SUNw: Scene Understanding Workshop

Best Poster Awards

Winner Understanding Image Virality (pdf, project page)
Arturo Deza (UCSB), Devi Parikh (Virginia Tech)
Runner-Up Deep filter banks for texture recognition and segmentation (pdf)
Mircea Cimpoi (University Of Oxford), Subhransu Maji (UMass Amherst), Andrea Vedaldi

Accepted Posters

SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite
Shuran Song (Princeton University), Samuel Lichtenberg (Princeton Uinversity), Jianxiong Xiao
Scene Labeling with LSTM Recurrent Neural Networks (pdf)
Wonmin Byeon (TU Kaiserslautern), Thomas Breuel (TU Kaiserslautern), Federico Raue (TU Kaiserslautern), Marcus Liwicki (TU Kaiserslautern)
Vanishing Point Attracts Eye Movements in Scene Free-viewing (pdf, project page)
Ali Borji (UWM), Mengyang Feng (Dalian University Of Technology), Huchuan Lu (Dalian University Of Technology)
PanoContext: A Whole-room 3D Context Model for Panoramic Scene Understanding (pdf, project page)
Yinda Zhang (Princeton University), Shuran Song (Princeton University), Ping Tan (Simon Fraser University), Jianxiong Xiao
Learning Filter-Based Motion Features for Dynamic Scene Analysis (pdf, project page)
Damien Teney (Carnegie Mellon University), Martial Hebert (Carnegie Mellon University)
Improving Human Pose Recognition Accuracy using CRF modeling (pdf, project page)
Vivek Sharma (KU Leuven), Frank Dittrich (KIT), Sule Yayilgan (HIG), Luc Van Gool (KU Leuven And ETH Zürich)
Searching for Objects in 20 Questions (pdf)
Xi Chen (University Of Maryland), He He (University Of Maryland), Larry Davis (University Of Maryland)
Towards Fuzzy Knowledge Based Scene Understanding from RGB-D Images (pdf)
Markus Eich (QUT, Centre For Robotic Vision)
Continuous Factor Graphs for Holistic Scene Understanding (pdf)
Niko Suenderhauf (QUT), Ben Upcroft (QUT), Michael Milford (QUT)
Extending Visual Perception With Haptic Exploration for Improved Scene Understanding (pdf, project page)
Jürgen Leitner (Queensland University Of Technology / Australian Centre For Robotic Vision)
Fast Indoor Structure Analysis of Single RGBD Images (pdf)
Junho Jeon (POSTECH), Daehoon Yoo (POSTECH), Seungyong Lee (POSTECH)
How Good Are Edge Boxes, Really? (pdf)
Sean McMahon (QUT), Niko Suenderhauf (QUT), Ben Upcroft (QUT), Michael Milford (QUT)
Modeling Context Effects on Image Memorability (pdf, project page)
Zoya Bylinskii (MIT), Phillip Isola (MIT), Antonio Torralba (MIT), Aude Oliva (MIT)
How you look at a picture determines if you will remember it (pdf, project page)
Zoya Bylinskii (MIT), Phillip Isola (MIT), Antonio Torralba (MIT), Aude Oliva (MIT)
Learning to Segment Under Various Forms of Weak Supervision (pdf, project page)
Jia Xu (UW-Madison), Alex Schwing (University Of Toronto), Raquel Urtasun (University Of Toronto)
Unconstrained ego-centric videos with eye-tracking data (pdf, project page)
Keng-Teck Ma (Institute For Infocomm Researc), Peilun Dai (Institute For Infocomm Research), Rosary Lim (Institute For Infocomm Research), Liyuan Li (Institute For Infocomm Research), Joo-Hwee Lim (Institute For Infocomm Research)
Video Surveillance Autopilot (pdf)
Leslie Smith (US Naval Research Laboratory), David Aha (US Naval Research Laboratory), David Bonanno (US Naval Research Laboratory), Timothy Doster (US Naval Research Laboratory)
Understanding Crowd Collectivity: A Meta-Tracking Approach (pdf, project page)
Afshin Dehghan (University Of Central Florida), Mahdi Kalayeh (University Of Central Florida)
Object-Level Generative Models for 3D Scene Understanding (pdf)
Ehsan Jahangiri (Johns Hopkins University), Rene Vidal (Johns Hopkins University), Laurent Younes (Johns Hopkins University), Donald Geman (Johns Hopkins University)
Object Detectors Emerge from Training CNNs for Scene Recognition (pdf, project page)
Bolei Zhou (MIT), Aditya Khosla (MIT), Agata Lapedriza (MIT), Aude Oliva (MIT), Antonio Torralba (MIT)
Finding Coherent Motions and Understanding Crowd Scenes: A Diffusion and Clustering-based Approach (pdf)
Weiyao Lin (Shanghai Jiao Tong University), Yang Mi, You-Ping Zhong, Weiyue Wang
Object Scene Flow for Autonomous Vehicles (pdf, project page)
Moritz Menze (Leibniz Universität Hannover), Andreas Geiger (MPI Tübingen)
Mining Semantic Affordances of Visual Object Categories (pdf, project page)
Yu-Wei Chao (University Of Michigan), Zhan Wang (University Of Michigan), Rada Mihalcea (University Of Michigan), Jia Deng (University Of Michigan)
Geometry Driven Semantic Labeling of Indoor Scenes (pdf, full paper)
Salman Khan (UWA), Mohammed Bennamoun (UWA), Ferdous Sohel (UWA), Roberto Togneri (UWA)
Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors (pdf, project page)
LINGQIAO LIU (University Of Adelaide), Chunhua Shen (University Of Adelaide), Lei Wang (University Of Wollongong), Anton Hengel (University Of Adelaide), Chao Wang (University Of Wollongong)
Salient Object Subitizing (pdf, project page)
Jianming Zhang (Boston University), Shugao Ma (Boston University), Mehrnoosh Sameki (Boston University), Stan Sclaroff (Boston University), Margrit Betke (Boston University), Zhe Lin (Adobe), Xiaohui Shen (Adobe), Brian Price (Adobe), Radomir Mech (Adobe)
From Captions to Visual Concepts and Back (pdf, project page)
Hao Fang (University Of Washington), Saurabh Gupta (University Of California, Berkeley), Forrest Iandola (University Of California, Berkeley), Rupesh Srivastava (IDSIA, USI-SUPSI), LI Deng (Microsoft Research), PIotr Dollar (Facebook AI Research), JIanfeng Gao (Microsoft Research), Xiaodong He (Microsoft Research), Margaret Mitchell (Microsoft Research), John Platt (Google), C. Lawrence Zitnick (Microsoft Research), Geoffrey Zweig (Microsoft Research)
Visual Saliency Based on Multiscale Deep Features (pdf, project page)
Guanbin LI (The University Of Hong Kong), Yizhou Yu (The University Of Hong Kong)
3D All The Way: Semantic Segmentation of Urban Scenes From Start to End in 3D (pdf, project page)
Andelo Martinovic (KU Leuven), Jan Knopp (KU Leuven), Hayko Riemenschneider (ETH Zurich), Luc Van Gool (KU Leuven And ETH Zürich)
Deep filter banks for texture recognition and segmentation (pdf)
Mircea Cimpoi (University Of Oxford), Subhransu Maji (UMass Amherst), Andrea Vedaldi
Holistic 3D Scene Understanding from a Single Geo-tagged Image (pdf)
Shenlong Wang (University Of Toronto), Sanja Fidler (University Of Toronto), Raquel Urtasun (University Of Toronto)
Understanding Image Virality (pdf, project page)
Arturo Deza (UCSB), Devi Parikh (Virginia Tech)
Part-based modelling of compound scenes from images
Anton Hengel (University Of Adelaide), Christopher Russel (University College London)
Indoor Scene Structure Analysis for Single Image Depth Estimation (pdf, full paper)
Wei Zhuo (NICTA), Mathieu Salzmann (NICTA), Xuming He (NICTA), Miaomiao Liu (NICTA)
Fully Convolutional Networks for Semantic Segmentation
Jonathan Long (UC Berkeley), Evan Shelhamer (UC Berkeley), Trevor Darrell (UC Berkeley)
Image Parsing with a Wide Range of Classes and Scene-Level Context (pdf, full paper)
Marian George (ETH Zurich)
Weakly Supervised Learning of Objects, Attributes and their Associations (pdf, project page)
Zhiyuan Shi (Queen Mary, Univ. Of London), Yongxin Yang, Timothy Hospedales, Tao Xiang
Multiclass Semantic Video Segmentation with Object-level Active Inference (pdf, project page)
Buyu Liu (ANU/NICTA), Xuming He (NICTA)
DEEP-CARVING: Discovering Visual Attributes by Carving Deep Neural Nets (pdf, full paper)
Sukrit Shankar (University Of Cambridge), Vikas Garg (MIT), Roberto Cipolla (University Of Cambridge)
Crowded Scene Understanding by Deeply Learned Attributes (pdf, project page)
Jing Shao (The Chinese University Of HK), Kai Kang (The Chinese University Of Hong Kong), Chen Change Loy (The Chinese University Of Hong Kong), Xiaogang Wang (The Chinese University Of Hong Kong)
segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection
Yukun Zhu (University Of Toronto), Raquel Urtasun (University Of Toronto), Ruslan Salakhutdinov, Sanja Fidler (University Of Toronto)
Layered RGBD Scene Flow Estimation (pdf)
Deqing Sun (Harvard University), Erik Sudderth (Brown University), Hanspeter Pfister (Harvard University)
Joint Multi-feature Spatial Context for Scene Recognition in the Semantic Manifold (pdf)
Xinhang Song (Institute Of Computing Technology, Chinese Academy Of Sciences), Shuqiang Jiang (Institute Of Computing Technology, Chinese Academy Of Sciences), Luis Herranz (Chinese Academy Of Sciences)
Joint SFM and Detection Cues for Monocular 3D Localization in Road Scenes (pdf)
Shiyu Song (Baidu USA LLC), Manmohan Chandraker (NEC Labs America)
Efficient Convolutional Patch Networks for Scene Understanding (pdf, project page)
Clemens Brust (FSU Jena), Sven Sickert (FSU Jena), Marcel Simon (FSU Jena), Erik Rodner (FSU Jena), Joachim Denzler
Semantic Segmentation in Indoor Scenes from Supervised Object-Background Hypotheses (pdf)
Md. Reza (George Mason University), Jana Kosecka (George Mason University)
Scene Chronology (pdf, project page)
Kevin Matzen (Cornell University), Noah Snavely
Social Saliency Prediction (pdf, project page)
Hyun Soo Park (UPENN), Jianbo Shi (UPENN)
Aligning 3D Models to RGB-D Images of Cluttered Scenes (pdf)
Saurabh Gupta (University Of California, Berkeley), Pablo Arbeláez, Ross Girshick, Jitendra Malik
Learning Coarse-to-Fine Sparselets for Efficient Object Detection and Scene Classification (pdf, full paper)
Gong Cheng (Northwestern Polytechnical U.), Junwei Han, Lei Guo, Tianming Liu
Book2Movie: Aligning Video scenes with Book chapters (pdf, project page)
Makarand Tapaswi (Karlsruhe Institute Of Tech.), Martin Bäuml, Rainer Stiefelhagen
VQA: Visual Question Answering
Stanislaw Antol (Virginia Tech), Aishwarya Agrawal (Virginia Tech), Jiasen Lu (Virginia Tech), Margaret Mitchell (Microsoft Research), Dhruv Batra (Virginia Tech), C. Lawrence Zitnick (Microsoft Research), Devi Parikh (Virginia Tech)
Symbolic Segmentation Using Algorithm Selection and Semantic Feedback (pdf, project page)
Martin Lukac (Nazarbayev University), Kamila Abdiyeva (Nazarbayev University), Michitaka Kameyama (Tohoku University)
Mind's Eye: A Recurrent Visual Representation for Image Caption Generation (pdf)
Xinlei Chen (CMU), C. Lawrence Zitnick (Microsoft Research)
Articulated Motion Models for Scene Understanding (pdf)
Suren Kumar (SUNY At Buffalo), Vikas Dhiman (University Of Michigan), Jason Corso (University At Michigan), Venkat Krovi (SUNY At Buffalo)
Multi-Object Classification and Unsupervised Scene Understanding Using Deep Learning Features and Latent Tree Probabilistic Models (pdf, project page)
Tejaswi Nimmagadda (UC Irvine), Animashree Anandkumar (UC Irvine)
Deep Hierarchical Parsing for Semantic Segmentation (pdf)
Abhishek Sharma (University Of Maryland), David Jacobs (University Of Maryland College Park), Oncel Tuzel (Mitsubishi Electric Research Lab Cambridge)
Image Retrieval using Scene Graphs (pdf)
Justin Johnson (Stanford University), Ranjay Krishna (Stanford University), Michael Stark (Max Planck Institute For Informatics), Li-Jia Li (Snapchat), David Shamma (Yahoo!), Michael Bernstein (Stanford University), Fei-Fei Li (Stanford University)
Learning Scene-Specific Pedestrian Detectors without Real Data (pdf, project page)
Hironori Hattori, Vishnu Naresh Boddeti (Carnegie Mellon University), Kris Kitani, Takeo Kanade
Holistic Scene Understanding via Multiple Structured Hypotheses from Perception Modules
Gordon Christie (Virginia Tech), Ankit Laddha (Carnegie Mellon University), Aishwarya Agrawal (Virginia Tech), Stanislaw Antol (Virginia Tech), Yash Goyal (Virginia Tech), Dhruv Batra (Virginia Tech)
Scene Classification with Semantic Fisher Vectors (pdf, full paper)
Mandar Dixit (UC San Diego), Si Chen (UC San Diego), Dashan Gao (Qualcomm Inc.), Nikhil Rasiwasia (SnapDeal.com), Nuno Vasconcelos (UC San Diego)
Picture: A Probabilistic Programming Language for Scene Perception (pdf)
Tejas Kulkarni (Massachusetts Institute Of Tec), Pushmeet Kohli, Joshua Tenenbaum, Vikash Mansinghka
Material Recognition in the Wild with the Materials in Context Database (pdf, project page)
Sean Bell (Cornell University), Paul Upchurch (Cornell University), Noah Snavely, Kavita Bala (Cornell University)