TAG 論文

「論文」に関する記事。大学や企業など多様な主体が、AIに関する開発・批評などを行い論文として発表している。

7月28日に公開された論文


ニューラルネットワーク


自然言語処理

Detecting and Explaining Causes From Text For a Time Series Event
著者:Dongyeop Kang, Varun Gangal, Ang Lu, Zheng Chen, Eduard Hovy
SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set
著者:William Havard, Laurent Besacier, Olivier Rosec
From Type Spaces to Probability Frames and Back, via Language
著者:Adam Bjorndahl, Joseph Y. Halpern

画像解析

Representation-Aggregation Networks for Segmentation of Multi-Gigapixel Histology Images
著者:Abhinav Agarwalla, Muhammad Shaban, Nasir M. Rajpoot
Relative Depth Order Estimation Using Multi-scale Densely Connected Convolutional Networks
著者:Ruoxi Deng, Tianqi Zhao, Chunhua Shen, Shengjun Liu

強化学習

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
著者:Matej Večerík, Todd Hester, Jonathan Scholz, Fumin Wang, Olivier Pietquin, Bilal Piot, Nicolas Heess, Thomas Rothörl, Thomas Lampe, Martin Riedmiller
"> キュレーション

【7月28日 更新分】機械学習に関する論文まとめ

7月28日に公開された論文 ニューラルネットワーク Deep Residual Learning for Weakly-Supervised Relation Extraction 著者:Yi Yao Huang, Wi…

7月27日に公開された論文


ニューラルネットワーク

Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition
著者:Shizhong Han, Zibo Meng, "James OReilly", Jie Cai, Xiaofeng Wang, Yan Tong

自然言語処理

Implicit Entity Linking in Tweets
著者:Sujan Perera, Pablo N. Mendes, Adarsh Alex, Amit Sheth, Krishnaprasad Thirunarayan
Determining Semantic Textual Similarity using Natural Deduction Proofs
著者:Hitomi Yanaka, Koji Mineshima, Pascual Martinez-Gomez, Daisuke Bekki

画像解析

Exploiting Web Images for Weakly Supervised Object Detection
著者:Qingyi Tao, Hao Yang, Jianfei Cai
Maximum entropy based non-negative optoacoustic tomographic image reconstruction
著者:Jaya Prakash, Subhamoy Mandal, Daniel Razansky, Vasilis Ntziachristos
Deep Interactive Region Segmentation and Captioning
著者:Ali Sharifi Boroujerdi, Maryam Khanian, Michael Breuss
RankIQA: Learning from Rankings for No-reference Image Quality Assessment
著者:Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov
Structure-Preserving Image Super-resolution via Contextualized Multi-task Learning
著者:Yukai Shi, Keze Wang, Chongyu Chen, Li Xu, Liang Lin
Residual Conv-Deconv Grid Network for Semantic Segmentation
著者:Damien Fourure, Rémi Emonet, Elisa Fromont, Damien Muselet, Alain Tremeau, Christian Wolf
Towards Accurate Markerless Human Shape and Pose Estimation over Time
著者:Yinghao Huang, Federica Bogo, Christoph Classner, Angjoo Kanazawa, Peter V. Gehler, Ijaz Akhter, Michael J. Black

音声解析

Learning Audio Sequence Representations for Acoustic Event Classification
著者:Zixing Zhang, Ding Liu, Jing Han, Björn Schuller

強化学習

Guiding Reinforcement Learning Exploration Using Natural Language
著者:Brent Harrison, Upol Ehsan, Mark O. Riedl
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
著者:Irina Higgins, Arka Pal, Andrei A. Rusu, Loic Matthey, Christopher P Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, Alexander Lerchner
"> キュレーション

【7月27日 更新分】機械学習に関する論文まとめ

7月27日に公開された論文 ニューラルネットワーク Enabling Efficient Question Answer Retrieval via Hyperbolic Neural Networks 著者:Yi Ta…

7月26日に公開された論文


ニューラルネットワーク


自然言語処理

Structural Regularities in Text-based Entity Vector Spaces
著者:Christophe Van Gysel, Maarten de Rijke, Evangelos Kanoulas
The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations
著者:Nikita Nangia, Adina Williams, Angeliki Lazaridou, Samuel R. Bowman
Challenges in Data-to-Document Generation
著者:Sam Wiseman, Stuart M. Shieber, Alexander M. Rush

画像解析

Graph-Based Classification of Omnidirectional Images
著者:Renata Khasanova, Pascal Frossard
Patch-based Carcinoma Detection on Confocal Laser Endomicroscopy Images - A Cross-Site Robustness Assessment
著者:Marc Aubreville, Miguel Goncalves, Christian Knipfer, Nicolai Oetter, Tobias Wuerfl, Helmut Neumann, Florian Stelzle, Christopher Bohr, Andreas Maier
Automatic Image Transformation for Inducing Affect
著者:Afsheen Rafaqat Ali, Mohsen Ali
Automatic Liver Segmentation Using an Adversarial Image-to-Image Network
著者:Dong Yang, Daguang Xu, S. Kevin Zhou, Bogdan Georgescu, Mingqing Chen, Sasa Grbic, Dimitris Metaxas, Dorin Comaniciu
Spatiotemporal Modeling for Crowd Counting in Videos
著者:Feng Xiong, Xingjian Shi, Dit-Yan Yeung
"> キュレーション

【7月26日 更新分】機械学習に関する論文まとめ

7月26日に公開された論文 ニューラルネットワーク Efficient Yet Deep Convolutional Neural Networks for Semantic Segmentation 著者:Sharif…

7月25日に公開された論文


ニューラルネットワーク

Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in End-to-End Question Answering
著者:Royal Sequiera, Gaurav Baruah, Zhucheng Tu, Salman Mohammed, Jinfeng Rao, Haotian Zhang, Jimmy Lin
Deep Architectures for Neural Machine Translation
著者:Antonio Valerio Miceli Barone, Jindřich Helcl, Rico Sennrich, Barry Haddow, Alexandra Birch

自然言語処理

Modeling Label Ambiguity for Neural List-Wise Learning to Rank
著者:Rolf Jagerman, Julia Kiseleva, Maarten de Rijke
Relational Learning and Feature Extraction by Querying over Heterogeneous Information Networks
著者:Parisa Kordjamshidi, Sameer Singh, Daniel Khashabi, Christos Christodoulopoulos, Mark Summons, Saurabh Sinha, Dan Roth
Towards Semantic Query Segmentation
著者:Ajinkya Kale, Thrivikrama Taula, Sanjika Hewavitharana, Amit Srivastava
AMR Parsing using Stack-LSTMs
著者:Miguel Ballesteros, Yaser Al-Onaizan
Image Pivoting for Learning Multilingual Multimodal Representations
著者:Spandana Gella, Rico Sennrich, Frank Keller, Mirella Lapata
Character-level Intra Attention Network for Natural Language Inference
著者:Han Yang, Marta R. Costa-jussà, José A. R. Fonollosa

画像解析

Linear Discriminant Generative Adversarial Networks
著者:Zhun Sun, Mete Ozay, Takayuki Okatani
ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features
著者:Inwan Yoo, David G. C. Hildebrand, Willie F. Tobin, Wei-Chung Allen Lee, Won-Ki Jeong
Towards Accurate Markerless Human Shape and Pose Estimation over Time
著者:Yinghao Huang, Federica Bogo, Christoph Classner, Angjoo Kanazawa, Peter V. Gehler, Ijaz Akhter, Michael J. Black
Delineation of line patterns in images using B-COSFIRE filters
著者:Nicola Strisciuglio, Nicolai Petkov
"> キュレーション

【7月25日 更新分】機械学習に関する論文まとめ

7月25日に公開された論文 ニューラルネットワーク Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in…

7月24日に公開された論文


ニューラルネットワーク

MatchZoo: A Toolkit for Deep Text Matching
著者:Yixing Fan, Liang Pang, JianPeng Hou, Jiafeng Guo, Yanyan Lan, Xueqi Cheng
Person Re-identification Using Visual Attention
著者:Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang Song, Hairong Qi

自然言語処理

Hierarchical Embeddings for Hypernymy Detection and Directionality
著者:Kim Anh Nguyen, Maximilian Köper, Sabine Schulte im Walde, Ngoc Thang Vu

画像解析

Traffic scene recognition based on deep cnn and vlad spatial pyramids
著者:Fang-Yu Wu, Shi-Yang Yan, Jeremy S. Smith, Bai-Ling Zhang
Toward Geometric Deep SLAM
著者:Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich
Synthesizing Robust Adversarial Examples
著者:Anish Athalye, Ilya Sutskever
Wavelet Convolutional Neural Networks for Texture Classification
著者:Shin Fujieda, Kohei Takayama, Toshiya Hachisuka
Semantic 3D Occupancy Mapping through Efficient High Order CRFs
著者:Shichao Yang, Yulan Huang, Sebastian Scherer
Compact Model Representation for 3D Reconstruction
著者:Jhony K. Pontes, Chen Kong, Anders Eriksson, Clinton Fookes, Sridha Sridharan, Simon Lucey
Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation
著者:Gui-Song Xia, Xin-Yi Tong, Fan Hu, Yanfei Zhong, Mihai Datcu, Liangpei Zhang
Deep Optical Flow Estimation Via Multi-Scale Correspondence Structure Learning
著者:Shanshan Zhao, Xi Li, Omar El Farouk Bourahla
"> キュレーション

【7月24日 更新分】機械学習に関する論文まとめ

7月24日に公開された論文 ニューラルネットワーク Learning uncertainty in regression tasks by deep neural networks 著者:Pavel Gurevich, …

7月21日に公開された論文


ニューラルネットワーク

Semantic Segmentation with Reverse Attention
著者:Qin Huang, Chunyang Xia, Chihao Wu, Siyang Li, Ye Wang, Yuhang Song, C. -C. Jay Kuo

自然言語処理

Toward Incorporation of Relevant Documents in word2vec
著者:Navid Rekabsaz, Bhaskar Mitra, Mihai Lupu, Allan Hanbury

画像解析

An All-in-One Network for Dehazing and Beyond
著者:Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng

音声解析

Voice Synthesis for in-the-Wild Speakers via a Phonological Loop
著者:Yaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani

強化学習

A multi-agent reinforcement learning model of common-pool resource appropriation
著者:Julien Perolat, Joel Z. Leibo, Vinicius Zambaldi, Charles Beattie, Karl Tuyls, Thore Graepel
"> キュレーション

【7月21日 更新分】機械学習に関する論文まとめ

7月21日に公開された論文 ニューラルネットワーク Semantic Segmentation with Reverse Attention 著者:Qin Huang, Chunyang Xia, Chihao Wu, …

7月19日に公開された論文


ニューラルネットワーク

Recognizing and Curating Photo Albums via Event-Specific Image Importance
著者:Yufei Wang, Zhe Lin, Xiaohui Shen, Radomir Mech, Gavin Miller, Garrison W. Cottrell

自然言語処理

Discovering topics in text datasets by visualizing relevant words
著者:Franziska Horn, Leila Arras, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek
Spherical Paragraph Model
著者:Ruqing Zhang, Jiafeng Guo, Yanyan Lan, Jun Xu, Xueqi Cheng

画像解析

Optimizing the Latent Space of Generative Networks
著者:Piotr Bojanowski, Armand Joulin, David Lopez-Paz, Arthur Szlam
One-Shot Learning in Discriminative Neural Networks
著者:Jordan Burgess, James Robert Lloyd, Zoubin Ghahramani
When Unsupervised Domain Adaptation Meets Tensor Representations
著者:Hao Lu, Lei Zhang, Zhiguo Cao, Wei Wei, Ke Xian, Chunhua Shen, Anton van den Hengel
Image Projective Invariants
著者:Erbo Li, Hanlin Mo, Dong Xu, Hua Li
Face Alignment Robust to Pose, Expressions and Occlusions
著者:Vishnu Naresh Boddeti, Myung-Cheol Roh, Jongju Shin, Takaharu Oguri, Takeo Kanade
Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation
著者:Arslan Chaudhry, Puneet K. Dokania, Philip H. S. Torr
Transitioning between Convolutional and Fully Connected Layers in Neural Networks
著者:Shazia Akbar, Mohammad Peikari, Sherine Salama, Sharon Nofech-Mozes, Anne Martel
Exploiting Convolutional Representations for Multiscale Human Settlement Detection
著者:Dalton Lunga, Dilip Patlolla, Lexie Yang, Jeanette Weaver, Budhendra Bhadhuri
Faster Than Real-time Facial Alignment: A 3D Spatial Transformer Network Approach in Unconstrained Poses
著者:Chandraskehar Bhagavatula, Chenchen Zhu, Khoa Luu, Marios Savvides
Spectral Filter Tracking
著者:Zhen Cui, You yi Cai, Wen ming Zheng, Jian Yang

強化学習

On-line Building Energy Optimization using Deep Reinforcement Learning
著者:Elena Mocanu, Decebal Constantin Mocanu, Phuong H. Nguyen, Antonio Liotta, Michael E. Webber, Madeleine Gibescu, J. G. Slootweg
"> キュレーション

【7月19日 更新分】機械学習に関する論文まとめ

7月19日に公開された論文 ニューラルネットワーク Recognizing and Curating Photo Albums via Event-Specific Image Importance 著者:Yufei W…

7月18日に公開された論文


ニューラルネットワーク

Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation
著者:Baosong Yang, Derek F. Wong, Tong Xiao, Lidia S. Chao, Jingbo Zhu
Order-Free RNN with Visual Attention for Multi-Label Classification
著者:Shang-Fu Chen, Yi-Chen Chen, Chih-Kuan Yeh, Yu-Chiang Frank Wang
Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition
著者:Shizhong Han, Zibo Meng, Ahmed Shehab Khan, Yan Tong

自然言語処理

Story Generation from Sequence of Independent Short Descriptions
著者:Parag Jain, Priyanka Agrawal, Abhijit Mishra, Mohak Sukhwani, Anirban Laha, Karthik Sankaranarayanan
MAG: A Multilingual, Knowledge-based Agnostic and Deterministic Entity Linking Approach
著者:Diego Moussallem, Ricardo Usbeck, Michael R öder, Axel-Cyrille Ngonga Ngomo
Artificial Error Generation with Machine Translation and Syntactic Patterns
著者:Marek Rei, Mariano Felice, Zheng Yuan, Ted Briscoe

画像解析

Pruning Convolutional Neural Networks for Image Instance Retrieval
著者:Gaurav Manek, Jie Lin, Vijay Chandrasekhar, Lingyu Duan, Sateesh Giduthuri, Xiaoli Li, Tomaso Poggio
Fully Automatic and Real-Time Catheter Segmentation in X-Ray Fluoroscopy
著者:Pierre Ambrosini, Daniel Ruijters, Wiro J. Niessen, Adriaan Moelker, Theo van Walsum

音声解析


強化学習

Reverse Curriculum Generation for Reinforcement Learning
著者:Carlos Florensa, David Held, Markus Wulfmeier, Pieter Abbeel
Trial without Error: Towards Safe Reinforcement Learning via Human Intervention
著者:William Saunders, Girish Sastry, Andreas Stuhlmueller, Owain Evans
"> キュレーション

【7月18日 更新分】機械学習に関する論文まとめ

7月18日に公開された論文 ニューラルネットワーク Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machin…

7月17日に公開された論文


ニューラルネットワーク

Reinforcement Learning for Architecture Search by Network Transformation
著者:Han Cai, Tianyao Chen, Weinan Zhang, Yong Yu, Jun Wang
Visual Question Answering with Memory-Augmented Networks
著者:Chao Ma, Chunhua Shen, Anthony Dick, Anton van den Hengel

自然言語処理

Iris: A Conversational Agent for Complex Tasks
著者:Ethan Fast, Binbin Chen, Julia Mendelsohn, Jonathan Bassen, Michael Bernstein
Automatized Generation of Alphabets of Symbols
著者:Serhii Hamotskyi, Anis Rojbi, Sergii Stirenko, Yuri Gordienko
End-to-End Information Extraction without Token-Level Supervision
著者:Rasmus Berg Palm, Dirk Hovy, Florian Laws, Ole Winther

画像解析

Low-Rank Kernel Subspace Clustering
著者:Pan Ji, Ian Reid, Ravi Garg, Hongdong Li, Mathieu Salzmann
Pathological OCT Retinal Layer Segmentation using Branch Residual U-shape Networks
著者:Stefanos Apostolopoulos, Sandro De Zanet, Carlos Ciller, Sebastian Wolf, Raphael Sznitman

音声解析

Listening while Speaking: Speech Chain by Deep Learning
著者:Andros Tjandra, Sakriani Sakti, Satoshi Nakamura

強化学習

"> キュレーション

【7月17日 更新分】機械学習に関する論文まとめ

7月17日に公開された論文 ニューラルネットワーク Reinforcement Learning for Architecture Search by Network Transformation 著者:Han Cai,…

7月14日に公開された論文


ニューラルネットワーク


自然言語処理


画像解析

Large-scale Multiview 3D Hand Pose Dataset
著者:Francisco Gomez-Donoso, Sergio Orts-Escolano, Miguel Cazorla
SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes
著者:Marc Assens, Kevin McGuinness, Xavier Giro-i-Nieto, "Noel E. OConnor"

音声解析

Automatic Speech Recognition with Very Large Conversational Finnish and Estonian Vocabularies
著者:Seppo Enarvi, Peter Smit, Sami Virpioja, Mikko Kurimo

強化学習

Distral: Robust Multitask Reinforcement Learning
著者:Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki, John Quan, James Kirkpatrick, Raia Hadsell, Nicolas Heess, Razvan Pascanu
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
著者:Shayegan Omidshafiei, Jason Pazis, Christopher Amato, Jonathan P. How, John Vian
"> キュレーション

【7月14日 更新分】機械学習に関する論文まとめ

7月14日に公開された論文 ニューラルネットワーク Large-scale Video Classification guided by Batch Normalized LSTM Translator 著者:Jae H…

7月13日に公開された論文


ニューラルネットワーク

Robust Visual Tracking via Hierarchical Convolutional Features
著者:Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang

自然言語処理

Quasar: Datasets for Question Answering by Search and Reading
著者:Bhuwan Dhingra, Kathryn Mazaitis, William W. Cohen

画像解析

Leveraging the Path Signature for Skeleton-based Human Action Recognition
著者:Weixin Yang, Terry Lyons, Hao Ni, Cordelia Schmid, Lianwen Jin, Jiawei Chang
Robust Visual Tracking via Hierarchical Convolutional Features
著者:Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Hsuan Yang
Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras
著者:Joris Guérin, Olivier Gibaru, Eric Nyiri, Stéphane Thiery

音声解析


強化学習

Autoencoder-augmented Neuroevolution for Visual Doom Playing
著者:Samuel Alvernaz, Julian Togelius
Merge or Not? Learning to Group Faces via Imitation Learning
著者:Yue He, Kaidi Cao, Cheng Li, Chen Change Loy
"> キュレーション

【7月13日 更新分】機械学習に関する論文まとめ

7月13日に公開された論文 ニューラルネットワーク Robust Visual Tracking via Hierarchical Convolutional Features 著者:Chao Ma, Jia-Bin H…

7月12日に公開された論文


自然言語処理

Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text
著者:Ayush Jaiswal, Ekraam Sabir, Wael AbdAlmageed, Premkumar Natarajan
Dataset for a Neural Natural Language Interface for Databases (NNLIDB)
著者:Florin Brad, Radu Iacob, Ionel Hosu, Traian Rebedea

画像解析

Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text
著者:Ayush Jaiswal, Ekraam Sabir, Wael AbdAlmageed, Premkumar Natarajan
Discriminative Block-Diagonal Representation Learning for Image Recognition
著者:Zheng Zhang, Yong Xu, Ling Shao, Jian Yang
Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
著者:Carole H Sudre, Wenqi Li, Tom Vercauteren, Sébastien Ourselin, M. Jorge Cardoso
Adversarial training and dilated convolutions for brain MRI segmentation
著者:Pim Moeskops, Mitko Veta, Maxime W. Lafarge, Koen A. J. Eppenhof, Josien P. W. Pluim
SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes
著者:Marc Assens, Kevin McGuinness, Xavier Giro-i-Nieto, "Noel E. OConnor"

音声解析


強化学習

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation
著者:YuXuan Liu, Abhishek Gupta, Pieter Abbeel, Sergey Levine
"> キュレーション

【7月12日 更新分】機械学習に関する論文まとめ

7月12日に公開された論文 自然言語処理 Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text 著者:Ayus…

7月11日に公開された論文


ニューラルネットワーク

A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning
著者:Honglun Zhang, Liqiang Xiao, Yongkun Wang, Yaohui Jin
Enhanced Deep Residual Networks for Single Image Super-Resolution
著者:Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee
Scale-Regularized Filter Learning
著者:Marco Loog, François Lauze

自然言語処理

A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques
著者:Mehdi Allahyari, Seyedamin Pouriyeh, Mehdi Assefi, Saied Safaei, Elizabeth D. Trippe, Juan B. Gutierrez, Krys Kochut
Understanding State Preferences With Text As Data: Introducing the UN General Debate Corpus
著者:Alexander Baturo, Niheer Dasandi, Slava J. Mikhaylov
Text Summarization Techniques: A Brief Survey
著者:Mehdi Allahyari, Seyedamin Pouriyeh, Mehdi Assefi, Saeid Safaei, Elizabeth D. Trippe, Juan B. Gutierrez, Krys Kochut

画像解析

Low Dose CT Image Reconstruction With Learned Sparsifying Transform
著者:Xuehang Zheng, Zening Lu, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler
Scan-path Prediction on 360 Degree Images using Saliency Volumes
著者:Marc Assens, Kevin McGuinness, Xavier Giro-i-Nieto, "Noel E. OConnor"
Automatic Understanding of Image and Video Advertisements
著者:Zaeem Hussain, Mingda Zhang, Xiaozhong Zhang, Keren Ye, Christopher Thomas, Zuha Agha, Nathan Ong, Adriana Kovashka
Foot anthropometry device and single object image thresholding
著者:Amir Mohammad Esmaieeli Sikaroudi, Sasan Ghaffari, Ali Yousefi, Hassan Sadeghi Naeini
Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras
著者:Joris Guérin, Olivier Gibaru, Eric Nyiri, Stéphane Thiery
Synthesis-based Robust Low Resolution Face Recognition
著者:Sumit Shekhar, Vishal M. Patel, Rama Chellappa

強化学習

Hindsight Experience Replay
著者:Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba
"> キュレーション

【7月11日 更新分】機械学習に関する論文まとめ

7月11日に公開された論文 ニューラルネットワーク A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task …

7月10日に公開された論文


自然言語処理


画像解析

Local Activity-tuned Image Filtering for Noise Removal and Image Smoothing
著者:Lijun Zhao, Jie Liang, Huihui Bai, Lili Meng, Anhong Wang, Yao Zhao
Class-Weighted Convolutional Features for Visual Instance Search
著者:Albert Jimenez, Jose M. Alvarez, Xavier Giro-i-Nieto

音声解析


強化学習

"> キュレーション

【7月10日 更新分】機械学習に関する論文まとめ

7月10日に公開された論文 自然言語処理 Controlling Linguistic Style Aspects in Neural Language Generation 著者:Jessica Ficler, Yoa…

7月7日に公開された論文


ニューラルネットワーク

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
著者:Kristof T. Schütt, Pieter-Jan Kindermans, Huziel E. Sauceda, Stefan Chmiela, Alexandre Tkatchenko, Klaus-Robert Müller

自然言語処理

An Interactive Tool for Natural Language Processing on Clinical Text
著者:Gaurav Trivedi, Phuong Pham, Wendy Chapman, Rebecca Hwa, Janyce Wiebe, Harry Hochheiser
The E2E Dataset: New Challenges For End-to-End Generation
著者:Jekaterina Novikova, Ondřej Dušek, Verena Rieser

画像解析

Cross-linguistic differences and similarities in image descriptions
著者:Emiel van Miltenburg, Desmond Elliott, Piek Vossen
Changing Views on Curves and Surfaces
著者:Kathlén Kohn, Bernd Sturmfels, Matthew Trager

強化学習

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
著者:Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans
"> キュレーション

【7月7日 更新分】機械学習に関する論文まとめ

7月7日に公開された論文 ニューラルネットワーク SchNet: A continuous-filter convolutional neural network for modeling quantum interac…

7月6日に公開された論文


ニューラルネットワーク

An Attention Mechanism for Answer Selection Using a Combined Global and Local View
著者:Yoram Bachrach, Andrej Zukov-Gregoric, Sam Coope, Ed Tovell, Bogdan Maksak, Conan McMurtie

自然言語処理

Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text
著者:Ayush Jaiswal, Ekraam Sabir, Wael Abd-Almajeed, Premkumar Natarajan

画像解析

Deep Learning Based Large-Scale Automatic Satellite Crosswalk Classification
著者:Rodrigo F. Berriel, Andre Teixeira Lopes, Alberto F. de Souza, Thiago Oliveira-Santos
Multimedia Semantic Integrity Assessment Using Joint Embedding Of Images And Text
著者:Ayush Jaiswal, Ekraam Sabir, Wael Abd-Almajeed, Premkumar Natarajan
Generative diffeomorphic atlas construction from brain and spinal cord MRI data
著者:Claudia Blaiotta, Patrick Freund, M. Jorge Cardoso, John Ashburner
Robust Multi-Image HDR Reconstruction for the Modulo Camera
著者:Florian Lang, Tobias Plötz, Stefan Roth
Laplacian-Steered Neural Style Transfer
著者:Shaohua Li, Xinxing Xu, Liqiang Nie, Tat-Seng Chua

強化学習

Hindsight Experience Replay
著者:Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba
Learning to Design Games: Strategic Environments in Deep Reinforcement Learning
著者:Haifeng Zhang, Jun Wang, Zhiming Zhou, Weinan Zhang, Ying Wen, Yong Yu, Wenxin Li
Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
著者:Pei-Hao Su, Pawel Budzianowski, Stefan Ultes, Milica Gasic, Steve Young
"> キュレーション

【7月6日 更新分】機械学習に関する論文まとめ

7月6日に公開された論文 ニューラルネットワーク An Attention Mechanism for Answer Selection Using a Combined Global and Local View 著者…

7月5日に公開された論文


ニューラルネットワーク


自然言語処理

DeepStory: Video Story QA by Deep Embedded Memory Networks
著者:Kyung-Min Kim, Min-Oh Heo, Seong-Ho Choi, Byoung-Tak Zhang
Complexity Metric for Code-Mixed Social Media Text
著者:Souvick Ghosh, Satanu Ghosh, Dipankar Das
CoNLL-SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection in 52 Languages
著者:Ryan Cotterell, Christo Kirov, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden

画像解析

UPSET and ANGRI : Breaking High Performance Image Classifiers
著者:Sayantan Sarkar, Ankan Bansal, Upal Mahbub, Rama Chellappa
Discriminative Localization in CNNs for Weakly-Supervised Segmentation of Pulmonary Nodules
著者:Xinyang Feng, Jie Yang, Andrew F. Laine, Elsa D. Angelini

音声解析

Hidden-Markov-Model Based Speech Enhancement
著者:Daniel Dzibela, Armin Sehr

強化学習

"> キュレーション

【7月5日 更新分】機械学習に関する論文まとめ

7月5日に公開された論文 ニューラルネットワーク Improving Slot Filling Performance with Attentive Neural Networks on Dependency Struc…

7月4日に公開された論文


ニューラルネットワーク

Selective Deep Convolutional Features for Image Retrieval
著者:Tuan Hoang, Thanh-Toan Do, Dang-Khoa Le Tan, Ngai-Man Cheung
Aggregating Frame-level Features for Large-Scale Video Classification
著者:Shaoxiang Chen, Xi Wang, Yongyi Tang, Xinpeng Chen, Zuxuan Wu, Yu-Gang Jiang

画像解析

High-Quality Face Image SR Using Conditional Generative Adversarial Networks
著者:Huang Bin, Chen Weihai, Wu Xingming, Lin Chun-Liang
Deep Representation Learning with Part Loss for Person Re-Identification
著者:Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian
Zero-Shot Fine-Grained Classification by Deep Feature Learning with Semantics
著者:Aoxue Li, Zhiwu Lu, Liwei Wang, Tao Xiang, Xinqi Li, Ji-Rong Wen
Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
著者:Fabian Isensee, Paul Jaeger, Peter M. Full, Ivo Wolf, Sandy Engelhardt, Klaus H. Maier-Hein
Detection and Localization of Image Forgeries using Resampling Features and Deep Learning
著者:Jason Bunk, Jawadul H. Bappy, Tajuddin Manhar Mohammed, Lakshmanan Nataraj, Arjuna Flenner, B. S. Manjunath, Shivkumar Chandrasekaran, Amit K. Roy-Chowdhury, Lawrence Peterson
Automatic Trimap Generation for Image Matting
著者:Vikas Gupta, Shanmuganathan Raman

強化学習

"> キュレーション

【7月4日 更新分】機械学習に関する論文まとめ

7月4日に公開された論文 ニューラルネットワーク Selective Deep Convolutional Features for Image Retrieval 著者:Tuan Hoang, Thanh-Toan D…

7月3日に公開された論文


自然言語処理

Where to Play: Retrieval of Video Segments using Natural-Language Queries
著者:Sangkuk Lee, Daesik Kim, Myunggi Lee, Jihye Hwang, Nojun Kwak

画像解析

Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
著者:Jiayun Wang, Sanping Zhou, Jinjun Wang, Qiqi Hou
A Fast Method For Computing Principal Curvatures From Range Images
著者:Andrew Spek, Wai Ho Li, Tom Drummond
Automatic Trimap Generation for Image Mattting
著者:Vikas Gupta, Shanmuganathan Raman

音声解析

"> キュレーション

【7月3日 更新分】機械学習に関する論文まとめ

7月3日に公開された論文 自然言語処理 Where to Play: Retrieval of Video Segments using Natural-Language Queries 著者:Sangkuk Lee, …

6月30日に公開された論文


ニューラルネットワーク

Scale-Aware Face Detection
著者:Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan, Xiu Li, Xiaolin Hu

自然言語処理

Relevance of Unsupervised Metrics in Task-Oriented Dialogue for Evaluating Natural Language Generation
著者:Shikhar Sharma, Layla El Asri, Hannes Schulz, Jeremie Zumer

画像解析

Image classification using local tensor singular value decompositions
著者:Elizabeth Newman, Misha Kilmer, Lior Horesh
Automatic Face Image Quality Prediction
著者:Lacey Best-Rowden, Anil K. Jain
Scale-Aware Face Detection
著者:Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan, Xiu Li, Xiaolin Hu
Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
著者:Waleed M. Gondal, Jan M. Köhler, René Grzeszick, Gernot A. Fink, Michael Hirsch
Towards Understanding the Dynamics of Generative Adversarial Networks
著者:Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt

音声解析

"> キュレーション

【6月30日 更新分】機械学習に関する論文まとめ

6月30日に公開された論文 ニューラルネットワーク Scale-Aware Face Detection 著者:Zekun Hao, Yu Liu, Hongwei Qin, Junjie Yan, Xiu Li, Xi…