SUNw: Scene Understanding Workshop

Accepted Posters

Towards Scene Understanding with Detailed 3D Object Representations (pdf)
Muhammad Zeeshan Zia (ETH-Zurich), Michael Stark (Stanford University), Konrad Schindler (ETH-Zurich)
Bayesian inference of indoor scenes using composite object models (pdf)
Luca Del Pero (University of Arizona), Kobus Barnard (University of Arizona)
A Discriminative Model for Learning Semantic and Geometric Interactions in Indoor Scenes (pdf)
Wongun Choi (University of Michigan), Yu-wei Chao (University of Michigan), Caroline Pantofaru (Google), Silvio Savarese (University of Michigan)
Label Ranking Based Semantic Texton Forests for Multi-label Problem (pdf)
Takaaki Fukuta (Yamaha Motor Co., Ltd.), Hironobu Fujiyoshi
RABIT-Model : Unsupervised Scene Understanding via Region and Boundary Integrated Topic Model (pdf)
Kazuhiko Murasaki (NTT), Kyoko Sudo (NTT), Yukinobu Taniguchi (NTT)
Counting Grids: Reconstructing the feature layout from bags by capturing spatial interdependence in image features (pdf)
Alessandro Perina (Microsoft Research), Nebojsa Jojic (Microsoft Research)
Multi-View Background Subtraction for Object Detection (pdf)
Raul Diaz (University of California, Irvine), Sam Hallman, Charless Fowlkes (University of California, Irvine)
Measurability of Crowd Collectiveness in Dynamic Scenes (pdf)
Bolei Zhou (The Chinese University of HK), Xiaoou Tang (The Chinese University of HK), Xiaogang Wang (The Chinese University of HK)
Hierarchical Space Tiling (HST) for scene classification and attribute localization (pdf)
Shuo Wang (Peking University), Jungseock Joo, Yizhou WANG (Peking University), Song-Chun Zhu (UCLA)
Probabilistic Map Localization through Visual Odometry (pdf)
Marcus Brubaker (TTI Chicago), Andreas Geiger (KIT & MPI Tubingen), Raquel Urtasan (Toyota Technological Institute at Chicago)
Scene Text Recognition using Part-based Tree-structured Character Detection (pdf)
Cunzhao Shi (Institute of Automation, CAS), Chunheng Wang, Baihua Xiao, Yang Zhang, Song Gao, Zhong Zhang
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors (pdf)
Joseph Tighe (UNC Chapel Hill), Svetlana Lazebnik (University of Illinois, Urbana Champagne)
A Search-Classify Framework for Cluttered Scene Understanding (pdf)
Liangliang Nan (SIAT), Ke Xie (SIAT), Andrei Sharf (Ben-Gurion University)
Manhattan Junction Catalogue for Spatial Understanding of Indoor Scenes (pdf)
Srikumar Ramalingam (MERL), Jaishanker Pillai (University of Maryland), Arpit Jain (University of Maryland), Yuichi Taguchi (MERL)
Detecting Actions, Poses and Objects with Relational Phraselets (pdf)
Chaitanya Desai (UC-Irvine), Deva Ramanan (UC Irvine)
Blocks that Shout: Distinctive Parts for Scene Classification (pdf)
Mayank Juneja (IIIT-Hyderabad), Andrea Vedaldi (Oxford University), C V Jawahar (IIIT-Hyderabad), Andrew Zisserman (University of Oxford)
Acquiring 3D Indoor Environments with Variability and Repetition (pdf)
Young Min Kim (Stanford University), Niloy Mitra (UCL), Dongming Yan (KAUST), Leonidas Guibas (Stanford University)
FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps (pdf)
Yinda Zhang (NUS), Jianxiong Xiao (MIT), James Hays (Brown University), Ping Tan
Hierarchical Saliency Detection (pdf)
Qiong Yan (CUHK), Li Xu, Jianping Shi, Jiaya Jia
From Perceptual Relations to Scene Gist Recognition (pdf)
Ilan Kadar (Ben-Gurion University), Ohad Ben-Shahar (Ben-Gurion University)
Mesh Based Semantic Modelling for Indoor and Outdoor Scenes (pdf)
Julien Valentin (Oxford Brookes), Sunando Sengupta, jonathan Warrell, Ali Shahrokni, Philip Torr
Stacked Local Predictors for Large-Scale Point Cloud Classification (pdf)
Benjamin Eckart (Carnegie Mellon University), Alonzo Kelly (Carnegie Mellon University)
Expanding Training Sets with Unlabeled Samples by Learned Attributes (pdf)
Jonghyun Choi (University of Maryland), Mohammad Rastegari (University of Maryland), Ali Farhadi (University of Washington), Larry Davis (University of Maryland)
Scene Parsing by Integrating Function, Geometry and Appearance Models (pdf)
Yibiao Zhao (UCLA), Song-Chun Zhu (UCLA)
Localizing 3D Cuboids in Single-view Images (pdf)
Jianxiong Xiao (MIT), Bryan Russell (University of Washington), Antonio Torralba (Massachusetts Institute of Technology)
Beyond Point Clouds: Scene Understanding by Reasoning Geometry and Physics (pdf)
Bo Zheng (The University of Tokyo, Japan), Yibiao Zhao (UCLA), Joey Yu (UCLA), Katsushi Ikeuchi (The University of Tokyo, Japan), Song-Chun Zhu (UCLA)
Latent Pyramidal Regions for Recognizing Scenes (pdf)
Fereshteh Sadeghi (University of Central Florida), Marshall Tappen (University of Central Florida)
Representing Videos using Mid-level Discriminative Patches (pdf)
Arpit Jain (University of Maryland), Abhinav Gupta (Carnegie Mellon University), Mikel Rodriguez (mitre), Larry Davis (University of Maryland)
Graph-Based Discriminative Learning for Location Recognition (pdf)
Song Cao (Cornell University), Noah Snavely
Using humans to build mid-level features (pdf)
Genevieve Patterson (Brown University), Tsung-Yi Lin (University of California at San Diego), James Hays (Brown University)
Modeling 3D indoor scenes with RGBD images
Ruiqi Guo (University of Illinois), Derek Hoiem (University of Illinois)
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
Saurabh Gupta (UC Berkeley), Pablo Arbelaez (UC Berkeley), Jitendra Malik (UC Berkeley)
Semantic Context for Nonparametric Scene Parsing and Scene Classification (pdf)
Gautam Singh (George Mason University), Jana Kosecka (George Mason University)
Improved Geometric Verification for Large Scale Landmark Image Collections (pdf)
Rahul Raguram (UNC Chapel Hill), Joseph Tighe (UNC Chapel Hill), Jan-Michael Frahm (UNC Chapel Hill)
A Linear Approach to Matching Cuboids in RGBD Images (pdf)
Hao Jiang (Boston College), Jianxiong Xiao (MIT)
Undoing the Damage of Dataset Bias (pdf)
Aditya Khosla (MIT), Tinghui Zhou (CMU), Tomasz Malisiewicz (MIT), Alexei Efros (CMU), Antonio Torralba (Massachusetts Institute of Technology)
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection (pdf)
Joseph Lim (MIT), Larry Zitnick (MSR), Piotr Dollar (Microsoft Research)
Bottom-up Segmentation for Top-down Detection (pdf)
Sanja Fidler (TTI-C), Roozbeh Mottaghi (UCLA), Alan Yuille, Raquel Urtasan (Toyota Technological Institute at Chicago)
A Sentence is Worth a Thousand Pixels (pdf)
Sanja Fidler (TTI-C), Abhishek Sharma, Raquel Urtasan (Toyota Technological Institute at Chicago)
3D Object Detection with a Deformable 3D Cuboid Model (pdf)
Sanja Fidler (TTI-C), Sven Dickinson (University of Toronto), Raquel Urtasan (Toyota Technological Institute at Chicago)