ILSVRC2017:Beyond ImageNet Large Scale Visual Recognition Challenge

Beyond ImageNet Large Scale Visual Recognition Challenge

July 26th in conjunction with CVPR 2017

引自:http://image-net.org/challenges/beyond_ilsvrc

Introduction

The workshop will mark the last of the ImageNet Challenge competitions, and focus on unanswered questions and directions for the future. The workshop will 1) present current results on the challenge competitions including new taster challenges, 2) review the state of the art in recognition as viewed through the lens of the object detection in images and videos, and classification competitions in the challenge. There will be a focus on 3) how this relates to the state of the art in computer vision techniques that are deployed in industry---one of the original goals of the challenge. The invited speakers will also be tasked with 4) presenting views on remaining future challenges, from cognitive vision, to robot vision, and beyond.

News

• Jul 17, 2017: ILSVRC2017 Results announced.
• Jun 16, 2017: Tentative schedule is announced.
• May 23, 2017: The workshop will feature a poster session from past ILSVRC participants. If you would like to apply, please email us for instructions before May 30.
• Mar 13, 2017: Webpage launched!

History

2016 2015 2014 2013

Challenges

• Please find detail challenge information at ILSVRC 2017

Workshop Schedule

The workshop will be on Wednesday, July 26th. Following is the tentative schedule.

• :

  9:00-9:05		Alex Berg andOlga Russakovsky:Opening remarks
  9:05-9:35		Fei-Fei Li andJia Deng:ImageNet: Where are we going? And where have we been?	slides
  9:35-10:10		Raquel Urtasun:Invited talk #1
  10:10-11:30 Poster session: recent work from winners of ILSVRC 2010-2016
  11:30-11:40		Overview of ILSVRC 2017	slides
  11:40-11:55		Jie Hu (WMW): Squeeze-and-Excitation Networks	slides
  11:55-12:10		Jianshu Li (NUS-Qihoo_DPNs): Dual Path Networks and its Applications	slides
  12:10-12:30		Short presentations of winning entries: NUS-Qihoo-UIUC_DPNs (VID), DeepView(ETRI), MIL_UT, SIIT_KAIST-SKT, KAISTNIA_ETRI	slides
  12:30-14:00 Lunch
  14:00-14:30		Jitendra Malik:Invited talk #2
  14:30-14:45 Awards
  14:45-15:00		Jiankang Deng (BDAT): BDAT Object Detection	slides
  15:00-15:15		Jiankang Deng (IC&USYD): Speed/Accuracy Trade-offs for Object Detection from Video	slides
  15:15-15:45		Larry Zitnick:Invited talk #3
  15:45-17:00 Poster session: winning entries of ILSVRC 2017
  Closing Remarks

Poster Sessions: Recent works from winners of ILSVRC 2010-2016

• [2013, NEC-MU] RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment - (Xi Peng, Rogerio S. Feris, Xiaoyu Wang, Dimitris N. Metaxas)
• [2013, NEC-MU] SEP-Net: Simple and Effective Pattern Networks - (Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang)
• [2014, TTIC-Chicago] DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild - (Riza Alp Guler, George Trigeorgis, Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, Iasonas Kokkinos)
• [2016, ResNeXt] Aggregated Residual Transformations for Deep Neural Networks - (Saining Xie, Ross Girshick, Piotr Dollar, Zhuowen Tu, Kaiming He)
• [2016, Trimps-Soushen] Brain MRI Diagnostic Using Deep Convolutional Network - (Shao Jie, Zhang Jie, Wu Jinsong, Zhang Zheng)
• [2013-2014, Overfeat,GoogLeNet] Unsupervised Imitation Learning - (Pierre Sermanet, Corey Lynch, Kelvin Xu, Jasmine Hsu, Sergey Levine)
• [2011-2015, UvA/Euvision,Qualcomm] SNPE: Snapdragon Neural Processing Engine powering deep learning on mobile devices - (Koen van de Sande, Cees Snoek)
• [2014-2016, CUHK,CUImage,CUVideo] Modeling context and deformation in object detection - (Wanli Ouyang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Kai Kang, Tong, Xiao, Kun Wang, Hongyang Li, Zhe Wang, Yucong, Zhou, Bin Yang, Xuanyi Dong, Ping Luo, Shi Qiu, Yonglong Tian, Shuo Yang, Yuanjun Xiong, Chen Qian, Zhenyao Zhu, Ruohui Wang, Yubin Deng, Buyu Li, Xin Zhu, Xihui Liu, Chen-Change Loy, Shengen Yan, Dahua Lin, Xiaogang Wang, Xiaoou Tang)

Poster Sessions: Winning entries of ILSVRC 2017

• [DeepView(ETRI)] DeepView ObjectNet: Rank of Experts - (Seung-Hwan Bae, Youngjoo Jo, Joongwon Hwang, Youngwan Lee, Young-Suk Yoon, Yuseok Bae, Jongyoul Park)
• [KAISTNIA_ETRI] Aggregating multi-level/shape features and confidence penalty for object detection - (Keun Dong Lee, Seungjae Lee, JongGook Ko, Jaehyung Kim, Jun Hyun Nam, Jinwoo Shin)
• [SIIT_KAIST-SKT] Deep Pyramidal Residual Networks - (Dongyoon Han, Jiwhan Kim, Gwang-Gook Lee, Junmo Kim)
• [MIL_UT] MIL_UT at ILSVRC2017 (CLS Task) - (Yuji Tokozume, Kosuke Arase, Yoshitaka Ushiku, Tatsuya Harada)
• [NUS-Qihoo-UIUC_DPNs] Improving Context Modeling for Video Object Detection and Tracking - (Yunchao Wei, Mengdan Zhang, Jianan Li, Yunpeng Chen, Jiashi Feng, Jian Dong, Shuicheng Yan, Honghui Shi)

Organizers

• Olga Russakovsky (Carnegie Mellon University / Princeton University)
• Eunbyung Park (UNC Chapel Hill)
• Wei Liu (UNC Chapel Hill)
• Jia Deng (University of Michigan)
• Fei-Fei Li (Stanford University)
• Alex Berg (UNC Chapel Hill)

Affiliated Challenge

• Low-Power Image Recognition Challenge(LPIRC) 2017

Contact

Please feel free to send any questions or comments to ilsvrc@image-net.org.