| Description |
1 online resource (xxv, 767 pages) : illustrations (some color) |
| Series |
Lecture notes in computer science ; 12047 |
|
LNCS sublibrary. SL 6, Image processing, computer vision, pattern recognition, and graphics |
|
Lecture notes in computer science ; 12047.
|
|
LNCS sublibrary. SL 6, Image processing, computer vision, pattern recognition, and graphics.
|
| Contents |
[I]. Pattern recognition and machine learning: Margin constraint for low-shot learning / Xiaotian Wu Yizhuo Wang -- Enhancing open-set face recognition by closing it with cluster-inferred gallery augmentation / Floris De Feyter, Kristof Van Beeck, Toon Goedemé -- Action recognition in untrimmed videos with composite self-attention two-stream framework / Dong Cao, Lisha Xu, HaiBo Chen -- Representation learning for style and content disentanglement with autoencoders / Jaemin Na, Wonjun Hwang -- Residual attention encoding neural network for terrain texture classification / Xulin Song, Jingyu Yang, Zhong Jin -- The shape of patterns tells more / Yuan Chang, Donald Bailey, Steven Le Moan -- A spatial density and phase angle based correlation for multi-type family photo identification / Anaica Grouver, Palaiahnakote Shivakumara, Maryam Asadzadeh Kaljahi, Bhaarat Chetty, Umapada Pal, Tong Lu et al. -- Does my gait look nice? Human perception-based gait relative attribute estimation using dense trajectory analysis / Allam Shehata, Yuta Hayashi, Yasushi Makihara, Daigo Muramatsu, Yasushi Yagi -- Scene-adaptive driving area prediction based on automatic label acquisition from driving information / Takuya Migishima, Haruya Kyutoku, Daisuke Deguchi, Yasutomo Kawanishi, Ichiro Ide, Hiroshi Murase -- Enhancing the ensemble-based scene character recognition by using classification likelihood / Fuma Horie, Hideaki Goto, Takuo Suganuma -- Continual learning of image translation networks using task-dependent weight selection masks / Asato Matsumoto, Keiji Yanai -- A real-time eye tracking method for detecting optokinetic nystagmus / Mohammad Norouzifard, Joanna Black, Benjamin Thompson, Reinhard Klette, Jason Turuwhenua -- Network structure for personalized face-pose estimation using incrementally updated face-shape parameters / Makoto Sei, Akira Utsumi, Hirotake Yamazoe, Joo-Ho Lee |
|
Optimal rejection function meets character recognition tasks / Xiaotong Ji, Yuchen Zheng, Daiki Suehiro, Seiichi Uchida -- Comparing the recognition accuracy of humans and deep learning on a simple visual inspection task / Naoto Kato, Michiko Inoue, Masashi Nishiyama, Yoshio Iwai -- Improved gamma corrected layered adaptive background model / Kousuke Sakamoto, Hiroki Yoshimura, Masashi Nishiyama, Yoshio Iwai -- One-shot learning-based handwritten word recognition / Asish Chakrapani Gv, Sukalpa Chanda, Umapada Pal, David Doermann -- First-person view hand parameter estimation based on fully convolutional neural network / En-Te Chou, Yun-Chih Guo, Ya-Hui Tang, Pei-Yung Hsiao, Li-Chen Fu -- Dual-attention graph convolutional network / Xueya Zhang, Tong Zhang, Wenting Zhao, Zhen Cui, Jian Yang -- Chart-type classification using convolutional neural network for scholarly figures / Takeo Ishihara, Kento Morita, Nobu C. Shirai, Tetsushi Wakabayashi, Wataru Ohyama -- Handwritten digit string recognition for Indian scripts / Hongjian Zhan, Pinaki Nath Chowdhury, Umapada Pal, Yue Lu -- Spatial-temporal graph attention network for video-based gait recognition / Xinhui Wu, Weizhi An, Shiqi Yu, Weiyu Guo, Edel B. García -- Supervised interactive co-segmentation using histogram matching and bipartite graph construction / Harsh Bhandari, Sarbani Palit, Bhabatosh Chanda -- Using deep convolutional LSTM networks for learning spatiotempoal features / Logan Courtney, Ramavarapu Sreenivas -- Two-stage fully convolutional networks for stroke recovery of handwritten Chinese character / Yujung Wang, Motoharu Sonogashira, Atsushi Hashimoto, Masaaki Iiyama |
|
Text like classification of skeletal sequences for human action recognition / Akansha Tyagi, Ashish Patel, Pratik Shah -- Background subtraction based on encoder-decoder structured CNN / Jingming Wang, Kwok Leung Chan -- Multi facet face construction / Hamed Alqahtani, Manolya Kavakli-Thorne |
|
[II]. Multi-media and signal processing and interaction: Automated 2D fetal brain segmentation of MR images using a deep U-net / Andrik Rampun, Deborah Jarvis, Paul Griffiths, Paul Armitage -- EEG representations of spatial and temporal features in imagined speech and overt speech / Seo-Hyun Lee, Minji Lee, Seong-Whan Lee -- GAN-based abnormal detection by recognizing ungeneratable patterns / Soto Anno, Yuichi Sasaki -- Modality-specific learning rate control for multimodal classification / Naotsuna Fujimori, Rei Endo, Yoshihiko Kawai, Takahiro Mochizuki -- 3D multi-frequency fully correlated causal random field texture model / Michal Haindl, Vojtěch Havlíček -- A segment level approach to speech emotion recognition using transfer learning / Sourav Sahoo, Puneet Kumar, Balasubramanian Raman, Partha Pratim Roy -- A decomposition based multi-objective genetic programming algorithm for classification of highly imbalanced tandem mass spectrometry / Samaneh Azari, Bing Xue, Mengjie Zhang, Lifeng Peng -- Automatic annotation method for document image binarization in real systems / Ryosuke Odate |
|
Meaning guided video captioning / Rushi J. Babariya, Toru Tamaki -- Infant attachment prediction using vision and audio features in mother-infant interaction / Honggai Li, Jinshi Cui, Li Wang, Hongbin Zha -- Early diagnosis of Alzheimer's disease based on selective kernel network with spatial attention / Huanhuan Ji, Zhenbing Liu, Wei Qi Yan, Reinhard Klette -- Detection of one dimensional anomalies using a vector-based convolutional autoencoder / Qien Yu, Muthusubash Kavitha, Takio Kurita -- Detection of pilot's drowsiness based on multimodal convolutional bidirectional LSTM network / Baek-Woon Yu, Ji-Hoon Jeong, Dae-Hyeok Lee, Seong-Whan Lee -- Deriving perfect reconstruction filter bank for focal stack refocusing / Asami Ito, Akira Kubota, Kazuya Kodama -- Skeleton-based labanotation generation using multi-model aggregation / Ningwei Xie, Zhenjiang Miao, Jiaji Wang -- Genetic programming-based simultaneous feature selection and imputation for symbolic regression with incomplete data / Baligh Al-Helali, Qi Chen, Bing Xue, Mengjie Zhang -- A generative adversarial network based ensemble technique for automatic evaluation of machine synthesized speech / Jaynil Jaiswal, Ashutosh Chaubey, Sasi Kiran Reddy Bhimavarapu, Shashank Kashyap, Puneet Kumar, Balasubramanian Raman et al. -- Large-scale font identification from document images / Subhankar Ghosh, Prasun Roy, Saumik Bhattacharya, Umapada Pal -- Aggregating motion and attention for video object detection / Ruyi Zhang, Zhenjiang Miao, Cong Ma, Shanshan Hao -- Convexity preserving contraction of digital sets / Lama Tarsissi, David Coeurjolly, Yukiko Kenmochi, Pascal Romon -- Parallax-tolerant video stitching with moving foregrounds / Muhammad Umer Kakli, Yongju Cho, Jeongil Seo |
|
Prototype-based interpretation of pathological image analysis by convolutional neural networks / Kazuki Uehara, Masahiro Murakawa, Hirokazu Nosato, Hidenori Sakanashi -- Design of an optical filter to improve green pepper segmentation using a deep neural network / Jun Yu, Xinzhi Liu, Pan Wang, Toru Kurihara -- Eye contact detection from third person video / Yuki Ohshima, Atsushi Nakazawa -- Semi-supervised early event detection / Liping Xie, Chen Gong, Jinxia Zhang, Shuo Shan, Haikun Wei -- A web-based augmented reality approach to instantly view and display 4D medical images / Huy Le, Minh Nguyen, Wei Qi Yan -- Group activity recognition via computing human pose motion history and collective map from video / Hsing-Yu Chen, Shang-Hong Lai -- DeepRoom : 3D room layout and pose estimation from a single image / Hung Jin Lin, Shang-Hong Lai -- Multi-task learning for fine-grained eye disease prediction / Sahil Chelaramani, Manish Gupta, Vipul Agarwal, Prashant Gupta, Ranya Habash -- EEG-based user identification using channel-wise features / Longbin Jin, Jaeyoung Chang, Eunyi Kim |
| Summary |
This two-volume set constitutes the proceedings of the 5th Asian Conference on ACPR 2019, held in Auckland, New Zealand, in November 2019. The 9 full papers presented in this volume were carefully reviewed and selected from 14 submissions. They cover topics such as: classification; action and video and motion; object detection and anomaly detection; segmentation, grouping and shape; face and body and biometrics; adversarial learning and networks; computational photography; learning theory and optimization; applications, medical and robotics; computer vision and robot vision; pattern recognition and machine learning; multi-media and signal processing and interaction |
| Notes |
Includes author index |
| Subject |
Pattern recognition systems -- Congresses
|
|
Computer vision -- Congresses
|
|
Signal processing -- Congresses
|
|
Computer vision
|
|
Pattern recognition systems
|
|
Signal processing
|
| Genre/Form |
proceedings (reports)
|
|
Conference papers and proceedings
|
|
Conference papers and proceedings.
|
|
Actes de congrès.
|
| Form |
Electronic book
|
| Author |
Palaiahnakote, Shivakumara.
|
|
Sanniti di Baja, Gabriella.
|
|
Wang, Liang
|
|
Yan, Wei Qi
|
| ISBN |
9783030412999 |
|
3030412997 |
|
