IntroductionThe purpose of the workshop is to present the methods and results of the Image Net Large Scale Visual Recognition Challenge (ILSVRC) 2013 and the new Fine-Grained Challenge 2013. Challenge participants with the most successful and innovative entries will be invited to present.
The ILSVRC2013 evaluates algorithms for object detection and image classification at large scale. This year there are three competitions:
- A PASCAL-style detection challenge on fully labeled data for 200 categories of objects,NEW
- An image classification challenge with 1000 categories, and
- An image classification plus object localization challenge with 1000 categories.
The new Fine-Grained Challenge 2013 runs concurrently with ILSVRC2013 this year, and targets classification among categories which are both visually and semantically similar. For more details, please visit Fine-Grained Challenge 2013.
- Dec. 11, 2013. The workshop was a success! Thanks to the many amazing participants! Slides are available below.
Workshop ScheduleThe workshop took place on Saturday, December 7th in Room 104.
|ILSVRC2013 classification and localization competitions (details, results)|
|8:30||Alexander Berg and Olga Russakovsky, ILSVRC2013 classification and localization: Introduction, analysis, awards||slides (12M)|
|8:50||Matthew Zeiler, Visualizing and Understanding Convolutional Neural Networks||video (368M)|
|9:05||Shuicheng Yan, Adaptive Non-parametric Rectification of Shallow and Deep Experts
|9:20||Andrew Zisserman, Deep Fisher Networks and Class Saliency Maps for Object Classification and Localisation
|9:35||Pierre Sermanet, Classification, Localization and Detection with Deep Learning||slides (31M)|
|9:50|| ILSVRC2013 classification spotlights:
|ILSVRC2013 detection competition (details, results)|
|10:30||Olga Russakovsky, ILSVRC2013 detection: Introduction, analysis, awards||slides (9M)|
|10:50|| Xiaoyu Wang, Regionlets for Generic Object Detection
[paper in ICCV13]
|11:10|| Koen van de Sande and Daniel Fontijne, University of Amsterdam and Euvision Technologies at ILSVRC 2013
[Euvision Technologies, research, Impala app, ImageNet app]
|11:30|| ILSVRC2013 detection spotlights:
|11:40|| Ross Girshick (UC Berkeley), Rich feature hierarchies for accurate object detection and semantic segmentation
|12:00|| Panel discussion:
|14:00||Vittorio Ferrari (University of Edinburgh), Auto-annotation and self-assessment in ImageNet||slides (22M)|
|Fine-Grained Challenge 2013|
|14:40||Detailed schedule available here|
- Olga Russakovsky ( Stanford University )
- Jonathan Krause ( Stanford University )
- Jia Deng ( Stanford University )
- Alex Berg ( UNC Chapel Hill )
- Fei-Fei Li ( Stanford University )