Conference Program

The program of ACPR 2019 will be single track, including keynotes, oral presentations, posters (with 1 minute brief oral presentations before the posters), tutorials, workshops and demos as in previous editions of ACPR.

The proceedings will be published in Springer's Lecture Notes in Computer Science (LNCS, indexed in the ISI Conference Proceedings Citation Index, Scopus, EI Engineering Index, Google Scholar, DBLP, etc.). The proceedings will be available at the conference in electronic form, and published as printed and online LNCS volumes shortly after the conference. Papers in the electronic version of the proceedings available at the conference will not be immediately indexed; only papers presented at the conference will be published in the Springer book and will be indexed. Selected papers will be invited to be submitted to a journal special issue in extended form - details (journals and submission process) will be determined prior to 2020.

The main conference has oral presentations of 15 minutes length (plus 5 minutes for discussion) and poster presentations, also including each a brief oral presentation (1 minute, called a "Poster Spotlight”). For Poster Spotlights, authors are requested to send 1-2 ppt slides to the conference organisers <[email protected]> with the subject "Spotlight IDxx" where xx is your paper number, by 15 November. See the Presenters page for full instructions.


Monday 25 November: Evening Welcome Reception at AUT (Sir Paul Reeves Building)
- 1700: Registration desk opens
- 1830: Welcome reception starts with a traditional welcoming ceremony
- 1900-2030: Drinks and food

Tuesday 26 November: Registration, Workshops and Tutorials at Aotea Centre (Hunua Rooms) and AUT (WG Building, 8th floor)
- 0800: Registration desk opens
- 0900-1700: Workshops and Tutorials
 - 0900-1215: Tutorial 1 - Classic and Deep Vision for Healthcare (Hunua 1 @ Aotea)
  Presenter: Angelica Willes-Rivero
 - 1230-1430: Tutorial 3 - Hands on Geometric Algebra (Hunua 1 @ Aotea)
  Presenter: Stephane Breuils
 - 1445-1800: Tutorial 2 - Digital Geometry in Pattern Recognition (Hunua 1 @ Aotea)
  Presenter: Bertrand Kerautret and Jacques-Olivier Lachaud
 - 0850-1730: Workshop 5 - Image and Pattern Analysis for Multidisciplinary Computational Anatomy (Hunua 2 @ Aotea)
  Organiser: Atsushi Imja
 - 0900-1230: Workshop 6 - Multi-Sensor for Action and Gesture Recognition (Hunua 3 @ Aotea)
  Organiser: Yianyu Yang
 - 1300-1800: Workshop 8 - Towards an Automatic Data Processing Chain for Airborne and Spaceborne Sensors (Hunua 3 @ Aotea)
  Organiser: Ralf Reulke
 - 0850-1230: Workshop 1 - Workshop on Computer Vision for Modern Vehicles (WG 8th Floor @ AUT)
  Organiser: Jinsheng Xiao
 - 0850-1230: Workshop 4 - Advances and Applications on Generative Deep Learning Models (WG 8th Floor @ AUT)
  Organiser: Mariano Rivera
- 1800: ACPR Steering Committee Meeting (with invited speakers)
Evenings are free for gatherings organised by the workshops

Wednesday 27 November: Keynote Speaker, Oral Sessions, Demos, Poster Spotlights and Posters at Aotea Centre
- 0850: Opening
- 0900-1000: Keynote Speaker 1: Andrea Cavallaro, Multimodal Learning for Robust and Privacy Preserving Analytics
Session Chair: Brendan McCane
- 1000-1030: Poster Spotlights: Computer Vision and Robot Vision
Session Chair: Clemens-Alexander Burst
- 1030-1100: Coffee break with posters
- 1100-1220: Oral Session 1: Classification
Session Chair: Michael Blumenstein
- 1220-1400: Lunch with posters
- 1400-1520: Oral Session 2: Action & Video & Motion
Session Chair: Martin Stommel
- 1520-1550: Coffee break with posters
- 1550-1710: Oral Session 3: Object Detection & Anomaly Detection
Session Chair: Shinichi Satoh

Thursday 28 November: Keynote Speaker, Oral Sessions, Demos, Poster Spotlights and Posters at Aotea Centre
- 0900-1000: Keynote Speaker 2: Yihong Wu, Is it Possible to Localize a Camera without Matching?
Session Chair: Seong-Whan Lee
- 1000-1030: Poster Spotlights: Pattern Recognition and Machine Learning
Session Chair: Ke Chen
- 1030-1100: Coffee break with posters
- 1100-1220: Oral Session 4: Segmentation, Grouping & Shape
Session Chair: Michael Haindl
- 1220-1400: Lunch with posters
- 1400-1520: Oral Session 5: Face & Body & Biometrics
Session Chair: Yasushi Makihara
- 1520-1550: Coffee break with posters
- 1550-1710: Oral Session 6: Adversarial Learning & Networks
Session Chair: Balasubramanian Raman
- 1710-1730: Special Session: Presentation of proposal for ACPR 2021
Session Chair: Yasushi Yagi
- 1730-1740: Auction of two Sky Jumps
- 1830-2030: Pre-Dinner Drinks and Nibbles at Sky Cafe, Visit of the Sky Deck
- 2030-2200: Conference Dinner at SkyCity, 3rd Floor, Fortuna Restaurant

Friday 29 November: Keynote Speaker, Oral Sessions, Demos, Poster Spotlights and Posters, Closing Ceremony at Aotea Centre
- 0900-1000: Keynote Speaker 3: Dacheng Tao, AI at Dawn - Opportunities and Challenges
Session Chair: Umapada Pal
- 1000-1030: Poster Spotlights: Multi-media and Signal Processing and Interaction
Session Chair: Masaki Onishi
- 1030-1100: Coffee break with posters
- 1100-1220: Oral Session 7: Computational Photography
Session Chair: Atsushi Imiya
- 1220-1400: Lunch with posters
- 1400-1520: Oral Session 8: Learning Theory & Optimization
Session Chair: Liang Wang
- 1520-1550: Coffee break with posters
- 1550-1710: Oral Session 9: Applications, Medical & Robotics
Session Chair: Bertrand Kerautret
- 1710-1730: Closing Ceremony with best paper awards
- 1730-1930: Survivor's Party with Tracey Collins and Band

Oral Presentation Schedule

Oral Session 1: Classification
Session Chair: Michael Blumenstein
11: Clemens-Alexander Brust and Joachim Denzler. Integrating Domain Knowledge: Using Hierarchies to Improve Deep Classifiers
134: Xianjie Mo, Tingting Wei, Hengmin Zhang, Qiong Huang and Wei Luo. Label-smooth Learning for Fine-grained Visual Categorization
203: Dalia Rodríguez-Salas, Nishant Ravikumar, Mathias Seuret and Andreas Maier. ForestNet - Automatic Design of Sparse Multilayer Perceptron Network Architectures using Ensembles of Randomized Trees
279: Zhiwei Wen, Zhiwei Ke, Weicheng Xie and Linlin Shen. Clustering-based Adaptive Dropout for CNN-based Classification

Oral Session 2: Action & Video & Motion
Session Chair: Martin Stommel
40: Liang Feng, Hiroaki Igarashi, Seiya Shibata, Yuki Kobayashi, Takashi Takenaka and Wei Zhang. Real-time Detection and Tracking using Hybrid DNNs and Space-aware Color Feature: from Algorithm to System
112: Adil Rahman, Prasun Roy and Umapada Pal. Continuous Motion Character Recognition using RNN Architecture in Air-Writing Environment
179: Yutong Zhou and Nobutaka Shimada. Using Motion Compensation and Matrix Completion Algorithm to Remove Rain Streaks and Snow for Video Sequences
229: Poonam Beniwal, Pranav Mantini and Shishir K. Shah. Assessing the Impact of Video Compression on Background Subtraction

Oral Session 3: Object Detection & Anomaly Detection
Session Chair: Shinichi Satoh
8: Fatima Zohra Daha and Shishir Shah. Learning Motion Regularity for Temporal Video Segmentation and Anomaly Detection
77: Sayani Kundu, Shivakumara Palaiahnakote, Anaica Grouver, Umapada Pal, Tong Lu and Michael Blumenstein. A New Forged Handwriting Detection Method based on Fourier Spectral Density and Variation
226: Chan Tong Lam, Jose Gaspar, Wei Ke, Xu Yang and Sio Kei Im. Robust Pedestrian Detection: Faster Deployments with Fusion of Models
240: Nina Tuluptceva, Bart Bakker, Irina Fedulova and Anton Konushin. Perceptual Image Anomaly Detection

Oral Session 4: Segmentation, Grouping & Shape
Session Chair: Michael Haindl
19: Shuchang Lyu, Guangliang Cheng and Qimin Ding. Deep Similarity Fusion Networks for One-Shot Semantic Segmentation
94: Thomas Dagès, Michael Lindenbaum and Alfred Bruckstein. Seeing Things in Random-Dot Videos
119: Zezhong Xu, Cheng Qian, Xianju Fei, Yanbing Zhuang, Shibo Xu and Reinhard Klette. Boundary Extraction of Planar Segments from Clouds of Unorganised Points

Oral Session 5: Face & Body & Biometrics
Session Chair: Yasushi Makihara
146: Yadong Pan and Shoji Nishimura. Multi-Person Pose Estimation with Mid-Points for Human Detection under Real-World Surveillance
163: Jun'Ichi Murakami and Ikuhisa Mitsugami. Gaze from Head: Gaze Estimation without Observing Eye
182: Mauricio Perez, Jun Liu and Alex C. Kot. Interaction Recognition Through Body Parts Relation Reasoning
190: Neeraj Battan, Abbhinav Venkat and Avinash Sharma. DeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences

Oral Session 6: Adversarial Learning & Networks
Session Chair: Balasubramanian Raman
35: Yujui Chen, Tse-Wei Lin and Chiou-Ting Hsu. Towards a Universal Appearance for Domain Generalization via Adversarial Learning
82: Runtong Zhang, Yuchen Wu and Keiji Yanai. Pre-trained and Shared Encoder in Cycle-Consistent Adversarial Networks to Improve Image Quality
145: Tomoyuki Shimizu, Jianfeng Xu and Kazuyuki Tasaka. MobileGAN: Compact Network Architecture for Generative Adversarial Network
253: Nobuyuki Hirahara, Motoharu Sonogashira, Hidekazu Kasahara and Masaaki Iiyama. Denoising and Inpainting of Sea Surface Temperature Image with Adversarial Physical Model Loss

Oral Session 7: Computational Photography
Session Chair: Atsushi Imiya
33: Yuhao Xiao, Dingding Xu, Guijin Wang, Xiaowei Hu, Yongbing Zhang, Xiangyang Ji and Li Zhang. Confidence Map Based 3D Cost Aggregation with Multiple Minimum Spanning Trees for Stereo Matching
60: Yiming Wan, Wei Gao and Yihong Wu. Optical Flow Assisted Monocular Visual Odometry
106: Yasuaki Mori, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu Fujiyoshi. Coarse-to-Fine Deep Orientation Estimator for Local Image Matching
278: Bertrand Kerautret and Jacques-Olivier Lachaud. Geometric Total Variation for Image Vectorization, Zooming and Pixel Art Depixelizing

Oral Session 8: Learning Theory & Optimization
Session Chair: Liang Wang
4: Henok Ghebrechristos and Gita Alaghband. Information Theory-Based Curriculum Learning Factory to Optimize Training
25: Andong Wang, Zhong Jin and Jingyu Yang. A Factorization Strategy for Tensor Robust PCA
58: Shuhei Watanabe, Yoshihiko Ozaki, Yoshiaki Bando and Masaki Onishi. Speeding up of the Nelder-Mead Method by Data-driven Speculative Execution
243: Noriko Yokoyama, Masahiro Kohjima, Tatsushi Matsubayashi and Hiroyuki Toda. Efficient Bayesian optimization based on parallel sequential random embeddings

Oral Session 9: Applications, Medical & Robotics
Session Chair: Bertrand Kerautret
47: Qier Meng, Shin'Ichi Satoh and Yohei Hashimoto. Fundus image classification and retinal disease localization with limited supervision
115: Zipeng Feng. OSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine Rectification
275: Dániel Varga, Sándor Laki, László Dobos, János Márk Szalai-Gindl, Péter Vaderna and Bence Formanek. On Fast Point Cloud Registration with Key Points and Parameter Tuning
280: Mario Michelini and Helmut Mayer. Detection of Critical Camera Configurations for Structure from Motion Using Random Forest

Poster Schedule

Wednesday: Computer Vision and Robot Vision
Session Chair: Clemens-Alexander Burst
1: Kevin Kolcheck, Zheyuan Wang, Haiyan Xu and Jiang Yu Zheng. Visual Counting of Traffic Flow from A Car via Vehicle Detection and Motion Analysis
13: Mofassir Ul Islam Arif, Mohsan Jameel and Lars Schmidt-Thieme. Directly Optimizing IoU for Bounding Box Localization
15: Ivan Kruzhilov, Mikhail Romanov, Dmitry Babichev and Anton Konushin. Double Refinement Network for Room Layout Estimation
24: Raghavendra Bhalerao, Varsha Kshirsagar and Mitesh Raval. Finger Tracking based Tabla syllable Transcription
26: Zhiqiang Hou, Lilin Chen and Lei Pu. Dual templates Siamese tracking
36: Divya Krishnani, Palaiahnakote Shivakumara, Tong Lu, Umapada Pal and Raghavendra Ramachadra. Structure Function based Transform Features for Person Behaviour-Oriented Social Media Image Classification
37: Ryo Abiko and Masaaki Ikehara. Single Image Reflection Removal based on GAN with Gradient Constraint
44: Daichi Horita and Keiji Yanai. SSA-GAN: End-to-End Time-Lapse Generation with Spatial Self-Attention
48: Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukojima and Nozomi Nagamine. Semantic Segmentation of Railway Images Considering Temporal Continuity
52: Youngbin Kim and Wonjun Hwang. Real Full Binary Neural Network for Image Classification and Object Detection
61: Shi Yan, Wei Feng, Peng Zhao and Cheng-Lin Liu. Progressive Scale Expansion Network with Octave Convolution for Arbitrary Shape Scene Text Detection
67: Shuhei Tarashima. SFLNet : Direct Sports Field Localization via CNN-based Regression
68: Tetsuo Inoshita, Yuichi Nakatani, Katsuhiko Takahashi, Asuka Ishii and Gaku Nakano. Trained Model Fusion for Object Detection using Gating Network
71: Kaori Kumagai, Yukito Watanabe, Takashi Hosono, Jun Shimamura and Atsushi Sagata. Unseen Object Transfiguration with Domain Region and Magnitude Aware GAN
78: Soumyadip Roy, Shivakumara Palaiahnakote, Umapada Pal, Tong Lu and Michael Blumenstein. New Moments based Fuzzy Similarity Measure for Text Detection in Distorted Social Media Images
85: Shih-Lun Tseng and Huei-Yung Lin. Fish Detection using Convolutional Neural Networks with Limited Training Data
96: Pinaki Nath Chowdhury, Palaiahnakote Shivakumara, Raghavendra Ramachandra, Umapada Pal, Tong Lu and Michael Blumenstein. A New U-Net based Enhancement Model for License Plate Detection in Night and Day Images
122: Daniel Griffiths, Laleh Badriasl, Tony Scoleri, Russell Brinkworth, Sanjeev Arulampalam and Anthony Finn. Integration of Biologically Inspired Pixel Saliency Estimation and IPDA Filters for Multi-Target Tracking
128: Nanyu Sun, Xianjie Mo, Tingting Wei, Dabin Zhang and Wei Luo. The Effectiveness of Noise in Data Augmentation for Fine-grained Image Classification
129: Guoqiang Zhong and Guohua Yue. Attention Recurrent Neural Networks for Image-Based Sequence Text Recognition
147: Beomhyuk Koo and Gyeonghwan Kim. Nighttime Haze Removal with Glow Decomposition using GAN
151: Sukalpa Chanda, Prashant Kumar Prasad, Anders Hast, Anders Brun, Lasse Mårtensson and Umapada Pal. Finding Logo and Seal in Historical Document Images - An Object Detection based Approach
155: Ling Zhou, Chunyan Xu and Zhen Cui. KIL: knowledge interactiveness Learning for joint depth estimation and semantic segmentation
168: Jayani Withanawasam, Ehsan Javanmardi, Kelvin Wong, Mahdi Javanmardi and Shunsuke Kamijo. Road scene risk perception for intelligent vehicles using end-to-end affordance learning and visual reasoning
174: Kei Shimonishi, Tyler Fisher, Hiroaki Kawashima and Kotaro Funakoshi. Image2Height: Self-Height Estimation from a Single-Shot Image
191: Kwok Leung Chan. Segmentation of foreground in image sequence with foveated vision concept
211: Jiang He, Yan Song and Haiyu Jiang. Bi-direction Feature Pyramid temporal Action Detection Network
220: Yusei Suzuki, Hiroya Kawai, Koichi Ito, Takafumi Aoki, Masakazu Fujio, Yosuke Kaga and Kenta Takahashi. Hand Segmentation for Contactless Palmprint Recognition
249: Qin Xu, Linyang Li, Qian Chen and Bin Luo. Selecting Discriminative Features for Fine-grained Visual Classification

Thursday: Pattern Recognition and Machine Learning
Session Chair: Ke Chen
16: Xiaotian Wu and Yizhuo Wang. Margin Constraint for Low-Shot Learning
17: Floris De Feyter, Kristof Van Beeck and Toon Goedemé. Enhancing open-set face recognition by closing it with Cluster-Inferred Gallery Augmentation
49: Dong Cao, Lisha Xu and Haibo Chen. Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
53: Jaemin Na and Wonjun Hwang. Representation Learning for Style and Content Disentanglement with Autoencoders
66: Yuan Chang, Donald Bailey and Steven Le Moan. The Shape of Patterns Tells More
76: Anaica Grouver, Shivakumara Palaiahnakote, Maryam Asadzadeh Kaljahi, Bhaarat Chetty, Umapada Pal, Tong Lu and G. Hemantha Kumar. A Spatial Density and Phase Angle based Correlation for Forged Family Photo Identification
80: Allam Shehata, Yuta Hayashi, Yasushi Makiahra, Daigo Muramatsu and Yasushi Yagi. Does My Gait Look Nice? Human Perception-based Gait Relative Attributes Estimation by Dense Trajectory Analysis
97: Takuya Migishima, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide and Hiroshi Murase. Scene-Adaptive Driving Area Prediction based on Automatic Label Acquisition from Driving Information
98: Fuma Horie, Hideaki Goto and Takuo Suganuma. Enhancing the Ensemble-based Scene Character Recognition by Using Classification Likelihood
103: Asato Matsumoto and Keiji Yanai. Continual Learning of An Image Transformation Network Using Task-dependent Weight Selection Masks
111: Daxing Chen and Hongpeng Wang. An Attention Module for Multi-Person Pose Estimation
117: Jennie Lioris. Real time lane level identification of automotive systems circulating on arbitrary highway stretches
118: Mohammad Norouzifard, Joanna Black, Benjamin Thompson, Reinhard Klette and Jason Turuwhenua. A Real-time Eye Tracking Method for Detecting Optokinetic Nystagmus
137: Makoto Sei, Akira Utsumi, Hirotake Yamazoe and Joo-Ho Lee. Network Structure for Personalized Face Pose Estimation Using Incrementally Updated Face Shape Parameters
138: Xiaotong Ji, Yuchen Zheng, Daiki Suehiro and Seiichi Uchida. Optimal Rejection Function Meets Character Recognition Tasks
142: Naoto Kato, Michiko Inoue, Masashi Nishiyama and Yoshio Iwai. Comparing the Recognition Accuracy of Humans and Deep Learning on a Simple Visual Inspection Task
152: Kousuke Sakamoto, Hiroki Yoshimura, Masashi Nishiyama and Yoshio Iwai. Improved gamma corrected layered adaptive background model
153: Asish Chakrapani Gv, Sukalpa Chanda, Umapada Pal and David Doermann. One-Shot Learning-Based Handwritten Word Recognition
160: En-Te Chou, Yun-Chih Guo, Ya-Hui Tang and Li-Chen Fu. First-Person View Hand Parameter Estimation based on Fully Convolutional Neural Network
170: Xueya Zhang, Tong Zhang, Wenting Zhao and Zhen Cui. Dual-Attention Graph Convolutional Network
195: Takeo Ishihara, Kento Morita, Nobu C. Shirai, Tetsushi Wakabayashi and Wataru Ohyama. Chart-type Classification using Convolutional Neural Network for Scholarly Figures
216: Hongjian Zhan, Pinaki Nath Chowdhury, Umapada Pal and Yue Lu. Handwritten Numeral String Recognition for Indian Scripts
221: Xinhui Wu, Shiqi Yu Shiqi Yu, Weizhi An, Weiyu Guo and Edel B. Garc´ıa. Spatial-Temporal Graph Attention Network for Video-based Gait Recognition
238: Harsh Bhandari, Sarbani Palit and Bhabatosh Chanda. Supervised Interactive Co-Segmentation Using Histogram Matching and Bipartite Graph Construction
242: Logan Courtney and Ramavarapu Sreenivas. Using Deep Convolutional LSTM Networks for Learning Spatiotemporal Features
244: Yu-Jung Wang, Motoharu Sonogashira, Atsushi Hashimoto and Masaaki Iiyama. Two-stage Fully Convolutional Networks for Stroke Recovery of Handwritten Chinese Character
262: Akansha Tyagi, Ashish Patel and Pratik Shah. Text Like Classification of Skeletal Sequences for Human Action Recognition
272: Wang Jingming and Kwok Leung Chan. Background subtraction based on Encoder-Decoder Structured CNN
277: Hamed Alqahtani and Manolya Kavakli-Thorne. Multi facet face construction

Friday: Multi-media and Signal Processing and Interaction
Session Chair: Masaki Onishi
22: Andrik Rampun, Deborah A. Jarvis, Paul D. Griffiths and Paul Armitage. Automated 2D Fetal Brain Segmentation of MR images using a Deep U-Net
41: Seo-Hyun Lee, Minji Lee and Seong-Whan Lee. EEG Representations of Spatial and Temporal Features in Imagined Speech and Overt Speech
42: Soto Anno and Yuichi Sasaki. GAN-based abnormal detection by recognizing ungeneratable patterns
43: Naotsuna Fujimori, Rei Endo, Yoshihiko Kawai and Takahiro Mochizuki. Modality-Specific Learning Rate Control for Multimodal Classification
56: Michal Haindl and Vojtech Havlicek. 3D Multi-frequency Fully Correlated Causal Random Field Texture Model
64: Sourav Sahoo, Puneet Kumar, Balasubramanian Raman and Partha Pratim Roy. A Segment Level Approach to Speech Emotion Recognition using Transfer Learning
70: Samaneh Azari, Bing Xue, Mengjie Zhang and Lifeng Peng. A Decomposition Based Multi-objective Genetic Programming Algorithm for Classification of Highly Imbalanced Tandem Mass Spectrometry
75: Ryosuke Odate. Automatic Annotation Method for Document Image Binarization in Real Systems
81: Rushi Babaria and Toru Tamaki. Meaning guided video captioning
84: Honggai Li, Jinshi Cui, Li Wang and Hongbin Zha. Infants Attachment Prediction Using Vision and Audio Features in Mother-Infant Interaction
99: Huanhuan Ji, Zhenbing Liu and Weiqi Yan. Early Diagnosis of Alzheimer's Disease Based on Selective Kernel Network with Spatial Attention
105: Qien Yu, Muthusubash Kavitha and Takio Kurita. Detection of One Dimensional Anomalies using a Vector-based Convolutional Autoencoder
110: Baek-Woon Yu, Ji-Hoon Jeong, Dae-Hyeok Lee, Taegeun Oh and Seong-Whan Lee. Detection of Pilot’s Drowsiness based on Multimodal Convolutional Bidirectional LSTM Network
114: Asami Ito, Akira Kubota and Kazuya Kodama. Deriving Perfect Reconstruction Filter Bank for Focal Stack Refocusing
130: Ningwei Xie, Zhenjiang Miao and Jiaji Wang. Skeleton-based Labanotation generation using multi-model aggregation
135: Baligh Al-Helali, Qi Chen, Bing Xue and Mengjie Zhang. Genetic Programming-based Simultaneous Feature Selection and Imputation for Symbolic Regression with Incomplete Data
148: Jaynil Jaiswal, Ashutosh Chaubey, Bhimavarapu Sasi Kiran Reddy, Shashank Kashyap, Puneet Kumar, Balasubramanian Raman and Partha Pratim Roy. A Generative Adversarial Network based Ensemble Technique for Automatic Evaluation of Machine Synthesized Speech
167: Subhankar Ghosh, Prasun Roy, Saumik Bhattacharya and Umapada Pal. Large-Scale Font Identification from Document Images
178: Ruyi Zhang, Zhenjiang Miao, Cong Ma and Shanshan Hao. Aggregating Motion and Attention for Video Object Detection
181: Lama Tarsissi, David Coeurjolly, Yukiko Kenmochi and Pascal Romon. Convexity Preserving Contraction of Digital Sets
185: Muhammad Umer Kakli, Yongju Cho and Jeongil Seo. Parallax-tolerant Video Stitching with Moving Foregrounds
189: Kazuki Uehara, Masahiro Murakawa, Hirokazu Nosato and Hidenori Sakanashi. Prototype-based Interpretation of Pathological Image Analysis by Convolutional Neural Networks
197: Xinzhi Liu, Pan Wang, Jun Yu and Toru Kurihara. Design of an optical filter to improve green pepper segmentation using a deep neural network
199: Yuki Ohshima and Atsushi Nakazawa. Eye contact detection from Third Person Video
223: Liping Xie, Chen Gong, Jinxia Zhang, Shuo Shan and Haikun Wei. Semi-supervised Early Event Detection
246: Huy Le, Minh Nguyen and Weiqi Yan. A Web-based Augmented Reality Approach to Instantly View and Display 4D Medical Images
254: Hsing-Yu Chen and Shang-Hong Lai. Group Activity Recognition via Computing Human Pose Motion History and Collective Map from Video
257: Hung Jin Lin and Shang-Hong Lai. DeepRoom: 3D Room Layout and Camera Pose Estimation from a Single Image
270: Sahil Chelaramani, Manish Gupta, Vipul Agarwal, Prashant Gupta and Ranya Habash. Multi-Task Learning for Eye Disease Prediction
282: Longbin Jin and Eun Yi Kim. EEG-based User Identification Using Channel-wise Features