Accepted Papers

Congratulations to the authors of the following papers, which have been accepted for the ACPR 2019 conference.

Oral Presentation Papers

IDAuthorsTitle
4Henok Ghebrechristos and Gita AlaghbandInformation Theory-Based Curriculum Learning Factory to Optimize Training
8Fatima Zohra Daha and Shishir ShahLearning Motion Regularity for Temporal Video Segmentation and Anomaly Detection
11Clemens-Alexander Brust and Joachim DenzlerIntegrating Domain Knowledge: Using Hierarchies to Improve Deep Classifiers
19Shuchang Lyu, Guangliang Cheng and Qimin DingDeep Similarity Fusion Networks for One-Shot Semantic Segmentation
25Andong Wang, Zhong Jin and Jingyu YangA Factorization Strategy for Tensor Robust PCA
33Yuhao Xiao, Dingding Xu, Guijin Wang, Xiaowei Hu, Yongbing Zhang, Xiangyang Ji and Li ZhangConfidence Map Based 3D Cost Aggregation with Multiple Minimum Spanning Trees for Stereo Matching
35Yujui Chen, Tse-Wei Lin and Chiou-Ting HsuTowards a Universal Appearance for Domain Generalization via Adversarial Learning
40Liang Feng, Hiroaki Igarashi, Seiya Shibata, Yuki Kobayashi, Takashi Takenaka and Wei ZhangReal-time Detection and Tracking using Hybrid DNNs and Space-aware Color Feature: from Algorithm to System
47Qier Meng, Shin'Ichi Satoh and Yohei HashimotoFundus image classification and retinal disease localization with limited supervision
58Shuhei Watanabe, Yoshihiko Ozaki, Yoshiaki Bando and Masaki OnishiSpeeding up of the Nelder-Mead Method by Data-driven Speculative Execution
60Yiming Wan, Wei Gao and Yihong WuOptical Flow Assisted Monocular Visual Odometry
77Sayani Kundu, Shivakumara Palaiahnakote, Anaica Grouver, Umapada Pal, Tong Lu and Michael BlumensteinA New Forged Handwriting Detection Method based on Fourier Spectral Density and Variation
82Runtong Zhang, Yuchen Wu and Keiji YanaiPre-trained and Shared Encoder in Cycle-Consistent Adversarial Networks to Improve Image Quality
94Thomas Dagès, Michael Lindenbaum and Alfred BrucksteinSeeing Things in Random-Dot Videos
106Yasuaki Mori, Tsubasa Hirakawa, Takayoshi Yamashita and Hironobu FujiyoshiCoarse-to-Fine Deep Orientation Estimator for Local Image Matching
112Adil Rahman, Prasun Roy and Umapada PalContinuous Motion Character Recognition using RNN Architecture in Air-Writing Environment
115Zipeng FengOSTER: An Orientation Sensitive Scene Text Recognizer with CenterLine Rectification
119Zezhong Xu, Cheng Qian, Xianju Fei, Yanbing Zhuang, Shibo Xu and Reinhard KletteBoundary Extraction of Planar Segments from Clouds of Unorganised Points
127Yu-Chi Chen, Chia-Yuan Chang, Pei-Yung Hsiao and Li-Chen FuREAL-TIME MULTI-CLASS INSTANCE SEGMENTATION WITH ONE-TIME DEEP EMBEDDING CLUSTERING
134Xianjie Mo, Tingting Wei, Hengmin Zhang, Qiong Huang and Wei LuoLabel-smooth Learning for Fine-grained Visual Categorization
145Tomoyuki Shimizu, Jianfeng Xu and Kazuyuki TasakaMobileGAN: Compact Network Architecture for Generative Adversarial Network
146Yadong Pan and Shoji NishimuraMulti-Person Pose Estimation with Mid-Points for Human Detection under Real-World Surveillance
163Jun'Ichi Murakami and Ikuhisa MitsugamiGaze from Head: Gaze Estimation without Observing Eye
179Yutong Zhou and Nobutaka ShimadaUsing Motion Compensation and Matrix Completion Algorithm to Remove Rain Streaks and Snow for Video Sequences
182Mauricio Perez, Jun Liu and Alex C. KotInteraction Recognition Through Body Parts Relation Reasoning
190Neeraj Battan, Abbhinav Venkat and Avinash SharmaDeepHuMS: Deep Human Motion Signature for 3D Skeletal Sequences
203Dalia Rodríguez-Salas, Nishant Ravikumar, Mathias Seuret and Andreas MaierForestNet - Automatic Design of Sparse Multilayer Perceptron Network Architectures using Ensembles of Randomized Trees
226Chan Tong Lam, Jose Gaspar, Wei Ke, Xu Yang and Sio Kei ImRobust Pedestrian Detection: Faster Deployments with Fusion of Models
229Poonam Beniwal, Pranav Mantini and Shishir K. ShahAssessing the Impact of Video Compression on Background Subtraction
240Nina Tuluptceva, Bart Bakker, Irina Fedulova and Anton KonushinPerceptual Image Anomaly Detection
243Noriko Yokoyama, Masahiro Kohjima, Tatsushi Matsubayashi and Hiroyuki TodaEfficient Bayesian optimization based on parallel sequential random embeddings
253Nobuyuki Hirahara, Motoharu Sonogashira, Hidekazu Kasahara and Masaaki IiyamaDenoising and Inpainting of Sea Surface Temperature Image with Adversarial Physical Model Loss
275Dániel Varga, Sándor Laki, László Dobos, János Márk Szalai-Gindl, Péter Vaderna and Bence FormanekOn Fast Point Cloud Registration with Key Points and Parameter Tuning
278Bertrand Kerautret and Jacques-Olivier LachaudGeometric Total Variation for Image Vectorization, Zooming and Pixel Art Depixelizing
279Zhiwei Wen, Zhiwei Ke, Weicheng Xie and Linlin ShenClustering-based Adaptive Dropout for CNN-based Classification
280Mario Michelini and Helmut MayerDetection of Critical Camera Configurations for Structure from Motion Using Random Forest

Poster Papers

IDAuthorsTitle
1Kevin Kolcheck, Zheyuan Wang, Haiyan Xu and Jiang Yu ZhengVisual Counting of Traffic Flow from A Car via Vehicle Detection and Motion Analysis
13Mofassir Ul Islam Arif, Mohsan Jameel and Lars Schmidt-ThiemeDirectly Optimizing IoU for Bounding Box Localization
15Ivan Kruzhilov, Mikhail Romanov, Dmitry Babichev and Anton KonushinDouble Refinement Network for Room Layout Estimation
16Xiaotian Wu and Yizhuo WangMargin Constraint for Low-Shot Learning
17Floris De Feyter, Kristof Van Beeck and Toon GoedeméEnhancing open-set face recognition by closing it with Cluster-Inferred Gallery Augmentation
22Andrik Rampun, Deborah A. Jarvis, Paul D. Griffiths and Paul ArmitageAutomated 2D Fetal Brain Segmentation of MR images using a Deep U-Net
24Raghavendra Bhalerao, Varsha Kshirsagar and Mitesh RavalFinger Tracking based Tabla syllable Transcription
26Zhiqiang Hou, Lilin Chen and Lei PuDual templates Siamese tracking
36Divya Krishnani, Palaiahnakote Shivakumara, Tong Lu, Umapada Pal and Raghavendra RamachadraStructure Function based Transform Features for Person Behaviour-Oriented Social Media Image Classification
37Ryo Abiko and Masaaki IkeharaSingle Image Reflection Removal based on GAN with Gradient Constraint
41Seo-Hyun Lee, Minji Lee and Seong-Whan LeeEEG Representations of Spatial and Temporal Features in Imagined Speech and Overt Speech
42Soto Anno and Yuichi SasakiGAN-based abnormal detection by recognizing ungeneratable patterns
43Naotsuna Fujimori, Rei Endo, Yoshihiko Kawai and Takahiro MochizukiModality-Specific Learning Rate Control for Multimodal Classification
44Daichi Horita and Keiji YanaiSSA-GAN: End-to-End Time-Lapse Generation with Spatial Self-Attention
48Yuki Furitsu, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase, Hiroki Mukojima and Nozomi NagamineSemantic Segmentation of Railway Images Considering Temporal Continuity
49Dong Cao, Lisha Xu and Haibo ChenAction Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
52Youngbin Kim and Wonjun HwangReal Full Binary Neural Network for Image Classification and Object Detection
53Jaemin Na and Wonjun HwangRepresentation Learning for Style and Content Disentanglement with Autoencoders
56Michal Haindl and Vojtech Havlicek3D Multi-frequency Fully Correlated Causal Random Field Texture Model
59Xulin Song, Jingyu Yang and Zhong JinRESIDUAL ATTENTION ENCODING NEURAL NETWORK FOR TERRAIN TEXTURE CLASSIFICATION
61Shi Yan, Wei Feng, Peng Zhao and Cheng-Lin LiuProgressive Scale Expansion Network with Octave Convolution for Arbitrary Shape Scene Text Detection
64Sourav Sahoo, Puneet Kumar, Balasubramanian Raman and Partha Pratim RoyA Segment Level Approach to Speech Emotion Recognition using Transfer Learning
66Yuan Chang, Donald Bailey and Steven Le MoanThe Shape of Patterns Tells More
67Shuhei TarashimaSFLNet : Direct Sports Field Localization via CNN-based Regression
68Tetsuo Inoshita, Yuichi Nakatani, Katsuhiko Takahashi, Asuka Ishii and Gaku NakanoTrained Model Fusion for Object Detection using Gating Network
70Samaneh Azari, Bing Xue, Mengjie Zhang and Lifeng PengA Decomposition Based Multi-objective Genetic Programming Algorithm for Classification of Highly Imbalanced Tandem Mass Spectrometry
71Kaori Kumagai, Yukito Watanabe, Takashi Hosono, Jun Shimamura and Atsushi SagataUnseen Object Transfiguration with Domain Region and Magnitude Aware GAN
75Ryosuke OdateAutomatic Annotation Method for Document Image Binarization in Real Systems
76Anaica Grouver, Shivakumara Palaiahnakote, Maryam Asadzadeh Kaljahi, Bhaarat Chetty, Umapada Pal, Tong Lu and G. Hemantha KumarA Spatial Density and Phase Angle based Correlation for Forged Family Photo Identification
78Soumyadip Roy, Shivakumara Palaiahnakote, Umapada Pal, Tong Lu and Michael BlumensteinNew Moments based Fuzzy Similarity Measure for Text Detection in Distorted Social Media Images
80Allam Shehata, Yuta Hayashi, Yasushi Makiahra, Daigo Muramatsu and Yasushi YagiDoes My Gait Look Nice? Human Perception-based Gait Relative Attributes Estimation by Dense Trajectory Analysis
81Rushi Babaria and Toru TamakiMeaning guided video captioning
84Honggai Li, Jinshi Cui, Li Wang and Hongbin ZhaInfants Attachment Prediction Using Vision and Audio Features in Mother-Infant Interaction
85Shih-Lun Tseng and Huei-Yung LinFish Detection using Convolutional Neural Networks with Limited Training Data
96Pinaki Nath Chowdhury, Palaiahnakote Shivakumara, Raghavendra Ramachandra, Umapada Pal, Tong Lu and Michael BlumensteinA New U-Net based Enhancement Model for License Plate Detection in Night and Day Images
97Takuya Migishima, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide and Hiroshi MuraseScene-Adaptive Driving Area Prediction based on Automatic Label Acquisition from Driving Information
98Fuma Horie, Hideaki Goto and Takuo SuganumaEnhancing the Ensemble-based Scene Character Recognition by Using Classification Likelihood
99Huanhuan Ji, Zhenbing Liu and Weiqi YanEarly Diagnosis of Alzheimer's Disease Based on Selective Kernel Network with Spatial Attention
103Asato Matsumoto and Keiji YanaiContinual Learning of An Image Transformation Network Using Task-dependent Weight Selection Masks
105Qien Yu, Muthusubash Kavitha and Takio KuritaDetection of One Dimensional Anomalies using a Vector-based Convolutional Autoencoder
110Baek-Woon Yu, Ji-Hoon Jeong, Dae-Hyeok Lee, Taegeun Oh and Seong-Whan LeeDetection of Pilot's Drowsiness based on Multimodal Convolutional Bidirectional LSTM Network
111Daxing Chen and Hongpeng WangAn Attention Module for Multi-Person Pose Estimation
114Asami Ito, Akira Kubota and Kazuya KodamaDeriving Perfect Reconstruction Filter Bank for Focal Stack Refocusing
117Jennie LiorisReal time lane level identification of automotive systems circulating on arbitrary highway stretches
118Mohammad Norouzifard, Joanna Black, Benjamin Thompson, Reinhard Klette and Jason TuruwhenuaA Real-time Eye Tracking Method for Detecting Optokinetic Nystagmus
122Daniel Griffiths, Laleh Badriasl, Tony Scoleri, Russell Brinkworth, Sanjeev Arulampalam and Anthony FinnIntegration of Biologically Inspired Pixel Saliency Estimation and IPDA Filters for Multi-Target Tracking
128Nanyu Sun, Xianjie Mo, Tingting Wei, Dabin Zhang and Wei LuoThe Effectiveness of Noise in Data Augmentation for Fine-grained Image Classification
129Guoqiang Zhong and Guohua YueAttention Recurrent Neural Networks for Image-Based Sequence Text Recognition
130Ningwei Xie, Zhenjiang Miao and Jiaji WangSkeleton-based Labanotation generation using multi-model aggregation
135Baligh Al-Helali, Qi Chen, Bing Xue and Mengjie ZhangGenetic Programming-based Simultaneous Feature Selection and Imputation for Symbolic Regression with Incomplete Data
137Makoto Sei, Akira Utsumi, Hirotake Yamazoe and Joo-Ho LeeNetwork Structure for Personalized Face Pose Estimation Using Incrementally Updated Face Shape Parameters
138Xiaotong Ji, Yuchen Zheng, Daiki Suehiro and Seiichi UchidaOptimal Rejection Function Meets Character Recognition Tasks
142Naoto Kato, Michiko Inoue, Masashi Nishiyama and Yoshio IwaiComparing the Recognition Accuracy of Humans and Deep Learning on a Simple Visual Inspection Task
147Beomhyuk Koo and Gyeonghwan KimNighttime Haze Removal with Glow Decomposition using GAN
148Jaynil Jaiswal, Ashutosh Chaubey, Bhimavarapu Sasi Kiran Reddy, Shashank Kashyap, Puneet Kumar, Balasubramanian Raman and Partha Pratim RoyA Generative Adversarial Network based Ensemble Technique for Automatic Evaluation of Machine Synthesized Speech
151Sukalpa Chanda, Prashant Kumar Prasad, Anders Hast, Anders Brun, Lasse Mårtensson and Umapada PalFinding Logo and Seal in Historical Document Images - An Object Detection based Approach
152Kousuke Sakamoto, Hiroki Yoshimura, Masashi Nishiyama and Yoshio IwaiImproved gamma corrected layered adaptive background model
153Asish Chakrapani Gv, Sukalpa Chanda, Umapada Pal and David DoermannOne-Shot Learning-Based Handwritten Word Recognition
155Ling Zhou, Chunyan Xu and Zhen CuiKIL: knowledge interactiveness Learning for joint depth estimation and semantic segmentation
160En-Te Chou, Yun-Chih Guo, Ya-Hui Tang and Li-Chen FuFirst-Person View Hand Parameter Estimation based on Fully Convolutional Neural Network
167Subhankar Ghosh, Prasun Roy, Saumik Bhattacharya and Umapada PalLarge-Scale Font Identification from Document Images
168Jayani Withanawasam, Ehsan Javanmardi, Kelvin Wong, Mahdi Javanmardi and Shunsuke KamijoRoad scene risk perception for intelligent vehicles using end-to-end affordance learning and visual reasoning
170Xueya Zhang, Tong Zhang, Wenting Zhao and Zhen CuiDual-Attention Graph Convolutional Network
174Kei Shimonishi, Tyler Fisher, Hiroaki Kawashima and Kotaro FunakoshiImage2Height: Self-Height Estimation from a Single-Shot Image
178Ruyi Zhang, Zhenjiang Miao, Cong Ma and Shanshan HaoAggregating Motion and Attention for Video Object Detection
181Lama Tarsissi, David Coeurjolly, Yukiko Kenmochi and Pascal RomonConvexity Preserving Contraction of Digital Sets
185Muhammad Umer Kakli, Yongju Cho and Jeongil SeoParallax-tolerant Video Stitching with Moving Foregrounds
189Kazuki Uehara, Masahiro Murakawa, Hirokazu Nosato and Hidenori SakanashiPrototype-based Interpretation of Pathological Image Analysis by Convolutional Neural Networks
191Kwok Leung ChanSegmentation of foreground in image sequence with foveated vision concept
195Takeo Ishihara, Kento Morita, Nobu C. Shirai, Tetsushi Wakabayashi and Wataru OhyamaChart-type Classification using Convolutional Neural Network for Scholarly Figures
197Xinzhi Liu, Pan Wang, Jun Yu and Toru KuriharaDesign of an optical filter to improve green pepper segmentation using a deep neural network
199Yuki Ohshima and Atsushi NakazawaEye contact detection from Third Person Video
211Jiang He, Yan Song and Haiyu JiangBi-direction Feature Pyramid temporal Action Detection Network
216Hongjian Zhan, Pinaki Nath Chowdhury, Umapada Pal and Yue LuHandwritten Numeral String Recognition for Indian Scripts
220Yusei Suzuki, Hiroya Kawai, Koichi Ito, Takafumi Aoki, Masakazu Fujio, Yosuke Kaga and Kenta TakahashiHand Segmentation for Contactless Palmprint Recognition
221Xinhui Wu, Shiqi Yu Shiqi Yu, Weizhi An, Weiyu Guo and Edel B. Garc´ıaSpatial-Temporal Graph Attention Network for Video-based Gait Recognition
223Liping Xie, Chen Gong, Jinxia Zhang, Shuo Shan and Haikun WeiSemi-supervised Early Event Detection
238Harsh Bhandari, Sarbani Palit and Bhabatosh ChandaSupervised Interactive Co-Segmentation Using Histogram Matching and Bipartite Graph Construction
242Logan Courtney and Ramavarapu SreenivasUsing Deep Convolutional LSTM Networks for Learning Spatiotemporal Features
244Yu-Jung Wang, Motoharu Sonogashira, Atsushi Hashimoto and Masaaki IiyamaTwo-stage Fully Convolutional Networks for Stroke Recovery of Handwritten Chinese Character
246Huy Le, Minh Nguyen and Weiqi YanA Web-based Augmented Reality Approach to Instantly View and Display 4D Medical Images
249Qin Xu, Linyang Li, Qian Chen and Bin LuoSelecting Discriminative Features for Fine-grained Visual Classification
254Hsing-Yu Chen and Shang-Hong LaiGroup Activity Recognition via Computing Human Pose Motion History and Collective Map from Video
257Hung Jin Lin and Shang-Hong LaiDeepRoom: 3D Room Layout and Camera Pose Estimation from a Single Image
262Akansha Tyagi, Ashish Patel and Pratik ShahText Like Classification of Skeletal Sequences for Human Action Recognition
270Sahil Chelaramani, Manish Gupta, Vipul Agarwal, Prashant Gupta and Ranya HabashMulti-Task Learning for Eye Disease Prediction
272Wang Jingming and Kwok Leung ChanBackground subtraction based on Encoder-Decoder Structured CNN
277Hamed Alqahtani and Manolya Kavakli-ThorneMulti facet face construction
282Longbin Jin and Eun Yi KimEEG-based User Identification Using Channel-wise Features