SUNw: Scene Understanding Workshop

Best Poster Awards

Bags of Spacetime Energies for Dynamic Scene Recognition (pdf, full paper)
Christoph Feichtenhofer (TU Graz), Axel Pinz (TU Graz), Richard Wildes (York University, Toronto)
Minimal Scene Descriptions from Structure from Motion Models (pdf, project page)
Song Cao (Cornell University), Noah Snavely (Cornell University)

Accepted Posters

Segmentation of Low-Level Motion Features to Infer Occlusion Boundaries and Local Depth Ordering (pdf)
Damien Teney (University Of Bath), Matthew Brown (University Of Bath)
PanoContext: A Whole-room 3D Context Model for Panoramic Scene Understanding (pdf, project page)
Yinda Zhang (Princeton University), Shuran Song (Princeton University), Ping Tan (NUS), Jianxiong Xiao (Princeton University)
High-Resolution 3D Layout from a Single View (pdf, full paper)
Muhammad Zeeshan Zia (ETH-Zurich), Michael Stark (Stanford University), Konrad Schindler (ETH-Zurich)
SUN3D: A Database of Big Spaces Reconstructed using SfM and Object Labels (pdf, project page)
Jianxiong Xiao (Princeton University), Andrew Owens (MIT), Antonio Torralba (MIT)
Tracking Revisited using RGBD Camera: Unified Benchmark and Baselines (pdf, full paper)
Shuran Song (Princeton University), Jianxiong Xiao (Princeton University)
Sliding Shapes for 3D Object Detection in RGB-D Images (pdf, project page)
Shuran Song (Princeton University), Jianxiong Xiao (Princeton University)
Learning Mid-level Attributes for Scene Understanding on Web-images (pdf)
Wonmin Byeon (University Kaiserslautern), Thomas Breuel (University Kaiserslautern)
Introspective Semantic Segmentation (pdf)
Gautam Singh (George Mason University), Jana Kosecka (George Mason University)
Estimating Structure of Rooms from Full-view Image (pdf)
Hanchao Jia (Tottori University), Shigang Li (Tottori University)
Decoding the Spatiotemporal Scene of a Road-Traffic Intersection for Real Time Event Detection (pdf)
Justin Eichel (Miovision Technologies Inc.), Akshaya Mishra (Miovision Technologies Inc.), Nicholas Miller (Miovision Technologies Inc.), Nicholas Jankovic (Miovision Technologies Inc.), Kurtis McBride (Miovision Technologies Inc.)
Semantic Segmentation with Deep Learning (pdf)
Michael Cogswell (Virginia Tech), Dhruv Batra (Virginia Tech)
Automatic spatial and temporal organization of long range video sequences from low level motion features (pdf)
Alberto Quintero Delgado (LE2I - Universite De Bourgogne), Yannick Benezeth (LE2I - Universite De Bourgogne), Desire Sidibe (LE2I - Universite De Bourgogne)
Entrance Detection from Street-View Images (pdf)
Jingchen Liu (Penn. State Univ.), Thommen Korah, Varsha Hedau, Vasu Parameswaran, Radek Grzeszczuk, Yanxi Liu
Combining Orientational Pooling Features for Scene Recognition (pdf, full paper)
Lingxi Xie (Tsinghua University), Jingdong Wang (Microsoft Research), Baining Guo (Microsoft Research), Bo Zhang (Tsinghua University), Qi Tian (University Of Texas At San Antonio)
Looking Beyond the Visible Scene (pdf, project page)
Aditya Khosla (MIT), Byoungkwon An (MIT), Joseph Lim (MIT), Antonio Torralba (MIT)
Dense Semantic Image Segmentation with Objects and Attributes (pdf, full paper)
Shuai Zheng (University Of Oxford), Ming-Ming Cheng (University Of Oxford), Jonathan Warrell (Oxford Brookes University), Paul Sturgess (Oxford Brookes University), Vibhav Vineet (Oxford Brookes University), Carsten Rother (TU Dresden), Philip Torr (University Of Oxford)
Multi-target tracking with context from interaction feature strings (pdf, full paper)
Laura Leal-Taixe (ETH Zurich), Michele Fenzi (Leibniz University Hannover), Alina Kuznetsova (Leibniz University Hannover), Bodo Rosenhahn (Leibniz University Hannover), Silvio Savarese (Stanford University)
Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition (pdf, project page)
Cong Yao (Huazhong Univ. Of Sci.&Tech.), Xiang Bai, Baoguang Shi, Wenyu Liu
COSTA: Co-Occurrence Statistics for Zero-Shot Classification (pdf, full paper)
Thomas Mensink (University Of Amsterdam), Efstratios Gavves, Cees Snoek
Bags of Spacetime Energies for Dynamic Scene Recognition (pdf, full paper)
Christoph Feichtenhofer (TU Graz), Axel Pinz (TU Graz), Richard Wildes (York University, Toronto)
Synergistic Clustering of Image and Segment Descriptors for Unsupervised Scene Understanding (pdf, project page)
Daniel Steinberg (NICTA), Oscar Pizarro (ACFR), Stefan Williams (ACFR)
ImageSpirit: Verbal Guided Image Parsing (pdf, full paper)
Ming-Ming Cheng (University Of Oxford), Shuai Zheng (University Of Oxford), Wen-Yan Lin (Oxford Brookes University), Vibhav Vineet (Oxford Brookes University), Paul Sturgess (Oxford Brookes University), Nigel Crook (Oxford Brookes University), Niloy Mitra ( University College London), Philip Torr (University Of Oxford)
Reasoning about Photo Collections using Outdoor Illumination Models (pdf)
Daniel Cabrini Hauagge (Cornell University), Kavita Bala (Cornell University), Noah Snavely (Cornell University), Scott Wehrwein (cornell University), Paul Upchurch (cornell University)
Exemplar part-based 2D-3D alignment with discriminative visual elements (pdf, project page)
Mathieu Aubry (INRIA), Daniel Maturana, Alexei Efros, Bryan Russell, Josef Sivic
Understanding Stationary Groups in Crowded Scenes (pdf)
Shuai Yi (CUHK), Xiaogang Wang, Cewu Lu, Jiaya Jia
Crowd Scene Understanding from Group Profiling (pdf, project page)
Jing Shao (The Chinese University Of HK), Chen Loy, Xiaogang Wang
Reconstructing PASCAL VOC (pdf, project page)
Sara Vicente (Anthropics Technology), Joao Carreira (UC Berkeley), Lourdes Agapito (UCL), Jorge Batista (ISR-Coimbra)
The Role of Context for Object Detection and Semantic Segmentation in the Wild (pdf, full paper)
Roozbeh Mottaghi (Stanford University), Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, Alan Yuille
Pyramid Coding for Functional Scene Element Recognition in Video Scenes (pdf, full paper)
Eran Swears (Kitware Inc.), Anthony Hoogs (Kitware), Kim Boyer (RPI)
Context Driven Scene Parsing with Attention to Rare Classes (pdf)
Jimei Yang (UC Merced), Brian Price (Adobe Research), Scott Cohen (Adobe Research), Ming-Hsuan Yang (UC Merced)
Learning People Detectors for Tracking in Crowded Scenes (pdf, project page)
Siyu Tang (MPII), Mykhaylo Andriluka, Anton Milan, Konrad Schindler, Stefan Roth, Bernt Schiele
Piecewise Rigid 3D Scene Flow (pdf, full paper)
Christoph Vogel (ETH Zurich), Konrad Schindler, Stefan Roth
Neural Decision Forests for Semantic Image Labelling (pdf, full paper)
Samuel Rota Bulo' (FBK), Peter Kontschieder (Microsoft Research)
Efficient 3D Scene Labelling Using Fields of Trees (pdf)
Olaf Kahler (University Of Oxford), David Murray (University Of Oxford), Ian Reid (University Of Adelaide)
A high-resolution neural portrait of natural scene processing (pdf)
Pavan Ramkumar (Northwestern University), Bruce Hansen (Colgate University), Alexa Lee (Colgate University), Stewart Lanphier (Colgate University), Sebastian Pannasch (Dresden University Of Technology), Lester Loschky (Kansas State University)
3D Object Modeling by Sharing Visual Attributes across Poses and Scales (pdf)
Liliana Lo Presti (University Of Palermo), Marco La Cascia (University Of Palermo)
Scalable Multitask Representation Learning for Scene Classification (pdf, project page)
Maksim Lapin (MPI Informatics), Bernt Schiele, Matthias Hein (Saarland University)
Minimal Scene Descriptions from Structure from Motion Models (pdf, project page)
Song Cao (Cornell University), Noah Snavely (Cornell University)
Socially-aware Large-scale Crowd Forecasting (pdf, full paper)
Alexandre Alahi (Stanford), Vignesh Ramanathan (Stanford), Fei-Fei Li (Stanford)
Tell Me What You See and I will Show You Where It Is (pdf, project page)
Jia Xu (UW-Madison), Alexander Schwing (University Of Toronto), Raquel Urtasun (University Of Toronto)
Single-View 3D Scene Parsing by Attributed Grammar (pdf)
Xiaobai Liu, Yibiao Zhao (, Song-Chun Zhu (UCLA)
Visual Persuasion: Inferring Communicative Intents of Images (pdf, project page)
Jungseock Joo (UCLA), Weixin Li (UCLA), Francis Steen (UCLA), Song-Chun Zhu (UCLA)
Incorporating Scene Context and Object Layout into Appearance Modeling (pdf, full paper)
Hamid Izadinia (University Of Washington), Fereshteh Sadeghi, Ali Farhadi
Active Learning for Structured Probabilistic Models (pdf)
QING SUN (Virginia Tech), Ankit Laddha (Virginia Tech), Dhruv Batra (Virginia Tech)
Improving semi-supervised neural networks for scene understanding by learning the neighborhood graph (pdf)
Jiwoong Im (University Of Guelph), Graham Taylor (University Of Guelph)
Object Proposals using Nonparametric Bounding Box Transfer (pdf)
Neelima Chavali (Virginia Tech), Dhruv Batra (Virginia Tech)
Scene Collaging: Analysis and Synthesis of Natural Images with Semantic Layers (pdf, project page)
Phillip Isola (MIT), Ce Liu (Microsoft Research)
What are you talking about? Text-to-Image Coreference (pdf, full paper)
Chen Kong (Tsinghua University), Dahua Lin (TTI-Chicago), Mohit Bansal (TTI-C), Raquel Urtasun (University Of Toronto), Sanja Fidler (University Of Toronto)
Analysis by Synthesis: 3D Object Recognition by Object Reconstruction (pdf, full paper)
Moshen Hejrati (UC Irvine), Deva Ramanan (University Of California, Irvine)