Programme‎ > ‎

Detailed Programme

BMVC 2016 PROGRAMME

Programme in pdf

MONDAY 19TH SEPTEMBER

11:00

Registration (until 17:00)

Exhibition Centre

13:00-14:30

Tutorial:  Chair – Will Smith

Measurement-based Appearance Modelling.

Abhijeet Ghosh (Imperial College London).

PX001

14:30-15:00

Break

Exhibition Centre

15:00-16:30

Tutorial continued:

Measurement-based Appearance Modelling.

Abhijeet Ghosh (Imperial College London).

PX001

19:00-21:00

Welcome Reception

Exhibition Centre

TUESDAY 20TH SEPTEMBER

08:15

Registration (until 17:45)

Exhibition Centre

08:45-09:00

Welcome

PX001

09:00-10:00

Keynote:

Chair: Edwin Hancock

e-Intangible Heritage.

Katsushi Ikeuchi (Microsoft Research Asia)

PX001

10:00-10:40

Session 1: Segmentation

Chair: Anders Bruhn

PX001

10:00-10:20

Local Shape Transfer for Image Co-segmentation.

Wei Teng (Beihang University), Yu Zhang, Xiaowu Chen, Jia Li and Zhiqiang He.

PX001

10:20-10:40

SMURFS: Superpixels from Multi-scale Refinement of Super-regions.

Imanol Luengo (University of Nottingham), Mark Basham and Andrew French.

PX001

10:40-11:00

Break

Exhibition Centre

11:00-12:40

Session 2: Low-level Vision and Computational Photography

Chair: Eraldo Ribeiro

PX001

11:00-11:20

Biologically plausible boundary detection.

Arash Akbarinia (Centre de Visió per Computador) and Alejandro Parraga.

PX001

11:20-11:40

Bio-inspired Collision Detector with Enhanced Selectivity for Ground Robotic Vision System.

Qinbing Fu (University of Lincoln) and Shigang Yue.

PX001

11:40-12:00

A Deep Primal-Dual Network for Guided Depth Super-Resolution.

Gernot Riegler (Graz University of Technology), David Ferstl, Matthias Rüther and Horst Bischof.

PX001

12:00-12:20

Towards Deep Style Transfer: A Content-Aware Perspective.

Yi-Lei (Pixart Imaging Inc.) Chen and  Chiou-Ting Hsu.

PX001

12:20-12:40

Real-Time Intensity-Image Reconstruction for Event Cameras Using Manifold Regularization.

Christian Reinbacher (Graz University of Technology), Gottfried Graber and Thomas Pock.

PX001

12:40-13:40

Lunch

13:40-14:40

Posters 1 (listed later)

Exhibition Centre

14:40-16:00

Session 3: 3D Computer Vision

Chair: Richard Bowden

PX001

14:40-15:00

Adding Synchronization and Rolling Shutter in Multi-Camera Bundle Adjustment.

Thanh-Tin  Nguyen (Institut Pascal) and Maxime Lhuillier.

PX001

15:00-15:20

EMVS: Event-based Multi-View Stereo.

Henri Rebecq (University of Zurich), Guillermo Gallego and Davide Scaramuzza.

PX001

15:20-15:40

Occlusion-aware 3D Morphable Face Models.

Bernhard Egger  (University of Basel), Andreas Schneider, Clemens Blumer, Andreas Forster, Sandro Schönborn and Thomas Vetter.

PX001

15:40-16:00

Next-Best Stereo: Extending Next-Best View Optimisation For Collaborative Sensors.

Oscar Mendez-Maldonado (University of Surrey), Simon Hadfield, Nicolas Pugeault and Richard Bowden.

PX001

16:00-16:20

Break

Exhibition Centre

16:20-17:20

Session 4: Motion and Tracking

Chair: David Suter

PX001

16:20-16:40

Shape-based Image Correspondence.

Berk Sevilmis  (Brown University) and Benjamin Kimia.

PX001

16:40-17:00

Reprojection Flow for Image Registration Across Seasons.

Shane Griffith (GeorgiaTech-Lorraine) and Cedric Pradalier

PX001

17:00-17:20

Unsupervised Learning of Shape-Motion Patterns for Objects in Urban Street Scenes.

Dirk Klostermann (RWTH Aachen University), Aljosa Osep, Jörg Stückler and Bastian Leibe.

PX001

17.20 – 18.10

Poster discussion sessions


Exhibition Centre

WEDNESDAY 21TH SEPTEMBER

08:15

Registration (until 17:45)

Exhibition Centre

09:00-10:00

Keynote:

Chair: Richard Wilson

Towards Affordable Self-driving Cars

Raquel Urtasun (University of Toronto)

PX001

10:00-10:40

Session 5: Statistical Methods and Learning

Chair: Andrea Cavallaro

PX001

10:00-10:20

Efficient Learning for Discriminative Segmentation with Supermodular Losses.

Jiaqian Yu (CentraleSupelec) and Matthew Blaschko.

PX001

10:20-10:40

Variational Weakly-Supervised Gaussian Processes.

Melih Kandemir (Heidelberg University), Manuel Haussmann, Ferran Diego, Kumar Rajamani, Jeroen van der Laak and Fred Hamprecht.

PX001

10:40-11:00

Break

Exhibition Centre

11:00-12:40

Session 6: Recognition and Physics-based Vision

Chair: William Smith

PX001

11:00-11:20

Regional Gating Neural Networks for Multi-label Image Classification.

Rui-Wei Zhao (Fudan University), Jianguo Li, Yurong Chen, Jia-Ming Liu, Yu-Gang Jiang and Xiangyang Xue.

PX001

11:20-11:40

Multispectral Deep Neural Network for Pedestrian Detection.

Jingjing Liu (Rutgers University), Shaoting Zhang, Shu Wang and Dimitris Metaxas.

PX001

11:40-12:00

L1 Graph Based Sparse Model for Label De-noising.

Xiaobin Chang (Queen Mary, Univ. of London), Tao Xiang and Timothy Hospedales.

PX001

12:00-12:20

PatchIt: Self-Supervised Network Weight Initialization for Fine-grained Recognition.

Patrick Sudowe (RWTH Aachen University) and Bastian Leibe.

PX001

12:20-12:40

Combining Shape from Shading and Stereo: A Variational Approach for the Joint Estimation of Depth, Illumination and Albedo.

Daniel Maurer (Univ of Stuttgart), Yong Chul Ju, Michael Breuß, Andres Bruhn.

PX001

12:40-13:40

Lunch

13:40-14:40

Posters 2 (listed later)

Exhibition Centre

14:40-16:00

Session 7: Recognition

Chair: Krystian Mikolajczyk

PX001

14:40-15:00

Structured Prediction of 3D Human Pose with Deep Neural Networks.

Bugra Tekin (EPFL), Isinsu Katircioglu, Mathieu Salzmann, Vincent Lepetit, and Pascal Fua.

PX001

15:00-15:20

Multi-task Relative Attribute Prediction by Incorporating Local Context and Global Style Information.

Yuhang He (Wuhan University), Long Chen and Jianda Chen.

PX001

15:20-15:40

Deep Multi-task Attribute-driven Ranking for Fine-grained Sketch-based Image Retrieval.

Jifei Song (Queen Mary Univ. of London), Yi-Zhe Song, Tao Xiang, Timothy Hospedales and Xiang Ruan.

PX001

15:40-16:00

The Role of Context Selection in Object Detection.

Ruichi Yu (Univ. of Maryland), Xi Chen, Vlad Morariu and Larry Davis.

PX001

16:00-16:20

Break

Exhibition Centre

16:20-17:20

Session 8: Face and Gesture

Chair: Nick Pears

PX001

16:20-16:40

Highly Efficient Regression for Scalable Person Re-Identification.

Hanxiao Wang (Queen Mary, University of London), Shaogang Gong and Tao Xiang.

PX001

16:40-17:00

Reflective Regression of 2D-3D Face Shape Across Large Pose.

Xuhui Jia (The University of Hong Kong), Heng Yang, Xiaolong Zhu,  Zhanghui Kuang, Yifeng Niu and Kwok-Ping Chan.

PX001

17:00-17:20

Deep Sign: Hybrid CNN-HMM for Continuous Sign Language Recognition.

Oscar Koller (RWTH Aachen University), Sepehr Zargaran, Hermann Ney and Richard Bowden.

PX001

17.20 – 18.10

Poster discussion sessions


BMVA Members AGM

Exhibition Centre

PX001

19:00-22:00

Banquet

National Railway Museum

THURSDAY 22TH SEPTEMBER

09:00-10:40

Session 9: Recognition, Optimisation and Performance Evaluation.

Chair: Paolo Remagnino

PX001

09:00-09:20

Measuring the effect of nuisance variables on classifiers.

Alhussein Fawzi (EPFL) and Pascal Frossard.

PX001

09:20-09:40

Learning Robust Graph Regularisation for Subspace Clustering.

Elyor Kodirov (Queen Mary, University of London), Tao Xiang, Zhenyong Fu and Shaogang Gong.

PX001

09:40-10:00

Solving Jigsaw Puzzles with Linear Programming.

Rui Yu (University College London), Chris Russell and Lourdes Agapito.

PX001

10:00-10:20

Detecting Tracking Errors via Forecasting.

Obaid Ullah Khalid (Queen Mary, University of London), Andrea Cavallaro and Bernhard Rinner.

PX001

10:20-10:40

Oracle Performance for Visual Captioning.

Li Yao (University of Montreal), Nicolas  Ballas, Kyunghyun Cho, John Smith and Yoshua Bengio.

PX001

10:40-11:00

Break

Exhibition Centre

11:00-12:40

Session 10: Video Events, Robot Vision and Deep Learning.

Chair: Adrian Bors

PX001

11:00-11:20

Beyond Action Recognition: Action Completion in RGB-D Data.

Farnoosh Heidarivincheh (University of Bristol), Majid Mirmehdi and Dima Damen.

PX001

11:20-11:40

Video Stream Retrieval of Unseen Queries using Semantic Memory.

Spencer Cappallo (University of Amsterdam), Thomas Mensink, and Cees Snoek.

PX001

11:40-12:00

Mapping Auto-context to a Deep, Sparse ConvNet for Semantic Segmentation.

David Richmond (Harvard University), Dagmar Kainmueller, Michael Yang, Eugene Myers and Carsten Rother.

PX001

12:00-12:20

Fully-trainable deep matching.

James Thewlis (University of Oxford), Shuai Zheng, Philip Torr and Andrea Vedaldi.

PX001

12:20-12:40

Detection of fast incoming objects with a moving camera.

Fabio Poiesi (Queen Mary University of London) and Andrea Cavallaro.

PX001

12:40-12:50

Conference closing remarks

PX001

POSTER SESSION 1, TUESDAY 20TH SEPTEMBER, 13:40-14:40.

Tue.1

Multi-view Multi-illuminant Intrinsic Dataset.

Shida Beigpour (Univ of Siegen), Mai Lan Ha, Sven Kunz, Andreas Kolb and Volker Blanz.

Exhibition Centre

Tue.2

Accurate Closed-form Estimation of Local Affine Transformations Consistent with the Epipolar Geometry.

Daniel Barath (MTA SZTAKI), Jiri Matas and Levente Hajder.

Exhibition Centre

Tue.3

Recognition of Transitional Action for Short-Term Action Prediction using Discriminative Temporal CNN Feature.

Hirokatsu Kataoka (AIST), Yudai Miyashita, Masaki Hayashi, Kenji Iwata and Yutaka Satoh.

Exhibition Centre

Tue.4

Multi-H: Efficient recovery of tangent planes in stereo images.

Daniel Barath (MTA SZTAKI), Jiri Matas, and Levente Hajder.

Exhibition Centre

Tue.5

Jointly Learning Non-negative Projection and Dictionary with Discriminative Graph Constraints for Classification.

Weiyang Liu (Peking University), Zhiding Yu, Yandong Wen, Rongmei Lin and Meng Yang.

Exhibition Centre

Tue.6

A MultiPath Network for Object Detection.

Sergey Zagoruyko , Adam Lerer, Tsung-Yi Lin, Pedro O. Pinheiro, Sam Gross, Soumith Chintala and Piotr Dollar.

Exhibition Centre

Tue.7

Fast Eigen Matching.

Yusuke Sekikawa  (Denso IT Laboratory, Inc.), Koichiro Suzuki,  Yuichi Yoshida, Kosuke Hara and Ikuro Sato.

Exhibition Centre

Tue.8

Recoding Color Transfer as A Color Homography.

Han Gong (University of East Anglia), Graham Finlayson and Robert B. Fisher.

Exhibition Centre

Tue.9

Pose-Robust 3D Facial Landmark Estimation from a Single 2D Image. Brandon Smith (Univ. of Wisconsin-Madison) and Charles Dyer.

Exhibition Centre

Tue.10

Bottom-up Instance Segmentation using Deep Higher-Order CRFs.

Anurag Arnab (University of Oxford) and Philip Torr.

Exhibition Centre

Tue.11

Horizon Lines in the Wild.

Scott Workman (University of Kentucky), Menghua Zhai and Nathan Jacobs.

Exhibition Centre

Tue.12

An Octree-Based Approach towards Efficient Variational Range Data Fusion.

Wadim Kehl (TU München), Tobias Holl, Federico Tombari, Slobodan Ilic and Nassir Navab.

Exhibition Centre

Tue.13

Finsler Geodesic Evolution Model for Region based Active Contours.

Da Chen (Univ Paris Dauphine), Laurent Cohen and Jean-Marie Mirebeau.

Exhibition Centre

Tue.14

Patch Based Confidence Prediction for Dense Disparity Map.

Akihito Seki (ETH Zurich) and Marc Pollefeys.

Exhibition Centre

Tue.15

Boosted Convolutional Neural Networks.

Mohammad Moghimi (Cornell University), Serge Belongie and Mohammad Saberian.

Exhibition Centre

Tue.16

Material-Specific Chromaticity Priors.

Jeroen Put (EDM - Uhasselt) and Nick Michiels.

Exhibition Centre

Tue.17

Play and Learn: Using Video Games to Train Computer Vision Models.

Alireza Shafaei (University of British Columbia), James Little and Mark Schmidt.

Exhibition Centre

Tue.18

SDF-TAR: Parallel Tracking and Refinement in RGB-D Data using Volumetric Registration.

Miroslava Slavcheva (Siemens AG) and Slobodan Ilic.

Exhibition Centre

Tue.19

Probabilistic Semi-Supervised Multi-Modal Hashing.

Behnam Gholami (Rutgers University).

Exhibition Centre

Tue.20

Learning to Invert Local Binary Patterns.

Felix Juefei-Xu (Carnegie Mellon University) and Marios Savvides.

Exhibition Centre

Tue.21

Probabilistic Compositional Active Basis Models for Robust Pattern Recognition.

Adam Kortylewski (University of Basel) and Thomas Vetter.

Exhibition Centre

Tue.22

Loglet SIFT for Part Description in Deformable Part Models: Application to Face Alignment.

Qiang Zhang (University of Warwick)  and Abhir Bhalerao.

Exhibition Centre

Tue.23

Dictionary Replacement for Single Image Restoration of 3D Scenes.

T M Nimisha (IIT Madras), Arun Mathamkode and Rajagopalan Ambasamudram.

Exhibition Centre

Tue.24

Poisson Noise Removal for Image Demosaicing.

Sukanya Patil (IIT Bombay) and Ajit Rajwade.

Exhibition Centre

Tue.25

Factorized Binary Codes for Large-Scale Nearest Neighbor Search.

Frederick Tung (Univ of British Columbia) and James Little.

Exhibition Centre

Tue.26

Edge Enhanced Direct Visual Odometry.

Xin Wang (Peking University), Wei Dong, Mingcai Zhou, Renju Li and Hongbin Zha.

Exhibition Centre

Tue.27

Optimised photometric stereo via non-convex variational minimisation.

Laurent Hoeltgen (B-TU Cottbus), Yvain Queau, Michael Breuß and Georg Radow.

Exhibition Centre

Tue.28

U-shaped Networks for Shape from Light Field.

Stefan Heber (TU Graz), Wei Yu and Thomas Pock.

Exhibition Centre

Tue.29

Using Shading and a 3D Template to Reconstruct Complex Surface Deformations.

Mathias Gallardo (ISIT–UMR 6284 CNRS / UdA), Toby Collins and Adrien Bartoli.

Exhibition Centre

Tue.30

Physics 101: Learning Physical Object Properties from Unlabeled Videos.

Jiajun Wu (MIT), Joseph Lim, Hongyi Zhang, Joshua Tenenbaum and William Freeman.

Exhibition Centre

Tue.31

Attribute Embedding with Visual-Semantic Ambiguity Removal for Zero-shot Learning.

Yang Long (The University of Sheffield), Li Liu and Ling Shao.

Exhibition Centre

Tue.32

NRSfM-Flow: Recovering Non-Rigid Scene Flow from Monocular Image Sequences.

Vladislav Golyanik (DFKI GmbH), Aman Shankar  Mathur and Didier Stricker.

Exhibition Centre

Tue.33

Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading.

Chris Russell (UCL), Lourdes Agapito, Qi Liu Yin, Rui Yu and Andrew Fitzgibbon and Qi Liu-Yin.

Exhibition Centre

Tue.34

STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition.

Wei Liu (The University of Hong Kong), Chaofeng Chen, Kwan-Yee K. Wong, Zhizhong Su and Junyu Han.

Exhibition Centre

Tue.35

Context Matters: Refining Object Detection in Video with Recurrent Neural Networks.

Subarna Tripathi (UC San Diego), Zachary  Lipton, Serge Belongie and Truong Nguyen.

Exhibition Centre

Tue.36

Outlier Rejection for Absolute Pose Estimation with Known Orientation.

Viktor Larsson (Lund University), Johan Fredriksson, Carl Toft and Fredrik Kahl.

Exhibition Centre

Tue.37

Learning from scratch a confidence measure.

Matteo Poggi (University of Bologna) and Stefano Mattoccia.

Exhibition Centre

Tue.38

Localizing Periodicity in Time Series and Videos.

Giorgos Karvounas (FORTH), Iason Oikonomidis, and Antonis Argyros.

Exhibition Centre

Tue.39

Person Re-identification in Appearance Impaired Scenarios.

Mengran Gou (Northeastern University), Xikang  Zhang, Angels Rates-Borras, Sadjad Asghari-Esfeden, Mario Sznaier and Octavia Camps.

Exhibition Centre

Tue.40

Learning to Detect and Match Keypoints with Deep Architectures.

Hani Altwaijry (Cornell University), Andreas Veit and Serge Belongie.

Exhibition Centre

Tue.41

Supervised Incremental Hashing.

Bahadir Ozdemir (University of Maryland), Mahyar Najibi and Larry Davis.

Exhibition Centre

Tue.42

Multi-Scale Fully Convolutional Network for Fast Face Detection.

Yancheng Bai (Institute of Software, Chinese), Wenjing Ma, Yucheng Li, Liangliang Cao, Wen Guo and Luwei Yang.

Exhibition Centre

Tue.43

Attention Networks for Weakly Supervised Object Localization.

Eu Wern Teh (University of Manitoba), Mrigank Rochan and Yang Wang.

Exhibition Centre

Tue.44

Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset.

Andrew Shin  (University of Tokyo), Yoshitaka Ushiku and Tatsuya Harada.

Exhibition Centre

Tue.45

Learning of Separable Filters by Stacked Projecting Convolutional Autoencoders.

Arash Shahriari (Australian National University).

Exhibition Centre

Tue.46

Deskewing by space-variant deblurring.

Karthik Seemakurthy (IIT Madras), Subeesh Vasu and Rajagopalan Ambasamudram.

Exhibition Centre

Tue.47

Faces in Places: compound query retrieval.

Yujie Zhong (University of Oxford), Relja Arandjelovic and Andrew Zisserman.

Exhibition Centre

Tue.48

Semi-supervised Video Object Segmentation Using Multiple Random Walkers.

Won-Dong (Korea University) Jang and Chang-Su Kim.

Exhibition Centre

Tue.49

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos.

Suman Saha (Oxford Brookes university), Gurkirt Singh, Michael Sapienza, Fabio Cuzzolin and Philip Torr.

Exhibition Centre

Tue.50

Exploiting Random RGB and Sparse Features for Camera Pose Estimation.

Lili Meng (University of British Columbia), Jianhui Chen, Frederick Tung, James Little and Clarence Silva.

Exhibition Centre

Tue.51

Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches.

Erik  Rodner  (University of Jena), Marcel Simon, Robert Fisher and Joachim Denzler.

Exhibition Centre

Tue.52

Near-Field Photometric Stereo in Ambient Light.

Fotios Logothetis (University of Cambridge), Roberto Mecca, Yvain Queau and  Roberto Cipolla.

Exhibition Centre

POSTER SESSION 2, WEDNESDAY 21ST SEPTEMBER, 13:40-14:40.

Wed.1

Solving Visual Madlibs with Multiple Cues.

Tatiana Tommas (UNC Chapel Hill),  Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Alexander Berg and Tamara Berg.

Exhibition Centre

Wed.2

LSTM for Image Annotation with Relative Visual Importance.

Geng Yan (Zhejiang University), Yang Wang and Zicheng Liao.

Exhibition Centre

Wed.3

OnionNet: Sharing Features in Cascaded Deep Classifiers.

Martin Simonovsky (Universite Paris Est, ENPC) and Nikos Komodakis.

Exhibition Centre

Wed.4

Line reconstruction using prior knowledge in single non-central view.

Jesus Bermudez-Cameo (Universidad de Zaragoza), Cédric Demonceaux, Gonzalo Lopez-Nicolas and Jose Guerrero.

Exhibition Centre

Wed.5

Attribute Recognition from Adaptive Parts.

Luwei Yang (Simon Fraser University), Ligeng Zhu, Yichen Wei, Shuang Liang and Ping Tan.

Exhibition Centre

Wed.6

Memory-based Gait Recognition.

Dan Liu (UESTC), Mao Ye, Xudong Li, Feng Zhang and Lan Lin.

Exhibition Centre

Wed.7

Three-Point Direct Stereo Visual Odometry.

Jeong-Kyun Lee (GIST) and Kuk-Jin Yoon.

Exhibition Centre

Wed.8

Semantic Segmentation for Real-World Data by Jointly Exploiting Supervised and Transferrable Knowledge.

Li-Hsien Lu (National Tsing Hua University) and Chiou-Ting Hsu.

Exhibition Centre

Wed.9

Optimized Regressor Forest for Image Super-Resolution.

Chia-Yang Chang (National Taiwan University), Wei-Chih Tu and Shao-Yi Chien.

Exhibition Centre

Wed.10

Convolutional aggregation of local evidence for large pose face alignment.

Adrian Bulat (University of Nottingham) and Yorgos Tzimiropoulos.

Exhibition Centre

Wed.11

Wide Residual Networks.

Sergey Zagoruyko  and Nikos Komodakis.

Exhibition Centre

Wed.12

Deep Part-Based Generative Shape Model with Latent Variables.

Alexander Kirillov (Technische Universität Dresden), Mikhail Gavrikov, Ekaterina Lobacheva, Anton Osokin and Dmitry Vetrov.

Exhibition Centre

Wed.13

General Human Traits Oriented Generic Elastic Model for 3D Face Reconstruction.

Joi San Tan, Ibrahim Venkat, Iman Yi Liao and Philippe De Wilde.

Exhibition Centre

Wed.14

Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization.

Spyridon Gidaris (ENPC) and Nikos Komodakis.

Exhibition Centre

Wed.15

Crafting a multi-task CNN for viewpoint estimation.

Francisco Massa (ENPC), Renaud Marlet and Mathieu Aubry.

Exhibition Centre

Wed.16

Improving Weakly-Supervised Object Localization By Micro-Annotation.

Alexander Kolesnikov (IST Austria) and Christoph Lampert.

Exhibition Centre

Wed.17

MBest Struct: M-Best diverse sampling for structured tracker.

Ivan Bogun (Florida Institute of Technology) and Eraldo Ribeiro.

Exhibition Centre

Wed.18

Event-Based Hough Transform in a Spiking Neural Network for Multiple Line Detection and Tracking Using a Dynamic Vision Sensor.

Sajjad Seifozzakerini (I2R), Wei-Yun Yau, Bo Zhao and Kezhi Mao.

Exhibition Centre

Wed.19

Holistically Constrained Local Model: Going Beyond Frontal Poses for Facial Landmark Detection.

KangGeon Kim (USC), Tadas Baltrušaitis, AmirAli Zadeh, Louis-Philippe Morency and Gérard Medioni.

Exhibition Centre

Wed.20

Bag of Surrogate Parts: one inherent feature of deep CNNs.

Yanming Guo  (Leiden University) and Michael S. Lew.

Exhibition Centre

Wed.21

Multi-scale Colorectal Tumour Segmentation Using a Novel Coarse to Fine Strategy.

Kun Zhang  (Shanghai University), Danny Crookes, Jim Diamond, Minrui Fei, Jianguo Wu, Peijian Zhang and Huiyu Zhou.

Exhibition Centre

Wed.22

Learning Additive Kernel For Feature Transformation and Its Application to CNN Features.

Takumi Kobayashi (National Institute of AIST).

Exhibition Centre

Wed.23

Robust 3D Car Shape Estimation from Landmarks in Monocular Image.

Yanan Miao, Xiaoming Tao (Tsinghua University) and Jianhua Lu.

Exhibition Centre

Wed.24

Projective Unsupervised Flexible Embedding with Optimal Graph.

Wei Wang, Yan Yan, Feiping Nie, Xavier Pineda, Shuicheng Yan and Nicu Sebe.

Exhibition Centre

Wed.25

Towards Automatic Image Editing: Learning to See another You.

Xu Jia (KU Leuven), Amir Ghodrati, Marco Pedersoli and Tinne Tuytelaars.

Exhibition Centre

Wed.26

Dense Labeling with User Interaction: an Example for Depth-Of-Field Simulation.

Ana Cambra (Universidad de Zaragoza), Adolfo Muñoz and Ana Murillo.

Exhibition Centre

Wed.27

MLBoost Revisited: a Faster Metric Learning Algorithm for Identity-Based Face Retrieval.

Romain Negrel  (GREYC), Alexis Lechervy and Frederic Jurie.

Exhibition Centre

Wed.28

Learning Neural Network Architectures using Backpropagation.

Suraj Srinivas (IISc) and Venkatesh Babu.

Exhibition Centre

Wed.29

Enhancing pose estimation through efficient patch synthesis.

Pierre Rolin (Université de Lorraine), Marie-Odile Berger and Frederic Sur.

Exhibition Centre

Wed.30

Discovering motion hierarchies via tree-structured coding of trajectories.

Juan-Manuel Perez-Rua (Technicolor), Tomas Crivelli, Patrick Perez and Patrick Bouthemy.

Exhibition Centre

Wed.31

Coplanar Repeats by Energy Minimization.

James Pritts (Czech Technical University), Denys Rozumnyi, M. Pawan Kumar and Ondrej Chum.

Exhibition Centre

Wed.32

Two-Stream SR-CNNs for Action Recognition in Videos.

Yifan Wang (ETHZ), Jie Song, Limin Wang and Otmar Hilliges.

Exhibition Centre

Wed.33

An Efficient Convolutional Network for Human Pose Estimation.

Umer Rafi (RWTH Aachen University, German), Bastian Leibe and Juergen Gall.

Exhibition Centre

Wed.34

A data augmentation methodology for training machine/deep learning gait recognition algorithms.

Christoforos Charalambous (Imperial College London) and Anil Bharath.

Exhibition Centre

Wed.35

Mean Box Pooling: A Rich Image   Representation and Output Embedding for  the Visual Madlibs Task.

Mateusz Malinowski (MPI for Informatics), Ashkan Mokarian and Mario Fritz.

Exhibition Centre

Wed.36

Practical View on Face Presentation Attack Detection.

Naser Damer (Fraunhofer IGD) and Kristiyan Dimitrov.

Exhibition Centre

Wed.37

Fast Feature-Less Quaternion-based Particle Swarm Optimization for Object  Pose Estimation From RGB-D Images.

Stefano Rosa (Politecnico di Torino) and Giorgio Toscana.

Exhibition Centre

Wed.38

Graph Convolutional Neural Network.

Michael Edwards (Swansea University) and Xianghua Xie.

Exhibition Centre

Wed.39

When is supervision enough? Transferring parts across categories.

David Novotny (University of Oxford), Diane Larlus and Andrea Vedaldi.

Exhibition Centre

Wed.40

Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets.

Manuel Amthor (Friedrich Schiller University Jena), Erik  Rodner and Joachim Denzler.

Exhibition Centre

Wed.41

Maximum Margin Linear Classifiers in Unions of Subspaces.

Xinrui Lyu , Joaquin Zepeda and Patrick Perez.

Exhibition Centre

Wed.42

Aerial image geolocalization from recognition and matching of roads and intersections.

Marius Leordeanu.

Exhibition Centre

Wed.43

Learning local feature descriptors with triplets and shallow convolutional neural networks.

Vassileios Balntas (Imperial College London), Edgar Riba, Daniel Ponsa and Krystian  Mikolajczyk.

Exhibition Centre

Wed.44

Online Feature Selection for Visual Tracking.

Giorgio Roffo (University of Verona) and Simone Melzi.

Exhibition Centre

Wed.45

Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval.

Takahiko Furuya (University of Yamanashi) and Ryutarou Ohbuchi.

Exhibition Centre

Wed.46

Learning Grimaces by Watching TV.

Samuel Albanie (Oxford University) and Andrea Vedaldi.

Exhibition Centre

Wed.47

Accurate and robust face recognition from RGB-D images with a deep learning approach.

Yuancheng Lee (National Tsing Hua University), Jiancong Chen, Ching Wei Tseng and Shang-Hong Lai.

Exhibition Centre

Wed.48

Global Deconvolutional Networks for Semantic Segmentation.

Vladimir Nekrasov (UNIST), Janghoon Ju and Jaesik Choi.

Exhibition Centre

Wed.49

Convolutional Sparse Coding-based Image Decomposition.

He Zhang (Rutgers University) and Vishal Patel.

Exhibition Centre

Wed.50

Domain Adaptive Subspace Clustering.

Mahdi Abavisani (Rutgers University) and Vishal Patel.

Exhibition Centre

Wed.51

Filtering 3D Keypoints Using GIST For Accurate Image-Based Localization.

Charbel Azzi (University of Waterloo), John Zelek, Daniel Asmar and Adel Fakih.

Exhibition Centre

Wed.52

Probabilistic Obstacle Partitioning of Monocular Video for Autonomous Vehicles.

Ryan Wolcott (University of Michigan) and Ryan Eustice.

Exhibition Centre

Wed.53

Face Alignment in Unconstrained Videos.

Xi Peng (Rutgers University) and Dimitris Metaxas.

Exhibition Centre



Ċ
Richard Wilson,
Sep 9, 2016, 6:49 AM