:&nbsp\;<span 
 class="s1">In this talk\, I will present a foveated object detector (FOD) 
 as a biologically-inspired alternative to the sliding window (SW) approach
  which is the dominant method of search in computer vision object detectio
 n. Similar to the human visual system\, the FOD has higher resolution at t
 he fovea and lower resolution at the visual periphery. Consequently\, more
  computational resources are allocated at the fovea and relatively fewer a
 t the periphery. The FOD processes the entire scene\, uses retino-specific
  object detection classifiers to guide eye movements\, aligns its fovea wi
 th regions of interest in the input image and integrates observations acro
 ss multiple fixations. Our approach combines object detectors from compute
 r vision with a recent model of peripheral pooling regions found at the V1
  layer of the human visual system. We assessed various eye movement strate
 gies on the PASCAL VOC 2007 dataset and show that the FOD performs on par 
 with the SW detector while bringing significant computational cost savings
 .</span></p>\n<p>Bio:&nbsp\;<span class="s1">Dr. Emre Akbas is an assistan
 t professor at the Department of Computer Engineering\, Middle East Techni
 cal University (METU). Prior to joining METU\, he was a postdoctoral resea
 rch associate at the Department of Psychological and Brain Sciences\, Univ
 ersity of California Santa Barbara. He received his PhD degree from the De
 partment of Electrical and Computer Engineering\, University of Illinois a
 t Urbana-Champaign in 2011. His BS and MS degrees are from the Department 
 of Computer Engineering\, METU.</span></p>
END:VEVENT
END:VCALENDAR