Proceedings of the British Machine Vision Conference 2017

Editors: T.K. Kim, S. Zafeiriou, G. Brostow, K. Mikolajczyk BMVA Press, September 2017, ISBN 1-901725-60-X

Tutorials 1

Probabilistic and Deep Models for 3D Reconstruction Andreas Geiger (Max Planck Institute)

Intro to Reinforcement Learning Shimon Whiteson (University of Oxford)

Tutorials 2

Deep Learning for 3D Localization Vincent Lepetit (University of Bordeaux)

Reconstruction of Dynamic Scenes from Monocular Video Lourdes Agapito (University College London)

Spotlights 1

Semantics-Preserving Locality Embedding for Zero-Shot Learning Shih-Yen Tao, Yi-Ren Yeh and Yu-Chiang Frank Wang

Hyperspectral CNN Classification with Limited Training Samples Lloyd Windrim, Rishi Ramakrishnan, Arman Melkumyan and Richard Murphy

Which is the better inpainted image? Learning without subjective annotation Mariko Isogawa, Dan Mikami, Kosuke Takahashi and Hideaki Kimata

Spatio-Temporal Consistency to Detect and Segment Carried Objects Farnoosh Ghadiri, Robert Bergevin and Guillaume-Alexandre Bilodeau

Improved Image Segmentation via Cost Minimization of Multiple Hypotheses Marc Bosch Bosch, Christopher Gifford, Austin Dress, Clare Lau and Jeffrey Skibo

Face Parsing via Recurrent Propagation Sifei Liu, Jianping Shi, Liang Ji and Ming-Hsuan Yang

Accurate Camera Registration in Urban Environments Using High-Level Feature Matching Anil Armagan, Martin Hirzer, Peter Roth and Vincent Lepetit

The Devil is in the Decoder Zbigniew Wojna, Jasper Uijlings, Sergio Guadarrama, Nathan Silberman, Liang-Chieh Chen, Alireza Fathi and Vittorio Ferrari

Virtual to Real Reinforcement Learning for Autonomous Driving Xinlei Pan, Yurong You, Ziyan Wang and Cewu Lu

Real-Time Salient Closed Boundary Tracking using Perceptual Grouping and Shape Priors Xuebin Qin, Shida He, Zichen Zhang, Masood Dehghan and Martin Jagersand

Orals 1 - Pose Estimation

Kinematic-Layout-aware Random Forests for Depth-based Action Recognition Seungryul Baek, Zhiyuan Shi, Masato Kawade and Tae-Kyun Kim

Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors Matthew Trumble, Andrew Gilbert, Charles Malleson, Adrian Hilton and John Collomosse

Indirect deep structured learning for 3D human body shape and pose prediction Vince Tan, Ignas Budvytis and Roberto Cipolla

Real-time Visual-Inertial Odometry for Event Cameras using Keyframe-based Nonlinear Optimization Henri Rebecq, Timo Horstschaefer and Davide Scaramuzza

Keynote 1

Visual Reconstruction and Image-Based Rendering Richard Szeliski (Facebook)

Posters 1

Weakly Supervised Semantic Segmentation Based on Co-segmentation Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen and Ian Reid

Semantic Segmentation with Reverse Attention Qin Huang, Chihao Wu, Chunyang Xia, Ye Wang and C.-C. Jay Kuo

Double Expansion for Optimization of Multilabel Energies Yelena Gorelick, Zhengqin Li and Olga Veksler

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation Arslan Chaudhry, Puneet Kumar Dokania and Philip Torr

Adapting Models to Signal Degradation using Distillation Jong-Chyi Su and Subhransu Maji

Localizing Actions from Video Labels and Pseudo-Annotations Pascal Mettes, Cees Snoek and Shih-Fu Chang

Introduction to Coherent Depth Fields for Dense Monocular Surface Recovery Vladislav Golyanik, Torben Fetzer and Didier Stricker

Real-time Factored ConvNets: Extracting the X Factor in Human Parsing James Charles, Ignas Budvytis and Roberto Cipolla

Holistic, Instance-level Human Parsing Qizhu Li, Anurag Arnab and Philip Torr

CT from Motion: Volumetric Capture of Moving Shapes using X-rays Julien Pansiot and Edmond Boyer

Concise Radiometric Calibration Using The Power of Ranking Han Gong, Graham Finlayson and Maryam Darrodi

Scale Exploiting Minimal Solvers for Relative Pose with Calibrated Cameras Stephan Liwicki and Christopher Zach

Multiple Instance Curriculum Learning for Weakly Supervised Object Detection Siyang Li, Xiangxin Zhu, Qin Huang, Hao Xu and C.-C. Jay Kuo

Fast Feature Fool: A data independent approach to universal adversarial perturbations Konda Reddy Reddy, Utsav Garg and Venkatesh Babu Radhakrishnan

3D color charts for camera spectral sensitivity estimation Rada Deeb, Damien Muselet, Mathieu Hebert, Alain Tremeau and Joost van de Weijer

Guided Robust Matte-Model Fitting for Accelerating Multi-light Reflectance Processing Techniques Ruggero Pintus, Andrea Giachetti, Gianni Pintore and Enrico Gobbetti

Fast Event-based Corner Detection Elias Mueggler, Chiara Bartolozzi and Davide Scaramuzza

PCN: Part and Context Information for Pedestrian Detection with CNNs Shiguang Wang

Adaptive Local Contrast Normalization for Robust Object Detection and Pose Estimation Mahdi Rad, Vincent Lepetit and Peter Roth

Object-Extent Pooling for Weakly Supervised Single-Shot Localization Amogh Gudi, Nicolai van Rosmalen, Marco Loog and Jan van Gemert

Transformed Anti-Sparse Hashing Zhangyang Wang, Ji Liu, Shuai Huang, Xinchao Wang and Shiyu Chang

Deeply Supervised 3D Recurrent FCN for Salient Object Detection in Videos Trung-Nghia Le and Akihiro Sugimoto

Robust Dense Depth Maps Generations from Sparse DVS Stereos Dongqing Zou, Feng Shi, Weiheng Liu, Jia Li, Qiang Wang, Paul-K.J. Park and Hyunsurk Eric Ryu

Adaptive Temporal Pooling for Object Detection using Dynamic Vision Sensor Jia Li, Feng Shi, Weiheng Liu, Dongqing Zou, Qiang Wang, Paul-K.J. Park and Hyunsurk Eric Ryu

High-Resolution Stereo Matching based on Sampled Photoconsistency Computation Chloe Legendre, Konstantinos Batsos and Philippos Mordohai

Generative OpenMax for Multi-Class Open Set Classification Zongyuan Ge, Sergey Demyanov and Rahil Garnavi

ANSAC: Adaptive Non-Minimal Sample and Consensus Victor Fragoso, Christopher Sweeney, Pradeep Sen and Matthew Turk

Color Restoration of Underwater Images Dana Menaker, Tali Treibitz and Shai Avidan

Fine-Grained Image Retrieval: the Text/Sketch Input Dilemma Jifei Song, Yi-zhe Song, Tony Xiang and Timothy Hospedales

Cross-domain Generative Learning for Fine-Grained Sketch-Based Image Retrieval Kaiyue Pang, Yi-zhe Song, Tony Xiang and Timothy Hospedales

Epipolar Plane Diffusion: An Efficient Approach for Light Field Editing Oriel Frigo

Group Cost-sensitive Boosting with Multi-scale Decorrelated Filters for Pedestrian Detection Chengju Zhou, Meiqing Wu and SiewKei Lam

Moving Object Segmentation in Jittery Videos by Stabilizing Trajectories Modeled in Kendall's Shape Space Geethu Jacob and Sukhendu Das

Urban Image Stitching using Planar Perspective Guidance Joo Ho Ho, Seung-Hwan Baek and Min H. Kim

Detecting Parts for Action Localization Nicolas Chesneau, Gregory Rogez, Karteek Alahari and Cordelia Schmid

Cascaded Boundary Regression for Temporal Action Detection Jiyang Gao, Zhenheng Yang and Ram Nevatia

Confidence and Diversity for Active Selection of Feedback in Image Retrieval Bhavin Modi and Adriana Kovashka

Shape Generation using Spatially Partitioned Point Clouds Matheus Gadelha, Subhransu Maji and Rui Wang

Person Re-Identification by Localizing Discriminative Regions Tanzila Rahman, Mrigank Rochan and Yang Wang

Adapting Object Detectors from Images to Weakly Labeled Videos Omit Chanda, Eu Wern Teh, Mrigank Rochan, Zhenyu Guo and Yang Wang

Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding Alex Kendall, Vijay Badrinarayanan and Roberto Cipolla

DepthComp: Real-time Depth Image Completion Based on Prior Semantic Scene Segmentation Amir Atapour Atapour and Toby Breckon

DEEP eye contact detector: Robust eye contact bid detection using convolutional neural network Yu Mitsuzumi, Atsushi Nakazawa and Toyoaki Nishida

BiSeg: Simultaneous Instance Segmentation and Semantic Segmentation with Fully Convolutional Networks Viet Pham, Satoshi Ito and Tatsuo Kozakaya

Salient Object Detection using a Context-Aware Refinement Network Md Amirul Amirul, Mahmoud Kalash, Mrigank Rochan, Neil Bruce and Yang Wang

Visual Odometry with Drift-Free Rotation Estimation Using Indoor Scene Regularities Pyojin Kim, Brian Coltin and Hyounjin Kim

One For All: Adaptive Learning-based Temporal Tracker for 3D Head Shape Models David Joseph Joseph, Federico Tombari and Nassir Navab

Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition Chu Wang, Marcello Pelillo and Kaleem Siddiqi

A Generalised Formulation for Collaborative Representation of Image Patches (GP-CRC) Tapabrata Chakraborti, Brendan McCane, Steven Mills and Umapada Pal

DeepShoe: A Multi-Task View-Invariant CNN for Street-to-Shop Shoe Retrieval Huijing Zhan, boxin shi and ALEX KOT

Weakly Supervised Saliency Detection with A Category-Driven Map Generator Kuang-Jui Hsu, Yen-Yu Lin and Yung-Yu Chuang

Saliency Detection by Compactness Diffusion Qi Zheng, Peng Zhang and Xinge You

Weakly-supervised Learning of Mid-level Features for Pedestrian Attribute Recognition and Localization Yang Zhou, Kai Yu, Biao Leng, zhang Zhang, Dangwei Li and Kaiqi Huang

AST-Net: An Attribute-based Siamese Temporal Network for Real-Time Emotion Recognition Shu-Hui Wang and Chiou-Ting Hsu

Combined Internal and External Category-Specific Image Denoising Saeed Anwar, Cong Huynh and Fatih Porikli

Temporal Perceptive Network for Skeleton-Based Action Recognition Yueyu Hu, Chunhui Liu, Yanghao Li and Jiaying Liu

Detecting Semantic Parts on Partially Occluded Objects Jianyu Wang, Zhishuai Zhang, Cihang Xie, Jun Zhu, Lingxi Xie and Alan Yuille

Place Recognition in Semi-Dense Maps Yawei Ye, Titus Cieslewski, Antonio Loquercio and Davide Scaramuzza

Image Completion with Intrinsic Reflectance Guidance Soomin Kim, Taeyoung Kim, Min H. Kim and Sung-Eui Yoon

Enhancement of SSD by concatenating feature maps for object detection Jisoo Jeong, Hyojin Park and Nojun Kwak

Colour Constancy: Biologically-inspired Contrast Variant Pooling Mechanism Arash Akbarinia, Raquel Gil Rodríguez and C. Alejandro Parraga

Superpixel-based semantic segmentation trained by statistical process control Hyojin Park, Jisoo Jeong, Youngjoon Yoo and Nojun Kwak

Robust Pixel-wise Dehazing Algorithm based on Advanced Haze-Relevant Features Guisik Kim and Junseok Kwon

General Deep Image Completion with Lightweight Conditional Generative Adversarial Networks Ching-Wei Tseng, Hung Jin Lin and Shang-Hong Lai

Augmented Reality meets Deep Learning Hassan Abu Abu, Siva Karthik Mustikovela, Lars Mescheder, Andreas Geiger and Carsten Rother

Improved IR-Colorization using Adversarial Training and Estuary Networks Matthias Limmer and Hendrik Lensch

Realtime Novel View Synthesis with Eigen-Texture Regression Yuta Nakashima, Fumio Okura, Norihiko Kawai, ryosuke Kimura, Hiroshi Kawasaki, Katsushi Ikeuchi and Ambrosio Blanco

Human Action Recognition Using A Multi-Modal Hybrid Deep Learning Model Hany El-Ghaish, Mohamed Hussein and Amin Shoukry

Probabilistic Image Colorization Amelie Royer, Alexander Kolesnikov and Christoph Lampert

Iterated Lifting for Robust Cost Optimization Christopher Zach and Guillaume Bourmaud

Orals 2 - Scene Understanding

Slanted Stixels: Representing San Francisco's Steepest Streets Daniel Hernandez-Juarez, Lukas Schneider, Antonio Espinosa, Juan Moure, David Vazquez, Antonio López, Uwe Franke and Marc Pollefeys

Deformable Part-based Fully Convolutional Network for Object Detection Taylor Mordan, Nicolas Thome, Gilles Henaff and Matthieu Cord

Multiple Instance Visual-Semantic Embedding Zhou Ren, Hailin Jin, Zhe Lin, Chen Fang and Alan Yuille

Thinking Outside the Box: Spatial Anticipation of Semantic Categories Martin Garbade and Juergen Gall

Orals 3 - Action Recognition

Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery Rui Hou, Rahul Sukthankar and Mubarak Shah

RED: Reinforced Encoder-Decoder Networks for Action Anticipation Jiyang Gao, Zhenheng Yang and Ram Nevatia

End-to-End, Single-Stream Temporal Action Detection in Untrimmed Videos Shyamal Buch, Victor Escorcia, Bernard Ghanem and Juan Carlos Niebles

Recognizing and Curating Photo Albums via Event-Specific Image Importance Yufei Wang, Zhe Lin, Xiaohui Shen, Radomir Mech, Gavin Miller and Garrison Cottrell

Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation Zhenheng Yang, Jiyang Gao and Ram Nevatia

Spotlights 2

Video Segmentation with Background Motion Models Scott Wehrwein and Richard Szeliski

Orientation-boosted Voxel Nets for 3D Object Recognition Nima Sedaghat, Mohammadreza Zolfaghari, Ehsan Amiri and Thomas Brox

Semantic 3D Reconstruction with Finite Element Bases Audrey Richard, Christoph Vogel, Maros Blaha, Thomas Pock and Konrad Schindler

SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettes Olivia Wiles and Andrew Zisserman

A Differential Approach to Shape from Polarization Roberto Mecca, Fotios Logothetis and Roberto Cipolla

Fast dense feature extraction with convolutional neural networks that have pooling or striding layers Christian Bailer, tewodros Habtegebrial, Kiran Varanasi and Didier Stricker

Local Visual Microphones: Improved Sound Extraction from Silent Video Mohammad Amin Amin, Mohammad Amin Shabani and Laleh Samadfam

Unsupervised Deep Generative Hashing Yuming Shen, li Liu and Ling Shao

Sampled Image Tagging and Retrieval Methods on User Generated Content Karl Ni, Kyle Zaragoza, Alexander Gude, Yonas Tesfaye, Carmen Carrano, Charles Foster and Barry Chen

Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking James Tompkin, Kwang In Kim, Hanspeter Pfister and Christian Theobalt

Orals 4 - Face Analysis

Now You See Me: Deep Face Hallucination for Unviewed Sketches Conghui Hu, Da Li, Yi-zhe Song and Timothy Hospedales

From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script Arsha Nagrani and Andrew Zisserman

Quantifying Facial Age by Posterior of Age Comparisons Yunxuan Zhang, Li Liu, Cheng Li and Chen-Change Loy

You said that? Joon Son Son, Amir Jamaludin and Andrew Zisserman

Keynote 2

Visipedia - A universal visual expert Pietro Perona (California Institute of Technology)

Posters 2

Reflectance and Shape Estimation with a Light Field Camera under Natural Illumination Trung Ngo, Hajime Nagahara, Ko Nishino, Rin-ichiro Taniguchi and Yasushi Yagi

GeneGAN: Learning Object Transfiguration and Object Subspace from Unpaired Data Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He and Weiran He

PixColor: Pixel Recursive Colorization Sergio Guadarrama, Ryan Dahl, David Bieber, Jonathon Shlens, Mohammad Norouzi and Kevin Murphy

Depth Estimation and Blur Removal from a Single Out-of-focus Image Saeed Anwar, Zeeshan Hayder and Fatih Porikli

Exploring the structure of a real-time, arbitrary neural artistic stylization network Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin and Jonathon Shlens

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization Frederick Tung, Srikanth Muralidharan and Greg Mori

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation Paul Voigtlaender and Bastian Leibe

Improved Bilinear Pooling with CNNs Tsung-Yu Lin and Subhransu Maji

Video to Text Summary: Joint Video Summarization and Captioning with Recurrent Neural Networks Bor-Chun Chen, Yan-Ying Chen and Francine Chen

A Recurrent Variational Autoencoder for Human Motion Synthesis Ikhsanul Habibie, Daniel Holden, Jonathan Schwarz, Joe Yearsley and Taku Komura

A deep learning pipeline for semantic facade segmentation Radwa Fathalla and George Vogiatzis

Deep Reinforcement Learning Attention Selection For Person Re-Identification XU LAN, HangXiao Wang, Shaogang Gong and Xiatian Zhu

Case-Based Histopathological Malignancy Diagnosis using Convolutional Neural Networks Qicheng Lao and Thomas Fevens

Labelless Scene Classification with Semantic Matching Meng Ye and Yuhong Guo

Patch-based Interferometric Phase Estimation via Mixture of Gaussian Density Modelling & Non-local Averaging in the Complex Domain Joshin Krishnan and José Bioucas-Dias

Feature Sequence Representation Via Slow Feature Analysis For Action Classification Takumi Kobayashi

A Convolutional Temporal Encoder for Video Caption Generation Qingle Huang and Zicheng Liao

Marginalized CNN: Learning Deep Invariant Representations Jian ZHAO, Jianshu Li, Fang Zhao, Xuecheng Nie, Yunpeng Chen, Shuicheng Yan and Jiashi Feng

Correlation Hashing Network for Efficient Cross-Modal Retrieval Yue Cao, Mingsheng Long and Jianmin Wang

Sunrise or Sunset: Selective Comparison Learning for Subtle Attribute Recognition Hong-Yu Zhou, Bin-Bin Gao and Jianxin Wu

BIM: Ball Intersection Multi Template Matching Bat El El

Visual Textbook Network: Watch Carefully before Answering Visual Questions Difei Gao, Ruiping Wang, Shiguang Shan and Xilin Chen

Key Person Aided Re-identification in Partially Ordered Pedestrian Set Chen Chen, Min Cao and Silong Peng

Learning confidence measures in the wild Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Alessio Tonioni and Luigi Di Stefano

Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model M. Saquib Saquib, Arne Schumann, Yan Wang and Rainer Stiefelhagen

Divide and Fuse: A Re-ranking Approach for Person Re-identification Rui Yu, Zhichao Zhou, Song Bai and Xiang Bai

Joint Optimization of Coded Illumination and Grayscale Conversion for One-Shot Raw Material Classification Chao Wang and Takahiro Okabe

Hand Pose Learning: Combining Deep Learning and Hierarchical Refinement for 3D Hand Pose Estimation Min-Yu Wu, Pai-Wen Ting and Li-Chen Fu

Learning Cross-scale Correspondence and Patch-based Synthesis for Reference-based Super-Resolution Haitian Zheng, Mengqi Ji, Lei Han, Ziwei Xu, Haoqian Wang, Yebin Liu and Lu Fang

Anomaly Detection using a Convolutional Winner-Take-All Autoencoder Hanh Tran and David Hogg

A Parallel Architecture for High Frame Rate Stereo using Semi-Global Matching Akshay Jain, Alexander Fell and Saket Anand

Accelerating Computation of Exemplar-SVM by Binary Approximation based on Matrix Decomposition Takato Kurokawa, Yuji Yamauchi, Mitsuru Ambai, Takayoshi YAMASHITA and Hironobu Fujiyoshi

Sparse and Noisy to Dense Depth Map Upsampling Based on Mesh and Colour Consistency Hanshin Lim and Junseok Lee

Efficient 3D Tracking in Urban Environments with Semantic Segmentation Martin Hirzer, Peter Roth and Vincent Lepetit

Class Weighted Convolutional Features for Visual Instance Search Albert Jimenez, Jose Alvarez and Xavier Giro-i-Nieto

Dynamic Steerable Blocks in Deep Residual Networks Jörn-Henrik Jacobsen, Bert De Brabandere and Arnold Smeulders

Towards Complete Scene Reconstruction from Single-View Depth and Human Motion Sam Fowler, Hansung Kim and Adrian Hilton

Flow Based Video Super-Resolution with Spatio-temporal Patch Similarity Joan Duran and Antoni Buades

BV-CNNs: Binary Volumetric Convolutional Networks for 3D Object Recognition Chao Ma, Wei An, Yinjie Lei and Yulan Guo

Combining Edge Images and Depth Maps for Robust Visual Odometry Fabian Schenk and Friedrich Fraundorfer

Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement Daniel Maurer, Michael Stoll and Andres Bruhn

Large-scale Continual Road Inspection: Visual Infrastructure Assessment in the Wild Ke Ma, Minh Hoai and Dimitris Samaras

Correlation Filter Tracking: Beyond an Open-loop System Qingyong Hu, Yulan Guo, Yunjin Chen, Jingjing Xiao and Wei An

Photorealistic Style Transfer with Screened Poisson Equation Roey Mechrez, Eli Shechtman and Lihi Zelnik-Manor

Probabilistic Spatial Regression using a Deep Fully Convolutional Neural Network S M MASUDUR RAHMAN AL M, Karen Knapp and Greg Slabaugh

Lip Reading in Profile Joon Son Son and Andrew Zisserman

Adversarial Robustness: Softmax versus Openmax Andras Rozsa, Manuel Gunther and Terrance Boult

Generative 3D Hand Tracking with Spatially Constrained Pose Sampling Konstantinos Roditakis, Alexandros Makris and Antonis Argyros

Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction Robert Maier, Raphael Schaller and Daniel Cremers

Long Range Stereo from Synchronized Monocular Optical Flow Streamss Darius Burschka

Learning temporal structures for human activity recognition Tiantian Xu and Edward Wong

END-TO-END MULTI-VIEW LIPREADING Stavros Petridis, Yujiang Wang, Zuwei Li and Maja Pantic

Supervised Scale-Regularized Linear Convolutionary Filters Marco Loog and Francois Lauze

Sparse Deep Feature Representation for Object Detection from Wearable Cameras Quanfu Fan and Richard Chen

Human Action Segmentation using 3D Fully Convolutional Network Pei Yu, Jiang Wang and Ying Wu

Deep fisher faces Harald Hanselmann, Shen Yan and Hermann Ney

Improving target tracking robustness with Bayesian data fusion Yevgeniy Reznichenko and Henry Medeiros

One-Shot Learning for Semantic Segmentation Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa and Byron Boots

Efficent Traffic-Sign Recognition with Scale-aware CNN Yuchen Yang, Shuo Liu, Wei Ma, Qiuyuan Wang and Zheng Liu

Plane-Aided Visual-Inertial Odometry for Pose Estimation of a 3D Camera based Indoor Blind Navigation System He Zhang and cang Ye

Dissecting scale from pose estimation in visual odometry Rong yuan, Hongyi Fan and Benjamin Kimia

Automatic Image transformation for inducing affect MOhsen Ali and Afsheen Rafaqat

Subpixel Semantic Flow Berk Sevilmis and Benjamin Kimia

Light Cascaded Convolutional Neural Networks for Accurate Player Detection Keyu Lu, Jianhui Chen, James Little and Hangen He

Exploiting Protrusion Cues for Fast and Effective Shape Modeling via Ellipses Alex Wong, Alan Yuille and Brian Taylor

A CNN-Based Approach for Automatic License Plate Recognition in the Wild Meng Dong, Dongliang He, Chong Luo, Dong Liu and Wenjun Zeng

Multi-Region Ensemble Convolutional Neural Network for High Accuracy Age Estimation Yiliang Chen, zichang Tan, Alex Po Leung, Jun Wan and Jianguo Zhang

Primitive-based Surface Regularization for Urban 3D Reconstruction Thomas Holzmann, Martin Oswald, Marc Pollefeys, Friedrich Fraundorfer and Horst Bischof

Cross-modal Retrieval via Memory Network Ge Song and Xiaoyang Tan

A Compact Parametric Solution to Depth Sensor Calibration Andrew Spek and Tom Drummond

Pansharpening via Locality-Constrained Sparse Representation Songze Tang, Nan zhou and Liang Xiao

Residual Conv-Deconv Grid Network for Semantic Segmentation Damien Fourure, Rémi Emonet, Elisa Fromont, Damien Muselet, Alain Tremeau and Christian Wolf

Deep GrabCut for Object Selection Ning Xu, Brian Price, Scott Cohen, Jimei Yang and Thomas Huang

Solar Power Plant Detection on Multi-Spectral Satellite Imagery using Weakly-Supervised CNN with Feedback Features and m-PCNN Fusion Nevrez Imamoglu, Motoki Kimura, Hiroki Miyamoto, Aito Fujita and Ryosuke Nakamura

Orals 5 - Matching

Multiple-Kernel Local-Patch Descriptor Arun Mukundan, Giorgos Tolias and Ondrej Chum

AutoScaler: Scale-Attention Networks for Visual Correspondence Shenlong Wang, Linjie Luo, Ning Zhang and Jia Li

Cross-View GAN Based Vehicle Generation for Re-identification Yi Zhou and Ling Shao

Efficient Video Summarization Using Principal Person Appearance for Video-Based Person Re-Identification Seongro Yoon, Furqan Khan and Francois Bremond

Fine-Grained Forensic Matching Bailey Kong, James Supancic, Deva Ramanan and Charless Fowlkes

Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization Yinpeng Dong, Jianguo Li and Renkun Ni

Orals 6 - Segmentation

Weakly Supervised Semantic Segmentation Based on Co-segmentation Tong Shen, Guosheng Lin, Lingqiao Liu, Chunhua Shen and Ian Reid

Semantic Segmentation with Reverse Attention Qin Huang, Chihao Wu, Chunyang Xia, Ye Wang and C.-C. Jay Kuo

Double Expansion for Optimization of Multilabel Energies Yelena Gorelick, Zhengqin Li and Olga Veksler

Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation Arslan Chaudhry, Puneet Kumar Dokania and Philip Torr

Online Adaptation of Convolutional Neural Networks for Video Object Segmentation Paul Voigtlaender and Bastian Leibe

Improved Bilinear Pooling with CNNs Tsung-Yu Lin and Subhransu Maji

Orals 7 - Enhancement

Reflectance and Shape Estimation with a Light Field Camera under Natural Illumination Trung Ngo, Hajime Nagahara, Ko Nishino, Rin-ichiro Taniguchi and Yasushi Yagi

GeneGAN: Learning Object Transfiguration and Object Subspace from Unpaired Data Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He and Weiran He

PixColor: Pixel Recursive Colorization Sergio Guadarrama, Ryan Dahl, David Bieber, Jonathon Shlens, Mohammad Norouzi and Kevin Murphy

Depth Estimation and Blur Removal from a Single Out-of-focus Image Saeed Anwar, Zeeshan Hayder and Fatih Porikli

Exploring the structure of a real-time, arbitrary neural artistic stylization network Golnaz Ghiasi, Honglak Lee, Manjunath Kudlur, Vincent Dumoulin and Jonathon Shlens

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization Frederick Tung, Srikanth Muralidharan and Greg Mori