SUNw: Scene Understanding Workshop 2017
July 26, 2017, CVPR 2017 at Hawaii.

Spotlight Posters

Understanding Convolution for Semantic Segmentation (pdf)
Panqu Wang, UC San Diego; Pengfei Chen, UC San Diego; Ye Yuan, Carnegie Mellon University; Ding Liu, UIUC; Zehua Huang, TuSimple, LLC; Xiaodi Hou, TuSimple, LLC; Garrison Cottrell, UC San Diego
High-level Cues for Predicting Motivations (pdf)
Arun Mallya, UIUC; Svetlana Lazebnik, UIUC
SalGAN: Visual Saliency Prediction with Adversarial Networks (pdf, webpage)
Junting Pan, UPC; Cristian Canton Ferrer, Facebook; Kevin McGuinness, Noel E. O'Connor, Insight DCU; Jordi Torres, BSC; Elisa Sayrol, Xavier Giro-i-Nieto, UPC
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (pdf)
Aishwarya Agrawal, Virginia Tech; Dhruv Batra, Georgia Institute of Technology; Devi Parikh, Georgia Institute of Technology; Aniruddha Kembhavi, Allen Institute for Artificial Intelligenc.
Network Dissection: Quantifying Interpretability of Deep Visual Representations (pdf, webpage)
David Bau*, MIT; Bolei Zhou*, MIT; Aditya Khosla, MIT; Aude Oliva, MIT; Antonio Torralba, MIT

All the Accepted Posters

Understanding Convolution for Semantic Segmentation (pdf)
Panqu Wang, UC San Diego; Pengfei Chen, UC San Diego; Ye Yuan, Carnegie Mellon University; Ding Liu, UIUC; Zehua Huang, TuSimple, LLC; Xiaodi Hou, TuSimple, LLC; Garrison Cottrell, UC San Diego
CNN based Repeated Cropping for Photo Re-composition (pdf)
Eunbin Hong, POSTECH; Junho Jeon, POSTECH; Seungyong Lee, POSTECH
Object-Level Context Modeling For Scene Classification with Context-CNN (pdf)
Syed Javed, IIIT Hyderabad; Anil Nelakanti, Amazon
Detecting Nonexistent Pedestrians (pdf)
Jui Ting Chien, National Tsing Hua University; Chia-Jung Chou, National Tsing Hua University; Hwann-Tzong Chen, National Tsing Hua University
Self-Supervised Depth Learning Improves Semantic Segmentation (pdf)
Huaizu Jiang, UMass Amherst; Erik Learned-Miller, University of Massachusetts, Amherst; Gustav Larsson, University of Chicago; Michael Maire, Toyota Technological Institute at Chicago; Greg Shakhnarovich, Toyota Technological Institute at Chicago
Depth Estimation from Monocular Image with Sparse Known Labels (pdf)
Yaoyu Li, Institute of Automation, Chinese Academy of Sciences; Yifan Zhang, Institute of Automation, Chinese Academy of Sciences
Good Practice on Deep Scene Classification: from Local Supervision to Knowledge Guided Disambiguation (pdf)
Yu Qiao, Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Limin Wang, ETHZ; Sheng Guo, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Zhe Wang, University of California, Irvine; Weilin Huang, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Yali Wang, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
Uber-Text: A Large-Scale Dataset for Optical Character Recognition from Street-Level Imagery (pdf)
Ying Zhang, University of Montreal; Ben Kadlec, Uber; Peter Zhang, Uber; Lionel Gueguen, Uber; Keith Seifert, Uber
Object Recognition and Reconstruction with Partial Appearance (pdf)
Lifeng Liu, Xiaotian Yin, Yingxuan Zhu, Jun Zhang, Jian Li, FutureWei Technologies.
Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (pdf)
Aishwarya Agrawal, Virginia Tech; Dhruv Batra, Georgia Institute of Technology; Devi Parikh, Georgia Institute of Technology; Aniruddha Kembhavi, Allen Institute for Artificial Intelligenc.
Object Filtering and Uniform Representation for Autonomous Decision Making (pdf)
Xiaotian Yin, Huawei R&D USA; Lifeng Liu, Huawei R&D USA; Yingxuan Zhu, Huawei R&D USA; jun zhang, Huawei R&D USA; Jian Li, Huawei R&D USA
AR-based Maintenance Verification Using Object State Recognition (pdf)
Pavel Dvorak, Konica Minolta Business Solutions Czech spol. s r. o.; Elisabetta Delponte, Konica Minolta Laboratory Europe; Radovan Josth, Konica Minolta Business Solutions Czech spol. s r. o.
Weakly Supervised PatchNets: Learning Aggregated Patch Descriptors for Scene Recognition (pdf)
Zhe Wang, University of California, Irvine; Limin Wang, ETH; Yali Wang, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Bowen Zhang, Tongji University; Yu Qiao, Multimedia Laboratory, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences; Charless Fowlkes, UC Irvine
Lessons Learned from a Lightweight Autonomous Vehicle Implementation (pdf)
Kuan Wang, Tsinghua University; Dawei Sun, Tsinghua University; Xiaojian Ma, Tsinghua University; Zhaoyuan Gu, Tsinghua University; Hao Zhao, Tsinghua University; Tianlei Zhang, Tsinghua University
High-level Cues for Predicting Motivations (pdf)
Arun Mallya, UIUC; Svetlana Lazebnik, UIUC
SalGAN: Visual Saliency Prediction with Adversarial Networks (pdf, webpage)
Junting Pan, UPC; Cristian Canton Ferrer, Facebook; Kevin McGuinness, Noel E. O'Connor, Insight DCU; Jordi Torres, BSC; Elisa Sayrol, Xavier Giro-i-Nieto, UPC
What is Wrong with Them?: Qualitative Analysis on ImageNet Failure Cases (pdf)
Han Lee, KAIST; Junmo Kim, KAIST
Network Dissection: Quantifying Interpretability of Deep Visual Representations (pdf)
David Bau*, MIT; Bolei Zhou*, MIT; Aditya Khosla, MIT; Aude Oliva, MIT; Antonio Torralba, MIT