By tech | October 4, 2018 | Category Uncategorized
Amir Rasouli will present “It’s Not All About Size: On the Role of Data Properties in Pedestrian Detection,” at the 6th Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving (CVRSUAD) at the European Conference on Computer Vision (ECCV 2018). The poster can be found here, and for more information on the workshop, […]
Read MoreBy tech | October 4, 2018 | Category Uncategorized
Abstract: The Selective Tuning model of visual attention (Tsotsos, 1990) has proposed that the focus of attention is surrounded by an inhibitory zone, eliciting a center-surround attentional distribution. This attentional suppressive surround inhibits irrelevant information which is located close to attended information in physical space (e.g., Cutzu and Tsotsos, 2003; Hopf et al., 2010) or […]
Read MoreBy tech | October 4, 2018 | Category Uncategorized
Abstract: Perceptual judgment of image similarity by humans relies on rich internal representations ranging from low-level features to high-level concepts, scene properties and even cultural associations. However, existing methods and datasets attempting to explain perceived similarity use stimuli which arguably do not cover the full breadth of factors that a ect human similarity judgments, even those […]
Read MoreBy tech | August 1, 2018 | Category Uncategorized
John Tsotsos recently turned 65! To honour John’s many contributions in the visual sciences, a Spoken Festschrift and Celebratory Symposium was held on Saturday, May 12th, 2018 at York University in Toronto, Canada. There were talks from distinguished researchers in areas in which John has contributed, as well as talks by his academic children. […]
Read MoreBy tech | July 5, 2018 | Category Uncategorized
A Demonstration of interesting failures of State-of-The-Art object detectors by Amir Rosenfeld. Contact details can be found here: https://sites.google.com/view/amirrosenfeld/ Media mentions: Quanta Magazine: Machine Learning Confronts the Elephant in the Room The Register: AI image recognition systems can be tricked by copying and pasting random objects jiqizhixin.com: 「房间里的大象」：让目标检测器一脸懵逼 Import AI: Fooling object recognition systems by […]
Read MoreBy tech | July 3, 2018 | Category Uncategorized
Markus Solbach and Amir Rosenfeld presented Totally-Looks-Like: How Humans Compare, Compared to Machines at the CVPR 2018 workshop “Mutual benefits of Cognitive and Computer Vision”. CVPR 2018 — Workshop “Mutual Benefits of Cognitive and Computer Vision”: https://sites.google.com/site/mbcc2018w/ Project page: https://sites.google.com/view/totally-looks-like-dataset
Read MoreBy tech | July 3, 2018 | Category Uncategorized
On June 26th, the lab hosted six visitors from Team Homer from the University of Koblenz! Team Homer is part of the Active Vision research group (AGAS, http://agas.uni-koblenz.de) at the Institute of Computational Visualistics of the University of Koblenz-Landau. It was a great day where we heard about their recent victory in the RoboCup @Home […]
Read MoreBy tech | May 2, 2018 | Category Uncategorized
On April 28th our lab welcomed a number of high school students interested in joining the Lassonde School of Engineering at the Lassonde Open House. The EECS department organized lab tours where students had an opportunity to see exciting research happening here first-hand, as well as hear about undergraduate opportunities at the School. Markus Solbach, […]
Read MoreBy tech | April 1, 2018 | Category Uncategorized
Abstract Scene Classification has been addressed with numerous techniques in the computer vision literature. However with the increasing size of datasets in the field, it has become difficult to achieve high accuracy in the context of robotics. We overcome this problem and obtain good results through our approach. In our approach, we propose to address […]
Read MoreBy tech | March 8, 2018 | Category Uncategorized
Paper (arXiv): Totally-Looks-Like: How Humans Compare, Compared to Machines Project website. Perceptual judgment of image similarity by humans relies on a rich internal representations ranging from low-level features to high-level concepts, scene properties and even cultural associations. Exist ing methods and datasets attempting to explain perceived similarity use stimuli which arguably do not cover the […]
Read More