SUNw: Scene Understanding Workshop

Accepted Posters

COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images (pdf, project website)
Andreas Veit (Cornell University), Tomas Matera (Cornell Tech), Lukas Neumann (Czech Technical University), Jiri Matas (CMP CTU FEE), Serge Belongie (Cornell University)
Graph based Dynamic Segmentation of Generic Objects in 3D (pdf, project website)
Xiao Lin (Technical University of Catalonia) Josep Casas (Technical University of Catalonia), Montse Pardas (Technical University of Catalonia)
Intrinsic Image Decomposition using Deep Convolutional Network (pdf)
Hyeongseok Son (POSTECH), Seungyong Lee (POSTECH)
Category co-occurrence modeling for large scale scene recognition (pdf)
Xinhang Song (ICT), Shuqiang Jiang (ICT, China Academy of Science), Herranz luis (Institute of Computing Technology, Chinese Academy of Sciences), Kai Zheng (IA of CAS), Kai Zheng (Soochow University)
Semantic Multinomial Representation for Scene Images Using Dynamic Kernel based SVMs (pdf)
Shikha Gupta (IT Mandi, H.P India), Samriddhi Jain (IIT Mandi, H.P India), Veena Thenkanidiyoor (Department of CSE, National Institute of Technology Goa, Ponda, Goa, India), Dileep A.D (IIT Mandi, H.P India)
Scene recognition with CNNs: objects, scales and dataset bias (pdf)
Herranz Luis (Institute of Computing Technology, Chinese Academy of Sciences), Shuqiang Jiang (ICT, China Academy of Science), Li Xiangyang (Institute of Computing Technology, Chinese Academy of Sciences)
Annotation Methodologies for Vision and Language Dataset Creation (pdf)
Gitit Kehat (Brandeis University), James Pustejovsky (Brandeis University)
A Context-Driven Forest-Based Approach to Hierarchical Scene Understanding (pdf)
Zachary Daniels (Rutgers University), Dimitris Metaxas (Rutgers University)
Deep Learned Full-3D Object Completion from Single View (pdf)
Dario Rethage (Technical University of Munich, Germany), Federico Tombari (Technical University of Munich, Germany), Felix Achilles (Technical University of Munich, Germany)
Human Attention in Visual Question Answering: Where Do Humans Choose to Look? (pdf)
Abhishek Das (Virginia Tech), Harsh Agrawal (Virginia Tech), Larry Zitnick (Facebook AI Research), Devi Parikh (Virginia Tech), Dhruv Batra (Virginia Tech)
DISCO: Describing Images Using Scene Contexts and Objects (pdf)
Ifeoma Nwogu (University at Buffalo, SUNY)
Towards Transparent AI Systems: Interpreting Visual Question Answering Models (pdf)
Yash Goyal (Virginia Tech), Akrit Mohapatra (Virginia Tech), Devi Parikh (Virginia Tech), Dhruv Batra (Virginia Tech)
Vanishing point detection with convolutional neural networks (pdf)
Ali Borji (University of Central Florida)