Paper List
Tuesday, May 28, 2019
Oral 1: 3D and Stereo
| 01-01 | SlamCraft: Dense Planar RGB Monocular SLAM |
| Jason Rambach (DFKI), Paul Lesur (DFKI), Alain Pagani (DFKI), Didier Stricker (DFKI) | |
| 01-02 | Reconstruction with Guided PatchMatch Stereo |
| Trevor Gee (University of Auckland), Patrice Delmas (University of Auckland) | |
| 01-03 | Recognition and 6D Pose Estimation of Large-scale Objects using 3D Semi-Global Descriptors |
| David Nospes (Technische Hochschule Mittelhessen), Kirill Safronov (KUKA Deutschland GmbH), Sarah Gillet (Royal Institute of Technology), Klaus Brillowski (Technische Hochschule Mittelhessen), Uwe E. Zimmermann (KUKA Deutschland GmbH) | |
| 01-04 | Robust 3D Human Pose Estimation Guided by Filtered Subsets of Body Keypoints |
| Alexandros Makris (FORTH), Antonis Argyros (CSD-UOC, ICS-FORTH) | |
| 01-05 | Uncalibrated Photometric Stereo Constrained by Intrinsic Reflectance Image and Shape from Silhoutte |
| Shuhei Hashimoto (Hiroshima City University), Daisuke Miyazaki (Hiroshima City University), Shinsaku Hiura (Hiroshima City University) | |
| 01-06 | Revisiting Visual Odometry for Real-Time Performance |
| Gaurav Singh (Nanyang Technological University Singapore), Meiqing Wu (Nanyang Technological University Singapore), Siew Kei Lam (Nanyang Technological University Singapore) |
Poster 1
| 02-01 | Zero-shot Learning of 3D Point Cloud Objects |
| Ali Cheraghian (Australian National University), Shafin Rahman (Australian National University), Lars Petersson (Data61/CSIRO) | |
| 02-02 | Indexing in k-Nearest Neighbor Graph by Hash-Based Hill-Climbing |
| Munlika Rattaphun (National Chiayi University), Amorntip Prayoonwong (National Chiayi University), Chih-Yi Chiu (National Chiayi University) | |
| 02-03 | Robust Auto-Calibration for Practical Scanning Setups from Epipolar and Trifocal Relations |
| Torben Fetzer (TU Kaiserslautern), Gerd Reis (DFKI), Didier Stricker (DFKI) | |
| 02-04 | An Evaluation of Recent Local Image Descriptors for Real-World Applications of Image Matching |
| Fabio Bellavia (University of Florence), Carlo Colombo (DINFO, University of Florence) | |
| 02-05 | Document Image Binarization using U-Net |
| Dhara Kotecha (DA-IICT), Manjunath Joshi (DA-IICT) | |
| 02-06 | Skip-Pose Vectors: Pose-based Motion Embedding using Encoder-Decoder Models |
| Yuta Shirakawa (Toshiba), Tatsuo Kozakaya (Toshiba) | |
| 02-07 | Automatic Measurement of Visual Attention to Video Content using Deep Learning |
| Attila Schulc (Realeyes), Jeffrey F. Cohn (University of Pittsburgh, Realeyes), Jie Shen (Imperial College London), Maja Pantic (Samsung AI Centre Cambridge, Imperial College London, Realeyes) | |
| 02-08 | Temporally Forward Nonlinear Scale Space with Octave Prediction for High Frame Rate and Ultra-Low Delay A-KAZE Matching System |
| Yuan Li (Waseda University), Songlin Du (Waseda University), Takeshi Ikenaga (Waseda University) | |
| 02-09 | CNN-based Image Denoising for Outdoor Active Stereo |
| Chengchao Qu (Fraunhofer IOSB), Maksim Moiseikin (Fraunhofer IOSB), Sascha Voth (Fraunhofer IOSB), Jürgen Beyerer (Fraunhofer IOSB) | |
| 02-10 | Online Targetless End-to-End Camera-LIDAR Self-Calibration |
| Balázs Nagy(MTA SZTAKI, Pázmany Péter Catholic University), Levente Kovács (MTA SZTAKI), Csaba Benedek (MTA SZTAKI, Pázmany Péter Catholic University) | |
| 02-11 | Measuring Robustness of Visual SLAM |
| David Prokhorov (Samsung AI Center), Dmitry Zhukov (Samsung AI Center), Olga Barinova (Samsung AI Center), Konushin Anton (Samsung AI Center), Anna Vorontsova (Samsung AI Center) | |
| 02-12 | Spatial Persevered Deep Image Analogy |
| Nengjie Zhen (Macau University of Science and Technology), Junliang Li (Macau University of Science and Technology), Siyuan Yu (Macau University of Science and Technology), Hon-Cheng Wong (Macau University of Science and Technology), Sio-Long Lo (Macau University of Science and Technology), Ping Li (Macau University of Science and Technology), Un-Hong Wong (Macau University of Science and Technology) | |
| 02-13 | Face Style Transfer and Removal with Generative Adversarial Network |
| Qiang Zhu (Simon Fraser University), Ze-Nian Li (Simon Fraser University) | |
| 02-14 | Domain Adaptation using a Gradient Reversal Layer with Instance Weighting |
| Kosuke Osumi (Chubu University), Takayoshi Yamashita (Chubu University), Hironobu Fujiyoshi (Chubu University) | |
| 02-15 | Single-Wavelength and Multi-Parallel Dotted- and Solid-Lines for Dense and Robust Active 3D Reconstruction |
| Genki Nagamatsu (Kyushu University), Ryo Furukawa (Hiroshima City University), Ryusuke Sagawa (AIST), Hiroshi Kawasaki (Kyushu University) | |
| 02-16 | A Hierarchical Segmentation Approach with Convolution-Recursive Deep Learning for 3D Multi-Object Recognition under Partial Occlusion Conditions |
| Soma Boubou (TTI-J, Omron Corporation), Tatsuo Narikiyo (TTI-J), Michihiro Kawanishi (TTI-J) | |
| 02-17 | Automatic Human Pose Annotation for Loose-Fitting Clothes |
| Takuya Matsumoto (TTI-J), Kodai Shimosato (TTI-J), Takahiro Maeda (TTI-J), Tatsuya Murakami (TTI-J), Kou Murakoso (Toei), Kazuhiko Mino (Toei), Norimichi Ukita (TTI-J) | |
| 02-18 | Exploring Better Food Detection via Transfer Learning |
| Jianing Sun (McGill University), Katarzyna Radecka (McGill University), Zeljko Zilic (McGill University) | |
| 02-19 | PCB-METAL: A PCB Image Dataset for Advanced Computer Vision Machine Learning Component Analysis |
| Gayathri Mahalingam (University of North Carolina Wilmington), Kevin Marshall Gay (University of North Carolina Wilmington), Karl Ricanek Jr. (University of North Carolina Wilmington) | |
| 02-20 | Performance Evalution of 3D Keypoint Detectors and Descriptors for Plants Health Classification |
| Shiva Azimi (Indian Institute of Technology-Delhi), Brejesh Lall (Indian Institute of Technology-Delhi), Tapan K. Gandhi (Indian Institute of Technology-Delhi) | |
| 02-21 | A Very Concise Feature Representation for Time Series Classification Understanding |
| Pattreeya Tanisaro (University of Osnabrück), Gunther Heidemann (University of Osnabrück) | |
| 02-22 | Spectral Normalization and Relativistic Adversarial Training for Conditional Pose Generation with Self-Attention |
| Yusuke Horiuchi (Waseda University), Edgar Simo-Serra (Waseda University), Satoshi Iizuka (University of Tsukuba), Hiroshi Ishikawa (Waseda University) | |
| 02-23 | Video Colorization using CNNs and Keyframes Extraction: An Application in Saving Bandwidth |
| Ankur Singh (Indian Institute of Technology Kanpur), Anurag Chanani (Indian Institute of Technology Kanpur), Harish Karnick (Indian Institute of Technology Kanpur), |
Oral 2: Segmentation and 2D
| 03-01 | Accurate Ellipse Extraction in Low-Quality Images |
| Zezhong Xu (Changzhou Institute of Technology), Cheng Qian (Changzhou Institute of Technology), Shibo Xu (Changsha High-tech Engineering School), Reinhard Klette (Auckland University of Technology) | |
| 03-02 | Auto-Retoucher(ART) --- A Framework for Background Replacement and Foreground Adjustment |
| Yunxuan Xiao (Shanghai Jiao Tong University), Yikai Li (Shanghai Jiao Tong University), Yuwei Wu (Shanghai Jiao Tong University), Lizhen Zhu (Shanghai Jiao Tong University) | |
| 03-03 | Uncertainty Based Model Selection for Fast Semantic Segmentation |
| Yu-Hui Huang (KU Leuven), Stamatios Georgoulis (ETH Zurich), Marc Proesmans (KU Leuven), Luc Van Gool (ETH Zurich) | |
| 03-04 | Region-wise Modeling of Facial Skin Age using Deep CNNs |
| Matthew Shreve (PARC, A Xerox Company), Raja Bala (PARC), Wencheng Wu (University of Rochester), Beilei Xu (University of Rochester), Ankur Purwar (Procter & Gamble), Paul Mats (Procter & Gamble) | |
| 03-05 | Re-staining Pathology Images by FCNN |
| Masayuki Fujitani (Waseda University), Yoshihiko Mochizuki (Waseda University), Satoshi Iizuka (University of Tsukuba), Edgar Simo-Serra (Waseda University), Hirokazu Kobayashi (Nagoya Institute of Technology), Chika Iwamoto (Kyushu University), Kenoki Ohuchida (Kyushu University), Makoto Hashizume (Kyushu University), Hidekata Hontani (Nagoya Institute of Technology), Hiroshi Ishikawa (Waseda University) | |
| 03-06 | DCNN-GAN: Reconstructing Realistic Image from fMRI |
| Yunfeng Lin (Shanghai Jiao Tong University), Jiangbei Li (Shanghai Jiao Tong University), Hanjing Wang (Shanghai Jiao Tong University) |
Wednesday, May 29, 2019
Oral 3: Learning
| 04-01 | A Three-Player GAN: Generating Hard Samples To Improve Classification Networks |
| Simon Vandenhende (KU Leuven), Bert De Brabandere (KU Leuven), Davy Neven (KU Leuven), Luc Van Gool (KU Leuven) | |
| 04-02 | UMGAN: Generative Adversarial Network for Image Unmosaicing using Perceptual Loss |
| Kamran Javed (Sungkyunkwan University), Nizam Ud Din (Sungkyunkwan University), Seho Bae (Sungkyunkwan University), Rahul S. Maharjan (Sungkyunkwan University), Donghwan Seo (Sungkyunkwan University), JuneHo Yi (Sungkyunkwan University) | |
| 04-03 | Gradual Sampling Gate for Bidirectional Knowledge Distillation |
| Soma Minami (Chubu University), Takayoshi Yamashita (Chubu University), Hironobu Fujiyoshi (Chubu University) | |
| 04-04 | Gait Recognition Based on Constrained Mutual Subspace Method with CNN Features |
| Akinari Sakai (University of Tsukuba), Naoya Sogi (University of Tsukuba), Kazuhiro Fukui (University of Tsukuba) | |
| 04-05 | Improving Image Classifiers for Small Datasets by Learning Rate Adaptations |
| Sourav Mishra (The University of Tokyo), Toshihiko Yamasaki (The University of Tokyo), Hideaki Imaizumi (exMedio Inc.) | |
| 04-06 | Kernelized Cross-view Quadratic Discriminant Analysis for Person Re-Identification |
| Tetsu Matsukawa (Kyushu University), Einoshin Suzuki (Kyushu University) |
Poster 2
| 05-01 | Learning Based Character Segmentation Method for Various License Plates |
| PyongKun Kim (Electronics and Telecommunications Research Institute), Kil-Taek Lim (Electronics and Telecommunications Research Institute), DooSik Kim (Electronics and Telecommunications Research Institute) | |
| 05-02 | Welding Joints Inspection via Residual Attention Network |
| Jinguo Zhu (Xi‘an Jiaotong University), Zejian Yuan (Xi‘an Jiaotong University), Tie Liu (Capital Normal University) | |
| 05-03 | Residual Squeeze-and-Excitation Network for Battery Cell Surface Inspection |
| Ziyang Song (Xi’an Jiaotong University), Zejian Yuan (Xi’an Jiaotong University), Tie Liu (Capital Normal University) | |
| 05-04 | Bullet-time Image Generation without 3-D |
| Yasuyuki Sugaya (Toyohashi University of Technology), Keita Ohseki (Toyohashi University of Technology) | |
| 05-05 | Autoencoder-Based Fabric Defect Detection with Cross-Patch Similarity |
| Hu Tian (Fujitsu Research & Development Center Co., Ltd.), Fei Li (Fujitsu Research & Development Center Co., Ltd.) | |
| 05-06 | Human Identification by Gait from Event-based Camera |
| Anna Sokolova (Samsung-MSU Laboratory, Lomonosov Moscow State University, NRU Higher School of Economics), Anton Konushin (Samsung-MSU Laboratory, Lomonosov Moscow State University, Samsung AI Center) | |
| 05-07 | The CASE Dataset of Candidate Spaces for Advert Implantation |
| Soumyabrata Dev (Trinity College Dublin), Murhaf Hossari (Trinity College Dublin), Matthew Nicholson (Trinity College Dublin), Killan McCabe (Trinity College Dublin), Atul Nautiyal (Trinity College Dublin), Clare Conran (Trinity College Dublin), Jian Tang (Huawei Ireland Research Center), Wei Xu (Huawei Ireland Research Center), François Pitié (Trinity College Dublin) | |
| 05-08 | Team Formation Mapping and Sequential Ball Motion State Based Event Recognition for Automatic Data Volley |
| Linzi Liang (Waseda University), Xina Cheng (Waseda University), Takeshi Ikenaga (Waseda University) | |
| 05-09 | End-to-End Person Re-Identification: Top View Analytics |
| Siti Khairuni Amalina Kamarol (Intel), Wendy, Siew Wen Chin (Intel) | |
| 05-10 | End-to-End Feature Pyramid Network for Real-Time Multi-Person Pose Estimation |
| Dingli Luo (Waseda University, University of Electronic Science and Technology of China), Songlin Du (Waseda University), Takeshi Ikenaga (Waseda University) | |
| 05-11 | 3D Object Trajectory Reconstruction using Stereo Matching and Instance Flow based Multiple Object Tracking |
| Sebastian Bullinger (Fraunhofer IOSB), Christoph Bodensteiner (Fraunhofer IOSB), Michael Arens (Fraunhofer IOSB) | |
| 05-12 | Integrating Visual and Geometric Consistency for Pose Estimation |
| Huiqin Chen (Paris-Saclay University), Emanuel Aldea (Paris-Saclay University), Sylvie Le Hégarat-Mascle (Paris-Saclay University) | |
| 05-13 | Pupil Localization for Ophthalmic Diagnosis Using Anchor Ellipse Regression |
| Horng-Horng Lin (Southern Taiwan University of Science and Technology), Zheng-Yi Li (National Cheng Kung University), Min-Hsiu Shih (National Cheng Kung University), Yung-Nien Sun (National Cheng Kung University), Ting-Li Shen (National Cheng Kung University) | |
| 05-14 | News2meme: An Automatic Content Generator from News Based on Word Subspaces from Text and Image |
| Erica K. Shimomoto (University of Tsukuba), Lincon S. Souza (University of Tsukuba), Bernardo B. Gatto (Center for Artificial Intelligence Research), Kazuhiro Fukui (Center for Artificial Intelligence Research) | |
| 05-15 | EyeWeS: Weakly Supervised Pre-Trained Convolutional Neural Networks for Diabetic Retinopathy Detection |
| Pedro Costa (INESC TEC), Teresa Araújo (INESC TEC, University of Porto), Guilherme Aresta (INESC TEC, University of Porto), Adrian Galdran (INESC TEC), Ana Maria Mendonça (University of Porto), Asim Smailagic (Carnegie Mellon University), Aurélio Campilho (University of Porto) | |
| 05-16 | Accurate Hand Keypoint Localization on Mobile Devices |
| Filippos Gouidis (University of Crete), Paschalis Panteleris (FORTH), Iason Oikonomidis (FORTH), Antonis Argyros (FORTH, University of Crete) | |
| 05-17 | FoodTracker: A Real-time Food Detection Mobile Application by Deep Convolutional Neural Networks |
| Jianing Sun (McGill University), Katarzyna Radecka (McGill University), Zeljko Zilic (McGill University) | |
| 05-18 | A Photo Booth That Finds Your Sports Player Lookalike |
| Mitsuru Nakazawa (Rakuten Institute of Technology), Tomoyuki Mukasa (Rakuten Institute of Technology), Björn Stenger (Rakuten Institute of Technology) | |
| 05-19 | Phenotypic Profiling of High Throughput Imaging Screens with Generic Deep Convolutional Features |
| Philip T. Jackson (Durham University), Yinhai Wang (AstraZeneca), Sinead Knight (AstraZeneca), Hongming Chen (AstraZeneca), Thierry Dorval (AstraZeneca), Martin Brown (AstraZeneca), Claus Bendtsen (AstraZeneca), Boguslaw Obara (Durham University) | |
| 05-20 | Visual Rhythm Prediction with Feature-Aligning Network |
| Yutong Xie (Shanghai Jiao Tong University), Haiyang Wang (Shanghai Jiao Tong University), Yan Hao (Shanghai Jiao Tong University), Zihao Xu (Shanghai Jiao Tong University) | |
| 05-21 | Invariant Spatial Information for Loop-Closure Detection |
| Ryohei Yamamoto (University of Fukui), Kanji Tanaka (University of Fukui), Koji Takeda (University of Fukui) | |
| 05-22 | Sparse and Noisy LiDAR Completion with RGB Guidance and Uncertainty |
| Wouter Van Gansbeke (KU Leuven), Davy Neven (KU Leuven), Bert De Brabandere (KU Leuven), Luc Van Gool (KU Leuven) |
Oral 4: Detection and Applications
| 06-01 | BallTrack: Football Ball Tracking for Real-Time CCTV Systems |
| Jacek Komorowski (Warsaw University of Technology, Sport Algorithmics and Gaming), Grzegorz Kurzejamski (Warsaw University of Technology, Sport Algorithmics and Gaming), Grzegorz Sarwas (Warsaw University of Technology, Sport Algorithmics and Gaming) | |
| 06-02 | Super Accurate Low Latency Object Detection on a Surveillance UAV |
| Maarten Vandersteegen (KU Leuven), Kristof Van Beeck (KU Leuven), Toon Goedemé (KU Leuven) | |
| 06-03 | Unsupervised Anomaly Detection with Compact Deep Features for Wind Turbine Blade Images Taken by a Drone |
| Yinan Wang (The University of Tokyo), Ryota Yoshihashi (The University of Tokyo), Rei Kawakami (The University of Tokyo), Shaodi You (Data61-CSIRO), Tohru Harano (EcoPower Co., Ltd.), Masahiko Ito (EcoPower Co., Ltd.), Katsura Komagome (EcoPower Co., Ltd.), Makoto Iida (The University of Tokyo), Takeshi Naemura (The University of Tokyo) | |
| 06-04 | Spatio-Temporal Eye Contact Detection Combining CNN and LSTM |
| Yuki Watanabe (Kyoto University), Atsushi Nakazawa (Kyoto University), Yu Mitsuzumi (Kyoto University), Toyoaki Nishida (Kyoto University) | |
| 06-05 | Hotspots Integrating of Expert and Beginner Experiences of Machine Operations through Egocentric Vision |
| Longfei Chen (Kyoto University), Yuichi Nakamura (Kyoto University), Kazuaki Kondo (Kyoto University), Dima Damen (University of Bristol), Walterio W. Mayol-Cuevas (University of Bristol) | |
| 06-06 | Cooking Video Summarization Guided By Matching with Step-By-Step Recipe Photos |
| Ryo Sobue (Chubu University), Mitsuru Nakazawa (Rakuten Institute of Technology), Yeongnam Chae (Rakuten Institute of Technology), Bjorn Stenger (Rakuten Institute of Technology), Takayoshi Yamashita (Chubu University), Hironobu Fujiyoshi (Chubu University) |
Thursday, May 30, 2019
Oral 5: Motion
| 07-01 | Learning 3D Joint Constraints from Vision based Motion Capture Datasets |
| Pramod Murthy (DFKI, Technische Universität Kaiserslautern), Hammad T. Butt (DFKI, National University of Sciences and Technology), Sandesh Hiremath (Technische Universität Kaiserslautern), Alireza Khoshhal (DFKI), Didier Stricker (DFKI, Technische Universität Kaiserslautern) | |
| 07-02 | Human-Object Maps for Daily Activity Recognition |
| Haruya Ishikawa (Keio University), Yuchi Ishikawa (Keio University), Shuichi Akizuki (Keio University), Yoshimitsu Aoki (Keio University) | |
| 07-03 | Heatmapping of People Involved in Group Activities |
| Kohei Sendo (TTI-J), Norimichi Ukita (TTI-J) | |
| 07-04 | Perspective-Aware Loss Function for Crowd Density Estimation |
| Bedir Yilmaz (National University of Malaysia), Ven Jyn Kok (National University of Malaysia), Mei Kuan Lim (Monash University), Siti Norul Huda Sheikh Abdullah (National University of Malaysia) | |
| 07-05 | Similar Finger Gesture Recognition using Triplet-Loss Networks |
| Gibran Benitez-Garcia (TTI-J), Muhammad Haris (TTI-J), Yoshiyuki Tsuda (DENSO CORPORATION), Norimichi Ukita (TTI-J) | |
| 07-06 | Consolidating Segmentwise Non-Rigid Structure from Motion |
| Vladislav Golyanik (MPI for Informatics, University of Kaiserslautern), André Jonas (University of Kaiserslautern), Didier Stricker (DFKI) |