Introduction
The purpose of the workshop is to present the methods and results of the Image Net Large Scale Visual Recognition Challenge (ILSVRC) 2014. Challenge participants with the most successful and innovative entries will be invited to present.The challenge evaluates algorithms for object detection and image classification at large scale. This year there will be two competitions:
- A PASCAL-style detection challenge on fully labeled data for 200 categories of objects, and
- An image classification plus object localization challenge with 1000 categories.
For more details, please visit ILSVRC 2014. The submission deadline was August 15, 2014.
News
- September 19, 2014: All slides and videos are now available. The videos are courtesy of Koen van de Sande -- thank you!!
- September 12, 2014: Many thanks to all workshop participants! Slides and videos will be available shortly.
Workshop Schedule
The workshop took place on Friday, September 12th in room E7.ILSVRC2014 object detection competition (details, results) | |||||||||||||||||||
8:45 | ![]() ![]() |
Alex Berg and Olga Russakovsky, ILSVRC2014 object detection: introduction, results, analysis | video, slides (16M) |
||||||||||||||||
9:10 | ![]() |
NUS team: Shuicheng Yan, NIN, Good | video, slides (1.9M) |
||||||||||||||||
9:25 | ![]() |
GoogLeNet team: Christian Szegedy, Going Deeper With Convolutions | video, slides (2M), paper | ||||||||||||||||
9:45 | ![]() |
CUHK DeepID-Net team: Wanli Ouyang, DeepID-Net: deformable deep convolutional neural network for generic object detection |
video, slides (5.6M), project |
||||||||||||||||
10:00 | ![]() |
MSRA Visual Computing team: Kaiming He SPP-net: Spatial Pyramid Pooling in Deep Convolutional Networks |
video, slides, poster, project, code |
||||||||||||||||
10:15 | ILSVRC2014 object detection spotlights:
|
video | |||||||||||||||||
Coffee break | |||||||||||||||||||
ILSVRC2014 classification and localization competition (details, results) | |||||||||||||||||||
11:00 | ![]() |
Olga Russakovsky, ILSVRC2014 classification and localization: introduction, results, analysis | video, slides (16M) |
||||||||||||||||
11:15 | ![]() |
TTIC_ECP team: Iasonas Kokkinos, Deep Epitomic Neural Networks and Explicit Scale/Position Search for Image Recognition |
video, slides pptx (8.1M), slides pdf (12M), project |
||||||||||||||||
11:30 | ![]() |
VGG team: Karen Simonyan, Very Deep Convolutional Networks for Large-Scale Image Recognition |
video, slides, paper, project |
||||||||||||||||
11:45 | ![]() |
CASIA_CRIPAC_Weak_Supervision team: Chong Wang, Object Recognition with Weak Supervision | video, slides (6M) |
||||||||||||||||
12:00 | ![]() |
MIL team: Tatsuya Harada, MIL-UT at ILSVRC2014 |
video, slides (1.2M) |
||||||||||||||||
12:15 | ILSVRC2014 classification with localization spotlights:
|
video | |||||||||||||||||
Lunch break | |||||||||||||||||||
ILSVRC2014 awards and discussion | |||||||||||||||||||
14:00 |
![]() ![]() |
ILSVRC2014 awards presented by Jia Deng, sponsored by NVIDIA | video, slides (2.2M) |
||||||||||||||||
14:10 | ![]() |
Larry Zitnick, Microsoft COCO: Common Objects in Context |
video, slides, project |
||||||||||||||||
14:20 | ![]() |
Lubomir Bourdev, Using Context for Object Recognition at Facebook | |||||||||||||||||
14:30 | ![]() |
Chuck Rosenberg, Deep Networks for Computer Vision at Google | slides (50M) video | ||||||||||||||||
14:40 | ![]() |
Open discussion moderated by Alex Berg | video | ||||||||||||||||
15:00 | ILSVRC2014 poster and demo session | ||||||||||||||||||
Live demos:
|
Organizers
- Olga Russakovsky ( Stanford University )
- Sean Ma ( Stanford University )
- Jonathan Krause ( Stanford University )
- Jia Deng ( University of Michigan )
- Alex Berg ( UNC Chapel Hill )
- Fei-Fei Li ( Stanford University )
Sponsors




