The PASCAL Visual Object Classes Challenge Workshop 2010

11th September 2010, ECCV 2010, Crete, Greece

Introduction

This workshop will present and discuss the results of the PASCAL Visual Object Classes Challenge (VOC2010). The challenge has three main competitions, one testing image classification ("does the image contain an instance of this class?"), one testing object detection ("provide a bounding box for each instance of the class, if any"), and one evaluating object segmentation at the pixel level. In addition there are three 'taster' competitions, on person layout ("where are this person's head, hands and feet?"), still-image action classification ("is this person running/playing an instrument, etc.?"), and large scale recognition using ImageNet.

Full details of the challenge.

Venue

The workshop was held on 11th September 2010, in association with ECCV 2010.

"Lifetime Achievement" Prize

The VOC organizers were especially happy to award a "lifetime achievement" prize to the authors of the "Discriminatively Trained Deformable Part Model" known to VOC participants as the "UoCTTI" object detection method:

Pedro Felzenszwalb1, Ross Girshick1, David McAllester2, Deva Ramanan3
1University of Chicago; 2Toyota Technological Institute at Chicago; 3University of California, Irvine

First submitted to the PASCAL VOC challenge in 2007, this detector has now become a core component of many classification, segmentation, person layout and action classification submissions. We honour the contribution made to the community by the innovation and success of the method and its free distribution.

Prizes

The following prizes were announced at the workshop:

Classification
Winner: NUSPSL_KERNELREGFUSING
Qiang Chen1, Zheng Song1, Si Liu1, Xiangyu Chen1, Xiaotong Yuan1, Tat-Seng Chua1, Shuicheng Yan1, Yang Hua2, Zhongyang Huang2, Shengmei Shen2
1National University of Singapore; 2Panasonic Singapore Laboratories
Detection
Winner: NLPR_HOGLBP_MC_LCEGCHLC
Yinan Yu, Junge Zhang, Yongzhen Huang, Shuai Zheng, Weiqiang Ren, Chong Wang, Kaiqi Huang, Tieniu Tan
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
Honourable Mentions: MITUCLA_HIERARCHY
Long Zhu, Yuanhao Chen, William Freeman, Alan Yuille, Antonio Torralba
MIT, UCLA

NUS_HOGLBP_CTX_CLS_RESCORE_V2
Zheng Song, Qiang Chen, Shuicheng Yan
National University of Singapore

UVA_GROUPLOC/UVA_DETMONKEY
Jasper Uijlings, Koen van de Sande, Theo Gevers, Arnold Smeulders, Remko Scha
University of Amsterdam
Segmentation
Joint Winners: CVC_HARMONY_DET
Josep Maria Gonfaus, Xavier Boix, Fahad Kahn, Joost van de Weijer, Andrew Bagdanov, Marco Pedersoli, Joan Serrat, Xavier Roca, Jordi Gonzalez
Computer Vision Center, Universitat AutÚnoma de Barcelona

BONN_SVR_SEGM
Joao Carreira, Fuxin Li, Cristian Sminchisescu
University of Bonn
Honourable Mention: BERKELEY_POSELETS_ALIGN_PB
Thomas Brox, Lubomir Bourdev, Subhransu Maji, Jitendra Malik
University of California, Berkeley
Person Layout Taster
Joint Winners: BCNPCL_Human_Layout
M. Drozdzal, A. HernŠndez, S. SeguŪ, X. Baro, S. Escalera, A. Lapedriza, D. Masip, P. Radeva, J. Vitria
Computer Vision Center Barcelona; Universitat Oberta de Catalunya

OXFORD_SBD
Arpit Mittal, Andrew Zisserman, Philip H. S. Torr, Manuel J. Marin
University of Oxford; Oxford Brookes University
Action Classification Taster
Joint Winners: CVC_SEL/CVC_BASE
Nataliya Shapovalova, Wenjuan Gong, Fahad Shahbaz Khan, Josep M. Gonfaus, Marco Pedersoli, Andrew D. Bagdanov, Joost van de Weijer, Jordi Gonzalez
Computer Vision Center, Universitat Autonoma de Barcelona

INRIA_SPM_HT
Norberto Adrian Goussies, Arnau Ramisa, Cordelia Schmid
INRIA LEAR

NUDT_SVM_WHGO_SIFT_CENTRIST_LLM
Li Zhou, Zongtan Zhou, Dewen Hu
National University of Defence Technology

SURREY_MK_KDA
Piotr Koniusz, Muhammad Atif Tahir, Mark Barnard, Fei Yan, Krystian Mikolajczyk
University of Surrey

UCLEAR_SVM_DOSP_MULTFEATS
Gaurav Sharma, Frederic Jurie, Cordelia Schmid
University of Caen; INRIA LEAR

UMCO_DHOG_KSVM
Xutao Lv, Xiaoyu Wang, Xi Zhou, Tony X. Han
University of Missouri - Columbia

Programme

09:00 - 09:20 Overview and results of the classification challenge
Mark Everingham
University of Leeds
[PDF]

09:20 - 09:40 Classification methods

Boosting Classification with Exclusive Context
Qiang Chen1, Zheng Song1, Si Liu1, Xiangyu Chen1, Xiaotong Yuan1, Tat-Seng Chua1, Shuicheng Yan1, Yang Hua2, Zhongyang Huang2, Shengmei Shen2
1National University of Singapore; 2Panasonic Singapore Laboratories
[PDF] NB: This is unpublished work. Please contact the authors if you plan to make use of any of the ideas presented.

09:40 - 10:00 Overview and results of the detection challenge
Mark Everingham
University of Leeds
[PDF]

10:00 - 10:40 Detection methods

Object Detection by Context and Boosted HOG-LBP
Yinan Yu, Junge Zhang, Yongzhen Huang, Shuai Zheng, Weiqiang Ren, Chong Wang, Kaiqi Huang, Tieniu Tan
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
[PDF] NB: This is unpublished work. Please contact the authors if you plan to make use of any of the ideas presented.

Latent Hierarchical Structural Learning
Long Zhu, Yuanhao Chen, William Freeman, Alan Yuille, Antonio Torralba
MIT; UCLA
- presented by Biliana Kaneva (MIT)
[PDF]

10:40 - 11:00 Break

11:00 - 11:20 Overview and results of the segmentation challenge
Mark Everingham
University of Leeds
[PDF]

11:20 - 11:40 Segmentation methods

Harmony Potentials: Fusing Global and Local Scale for Semantic Image Segmentation
Josep M. Gonfaus, Xavier Boix, Fahad S. Khan, Joost van de Weijer, Andrew D. Bagdanov, Marco Pedersoli, Joan Serrat, Xavier Roca, Jordi Gonzŗlez
Computer Vision Center - Universitat AutÚnoma de Barcelona
[PDF] NB: This is unpublished work. Please contact the authors if you plan to make use of any of the ideas presented.

11:40 - 12:00 Overview and results of the action classification taster challenge
Ivan Laptev
INRIA Paris
[PDF]

12:00 - 12:20 Action classification methods

Recognizing actions based on interactions between humans and objects
G. Sharma, N. Goussies, A. Ramisa, F. Jurie, C. Schmid
INRIA LEAR; University of Caen

12:20 - 12:40 Overview, results and methods of the person layout taster challenge
Mark Everingham
University of Leeds
[PDF]

12:40 - 14:00 Lunch

14:00 - 15:00 Overview and results of the ILSVRC2010 taster challenge in large scale visual recognition
Alex Berg
Stony Brook University

NEC-UIUC method
Yuanqing Lin1, Fengjun Lv1, Shenghuo Zhu1, Ming Yang1, Timothee Cour1, Kai Yu1, LiangLiang Cao2, Zhen Li2, Min-Hsuan Tsai2, Xi Zhou2, Thomas Huang2, Tong Zhang3
1NEC; 2UIUC; 3Rutgers

XCRE method Jorge Sanchez, Florent Perronnin, Thomas Mensink
Xerox Research Center Europe

More information and presentations available at the ILSVRC2010 website
15:00 - 15:40 Conclusions and discussion
[PDF]

Organizers

Support

The preparation and running of this challenge is supported by the EU-funded PASCAL2 Network of Excellence on Pattern Analysis, Statistical Modelling and Computational Learning.