YANAI Lab.

Refereed Papers

2024年度

• Kota Izumi and Keiji Yanai: CLIPFontDraw: Stylizing Fonts with CLIP, IEEE Access, (2024/10). (https://doi.org/10.1109/ACCESS.2024.3479417) (Open Access)
• Junwen Chen Yingcheng Wang Keiji Yanai: Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor，Proc. of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, USA, (2025/02).  
• Honghui Yuan and Keiji Yanai: KuzushijiDiffuser: Japanese Kuzushiji Font Generation with FontDiffuser, Proc. of International Conference on Multimedia Modeling, Nara, Japan, (2025/01).
• Hikaru Tanabe and Keiji Yanai: CalorieVoL: Integrating Volumetric Context into Multimodal Large Language Models for Image-based Calorie Estimation, Proc. of International Conference on Multimedia Modeling, Nara, Japan, (2025/01).
• Honghui Yuan and Keiji Yanai: SceneTextStyler: Editing Text with Style Transformation, Proc. of International Conference on Multimedia Modeling, Demo Track, Nara, Japan, (2025/01).
• Honghui Yuan and Keiji Yanai: KuzushijiFontDiff: Diffusion Model for Japanese Kuzushiji Font Generation, Proc. of International Conference on Multimedia Modeling, Demo Track, Nara, Japan, (2025/01).
• Kota Izumi and Keiji Yanai: WaveFontStyler: Font Style Transfer Based on Sound, Proc. of International Conference on Multimedia Modeling, Demo Track, Nara, Japan, (2025/01).
  
• Yuto Nakamizo and Keiji Yanai: Act-ChatGPT: Introducing Action Features into Multi-Modal Large Language Models for Video Understanding, Proc. of International Conference on Pattern Recognition (ICPR), Kolkata, India, (2024/12).
• Honghui Yuan and Keiji Yanai: Font Style Translation in Scene Text Images with CLIPstyler, Proc. of International Conference on Pattern Recognition (ICPR), Kolkata, India, (2024/12).
• Hikaru Tanabe and Keiji Yanai: CalorieLLaVA: Image-based Calorie Estimation with Multimodal Large Language Models, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADiMa), Kolkata, India, (2024/12).
• Kohei Yamamoto, Honghui Yuan and Keiji Yanai: Calorie-Aware Food Image Editing with Image Generation Models, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADiMa), Kolkata, India, (2024/12).
• Ryuta Yamakura and Keiji Yanai: Vector Logo Image Synthesis Using Differentiable Renderer,  Proc. of ACCV Workshop on Rich Media and Genarative AI, Hanoi, Vietnum, (2024/12).
• Rento Yamaguchi, Keiji Yanai: Exploring Cross-Attention Maps in Multi-modal Diffusion Transformers for Training-Free Semantic Segmentation, Proc. of ACCV Workshop on Large Vision – Language Model Learning and Applications (LAVA), Hanoi, Vietnum, (2024/12).
• Jing Yang, Junwen Chen and Keiji Yanai: RecipeSD: Injecting Recipe into Food Image Synthesis with Stable Diffusion, Proc. of ACMMM Workshop on Multimedia Content Generation and Evaluation: New Methods and Practice (McGE), Melbourne, Australia, (2024/10).
• Junwen Chen, Yingcheng Wang and Keiji Yanai: HOI as Embeddings: Advancements of Model Representation Capability in Human-Object Interaction Detection, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval, San Jose, USA (2024/08).
• Jing Yang, Junwen Chen and Keiji Yanai: Improving Cross-Modal Recipe Embeddings with Cross Decoder, Proc. of ACM ICMR Workshop on Intelligent Cross-Data Analysis and Retrieval, Phuket, Thailand (2024/06).

2023年度

• Kotaro Higuchi and Keiji Yanai: Patent Image Retrieval Using Transformer-based Deep Metric Learning, World Patent Information, Vol.74, (2023/09). (DOI: 10.1016/j.wpi.2023.102217)
• Zhongtao Chen, Yuma Hombu and Keiji Yanai: Mask-based Food Image Synthesis with Cross-Modal Recipe Embeddings, Proc. of ACM Multimedia Asia, Tainan, Taiwan (2023/12).
• Ryota Kaji and Keiji Yanai: VQ-VDM: Video Diffusion Models with 3D VQGAN, Proc. of ACM Multimedia Asia, Tainan, Taiwan (2023/12).
• Jingbin Xu, Junwen Chen and Keiji Yanai: Contextual Associated Triplet Queries for Panoptic Scene Graph Generation, Proc. of ACM Multimedia Asia, Tainan, Taiwan (2023/12).
• Yingcheng Wang, Junwen Chen and Keiji Yanai: HowToEat: Exploring Human Object Interaction and Eating Action in Eating Scenarios, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Ottawa, Canada (2023/10).
• Junwen Chen and Keiji Yanai: QAHOI: Query-Based Anchors for Human-Object Interaction Detection, Proc. of 18th International Conference on Machine Vision Applications (MVA), Hamamatsu, Japan (2023/07). (Best Paper Award)
• Kento Terauchi and Keiji Yanai, CalorieCam360: Simultaneous Eating Action Recognition of Multiple People Using Omnidirectional Camera, Proc.of ACM International Conference on Multimedia Retrieval (ICMR), Thessaloniki, Greece (2023/06).

2022年度

• Gibran Benitez-Garcia, Hiroki Takahashi and Keiji Yanai: Material Translation Based on Neural Style Transfer with Ideal Style Image Retrieval, Sensors, Vol.22, No.19 (2022).   (DOI: 10.3390/s22197317)
• Kotaro Higuchi, Yuma Honbu, and Keiji Yanai: Patent Image Retrieval Using Cross-entropy-based Metric Learning, Proc.of International Workshop on Frontiers of Computer Vision (IW-FCV), Yeosu, South Korea (2023/02). 
• Jing Yang, Junwen Chen and Keiji Yanai: Transformer-Based Cross-Modal Recipe Embeddings with Large Batch Training, Proc. of the International Multimedia Modeling Conference (MMM), Belgen, Norway (2023/01). 
• Daiki Shimizu and Keiji Yanai: Virtual Try-On Considering Temporal Consistency for Videoconferencing, Proc. of the International Multimedia Modeling Conference (MMM), Belgen, Norway (2023/01). 
• Junwen Chen and Keiji Yanai: Parallel Queries for Human-Object Interaction Detection, Proc. of ACM Multimedia Asia, Tokyo, Japan (2022/12).
• Kota Izumi and Keiji Yanai: Zero-shot Font Style Transfer with a Differentiable Renderer, Proc. of ACM Multimedia Asia, Tokyo, Japan (2022/12).
• Mana Takeda and Keiji Yanai: Continual Learning in Vision Transformer, Proc.of IEEE International Conference on Image Processing (ICIP), Bordeaux, France (2022/10).
• Shu Naritomi and Keiji Yanai: Real Scale 3D Reconstruction of a Dish and a Plate using Implicit Function and a Single RGB-D Image, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Lisbon, Portugal (2022/10).
• Kohei Yamamoto and Keiji Yanai: Text-based Image Editing for Food Images with CLIP, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Lisbon, Portugal (2022/10).
• Kento Adachi and Keiji Yanai: DepthGrillCam: A Mobile Application for Real-time Eating Action Recording Using RGB-D Images, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Lisbon, Portugal (2022/10).
• Yuma Honbu and Keiji Yanai: SetMealAsYouLike: Sketch-based Set Meal Image Synthesis with Plate Annotations, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Lisbon, Portugal (2022/10).
• Yuchen Qian, Kohei Yamamoto and Keiji Yanai: StyleGAN-based CLIP-guided Image Shape Manipulation, Proc.of International Conference on Content-based Multimedia Indexing (CBMI), Graz, Austria (2022/09).
• Yuma Honbu and Keiji Yanai: Unseen Food Segmentation, Proc.of ACM International Conference on Multimedia Retrieval (ICMR), Newark, USA (2022/06).

2021年度

• L. Rosas-Arias, G. Benitez-Garcia, J. Portillo-Portillo, J. Olivares-Mercado, G. Sanchez-Perez and K. Yanai, FASSD-Net: Fast and Accurate Real-Time Semantic Segmentation for Embedded Systems, IEEE Transactions on Intelligent Transportation Systems (Early Access).  (DOI: 10.1109/TITS.2021.3127553)
• Kizashi Nakano, Daichi Horita, Norihiko Kawai, Naoya Isoyama, Nobuchika Sakata, Kiyoshi Kiyokawa, Keiji Yanai, Takuji Narumi: A Study on Persistence of GAN-Based Vision-Induced Gustatory Manipulation, Electronics, 10(10), 1157-1157 (2021/05). (DOI: 10.3390/electronics10101157)
• Mana Takeda and Keiji Yanai: Generating Images from Small Datasets Using Adaptive Point-wise Grouped Convolutions, Proc.of International Workshop on Frontiers of Computer Vision (IW-FCV), Hiroshima, Japan (2022/02).
• Shu Naritomi, Gibran Benitez-Garcia and Keiji Yanai: Ketchup As You Like: Drawing Editor for Foods, Proc. of IEEE Airtificial Intelligence and Virtual Realty (IEEE AIVR), Demo paper (2021/11). (video)
• Kento Terauchi and Keiji Yanai: Pose Sequence Generation with a GCN and an Initial Pose Generator, Proc. of Asian Conference on Pattern Recgonition (ACPR), (2021/11).
• Yu Sugiyama and Keiji Yanai: Cross-Modal Recipe Embeddings by Disentangling Recipe Contents and Dish Styles, Proc. of ACM Multimedia, Online (2021/10).
• Shu Naritomi and Keiji Yanai: 3D Mesh Reconstruction of Foods from a Single Image, Proc. of ACM Multimedia WS on AIxFood, Online (2021/09). (Demo paper)  
• Honghui Yuan and Keiji Yanai: Multi-Style Transfer Generative Adversarial Network for Text Images, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), Tokyo, Japan (2021/09). 
• Shu Naritomi and Keiji Yanai: Pop’n Food: 3D Food Model Estimation System from a Single Image, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), Tokyo, Japan (2021/09). (Demo paper) 
• Yuma Honbu and Keiji Yanai: Few-Shot and Zero-Shot Semantic Segmentation for Food Images , Proc. of ICMR WS on Multimedia for Cooking and Eating Activities (CEA), Taipei, Taiwan (2021/08). (video)
• Kaimu Okamoto, Kento Adachi and Keiji Yanai: Region-Based Food Calorie Estimation for Multiple-Dish Meals, Proc. of ICMR WS on Multimedia for Cooking and Eating Activities (CEA), Taipei, Taiwan (2021/08).
• Gibran Benitez-Garcia and Keiji Yanai: Ketchup GAN: A New Dataset for Realistic Synthesis of Letters on Food, Proc. of ICMR WS on Multimedia Artworks Analysis and Attractiveness Computing (MMArt), Taipei, Taiwan (2021/08).

2020年度

• Shu Naritomi and Keiji Yanai: Hungry Networks: 3D Mesh Reconstruction of a Dish and a Plate from a Single Dish Image for Estimating Food Volume, Proc. of ACM Multimedia Asia, Online (2021/03).  
• Jaehyeong Cho, Wataru Shimoda, and Keiji Yanai: Mask-Based Style-Controlled Image Synthesis Using a Mask Style Encoder, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Online (2021/01).
  
• Gibran Benitez-Garcia, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, and Keiji Yanai: IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Online (2021/01). (https://arxiv.org/abs/2005.02134)
• Leonel Rosas-Arias, Gibran Benitez-Garcia, Jose Portillo-Portillo, Gabriel Sanchez-Perez, and Keiji Yanai: Fast and Accurate Real-Time Semantic Segmentation with Dilated Asymmetric Convolutions, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Online (2021/01).
• Mana Takeda, Gibran Benitez-Garcia, and Keiji Yanai: Training of Multiple and Mixed Tasks With A Single Network Using Feature Modulation, Proc. of ICPR Workshop on Deep Learning for Pattern Recognition (DLPR), Online, (2021/01).
• Yuta Ide, Tsuyohito Araki, Ryunosuke Hamada, Kazunori Ohno, and Keiji Yanai: Rescue Dog Action Recognition by Integrating Ego-centric Video, Sound and Sensor Information, Proc. of ICPR Workshop on Applications of Egocentric Vision (EgoApp), Online, (2021/01).
• Kaimu Okamoto and Keiji Yanai: UEC-FoodPix Complete: A Large-scale Food Image Segmentation Dataset, Proc. of ICPR Workshop on Multimedia Assisted Dietary Management (MADIMA), Online, (2021/01).
• Gibran Benitez-Garcia, Wataru Shimoda, and Keiji Yanai: Style Image Retrieval for Improving Material Translation Using Neural Style Transfer, Proc. of ACM ICMR Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia (MMArt-ACM), Online, (2020/10).
• Takuro Karamatsu, Gibran Benitez-Garcia, Keiji Yanai, and Seiichi Uchida: Iconify: Converting Photographs into Icons, Proc. of ACM ICMR Workshop on Multimedia Artworks Analysis and Attractiveness Computing in Multimedia (MMArt-ACM), Online, (2020/10). (https://arxiv.org/abs/2004.03179)
• Keiji Yanai, Daichi Horita, and Jaehyeong Cho: Food Image Generation and Translation and Its Application to Augmented Reality, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), Online, (2020/09).  
• Wataru Shimoda and Keiji Yanai: Predicting Plate Regions for Weakly-supervised Food Image Segmentation, Proc. of IEEE International Conference on Multimedia and Expo (ICME), Online, (2020/07).

2019年度

• Wataru Shimoda and Keiji Yanai: Weakly Supervised Semantic Segmentation Using Distinct Class Specific Saliency Maps, Computer Vision and Image Understanding, Elsevier (2019) (PDF) (in press) (https://doi.org/10.1016/j.cviu.2018.08.006)
• Takumi Ege and Keiji Yanai: Simultaneous Estimation of Dish Locations and Calories with Multi-task Learning, IEICE Transactions on Information and Systems, Vol. E102-D, No.7, pp.1240-1246 (2019/07). (https://doi.org/10.1587/transinf.2018CEP0004)
• Wataru Shimoda and Keiji Yanai: Webly-Supervised Food Detection with Foodness Proposal, IEICE Transactions on Information and Systems, Vol. E102-D, No.7, pp.1230-1239 (2019/07). (https://doi.org/10.1587/transinf.2018CEP0001)
• Shu Naritomi and Keiji Yanai: CalorieCaptorGlass: Food Calorie Estimation based on Actual Size using HoloLens and Deep Learning, Proc. of IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR) , Atlanta, USA, (2020/03). (Technical Demo)
• Daichi Horita and Keiji Yanai: SSA-GAN: End-to-End Time-Lapse Generation with Spatial Self-Attention, Proc. of Asian Conference on Pattern Recognition (ACPR), Auckland, New Zealand, (2019/11).

• Runtong Zhang, Yuchen Wu and Keiji Yanai: Pre-trained and Shared Encoder in Cycle-Consistent Adversarial Networks to Improve Image Quality, Proc. of Asian Conference on Pattern Recgonition (ACPR), Auckland, New Zealand, (2019/11).
• Asato Matsumoto and Keiji Yanai: Continual Learning of An Image Transformation Network Using Task-dependent Weight Selection Masks, Proc. of Asian Conference on Pattern Recgonition (ACPR), Auckland, New Zealand, (2019/11).
• Yuchen Wu, Runtong Zhang and Keiji Yanai: Attention Guided Unsupervised Image-to-Image Translation with Progressively Growing Strategy, Proc. of ACPR Workshop on Advances and Applications on Generative Deep Learning Models (AAGM), Auckland, New Zealand, (2019/11).

• Wataru Shimoda and Keiji Yanai: Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation, Proc. of IEEE/CVF Intternational Conference on Computer Vision (ICCV), Seoul, Korea (2019/10). (acceptance rate: 25.0% (1077/4303)) (https://arxiv.org/abs/1911.01370)
• Wataru Shimoda and Keiji Yanai: Zero-Annotation Plate Segmentation Using a Food Category Classifier and a Food/Non-Food Classifier, Proc. of ICCV Workshop on Multi-Discipline Approarch for Learning Concepts (MDALC), Seoul, Korea (2019/10). (Extended Abstract)
• Tsuyohito Araki, Ryunosuke Hamada, Kazunori Ohno, Keiji Yanai: Dog-Centric Activity Recognition by Integrating Appearance, Motion and Sound, Proc. of ICCV Workshop on Egocentric Perception, Interaction and Computing (EPIC), Seoul, Korea (2019/10). (Extended Abstract)
• Jaehyeong Cho, Wataru Shimoda and Keiji Yanai: Ramen as You Like: Sketch-based Food Image Generation and Editing, Proc. of ACM Multimedia, Nice, France (2019/10). (Demo paper)
  
• Yoshikazu Ando, Takumi Ege, Jaehyeong Cho and Keiji Yanai: DepthCalorieCam: A Mobile Application for Volume-Based Food Calorie Estimation using Depth Cameras, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Nice, France (2019/10).
• Takumi Ege, Wataru Shimoda and Keiji Yanai: A New Large-scale Food Image Segmentation Dataset and Its Application to Food Calorie Estimation Based on Grains of Rice, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Nice, France (2019/10).
• Daichi Horita, Wataru Shimoda and Keiji Yanai: Unseen Food Creation by Mixing Existing Food Images with Conditional StyleGAN, Proc. of ACMMM Workshop on Multimedia Assisted Dietary Management (MADIMA), Nice, France (2019/10).
• Kizashi Nakano, Daichi Horita, Nobuchika Sakata, Kiyoshi Kiyokawa, Keiji Yanai, and Takuji Narumi: DeepTaste: Augmented Reality Gustatory Manipulation with GAN-based Real-time Food-to-Food Translation, Proc. of IEEE International Symposium on Mixed and Augmented Reality (ISMAR), Beijing, China (2019/10).
• Keiji Yanai, Kaimu Okamoto, Tetsuya Nagano and Daichi Horita: Large-scale Twitter Food Photo Mining and Its Applications, Proc. of International Conference on Multimedia Big Data (BIGMM), Singapore (2019/09). [invited]
  
• Kaimu Okamoto and Keiji Yanai: Analyzing Regional Food Trends with Geo-tagged Twitter Food Photos, Proc. of International Conference on Content-Based Multimedia Indexing (CBMI), Dublin, Ireland (2019/09).
• Wataru Shimoda and Keiji Yanai: Self-supervised Difference Detection for Refinement CRF and Seed Interpolation, Proc. of CVPR Workshop on Weakly Supervised Learning for Real-World Computer Vision Applications, Long Beach, USA (2019/06).

2018年度

• Takumi Ege, Wataru Shimoda and Keiji Yanai: Image-search-based Food Calorie Estimation with CNN Feature Learning, IEICE Transactions on Information and Systems (Japanese Edition) Vol.J101-D, No.8, pp.1099-1109 (2018/08).
• Takumi Ege and Keiji Yanai: Image-Based Food Calorie Estimation Using Recipe Information, IEICE Transactions on Information and Systems, Vol. E101-D, No.5, pp.1333-1341 (2018/05).
• Takumi Ege, Yoshikazu Ando, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai: Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), San Jose, USA (2019/03).
• Tetsuya Nagano, Takumi Ege, Wataru Shimoda and Keiji Yanai: A Large-scale Analysis of Regional Tendency of Twitter Photos Using Only Image Features, Proc. of IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR), San Jose, USA (2019/03).
• Wataru Shimoda, Atsushi Narusawa, and Keiji Yanai: Font Style Transfer Using Deep Neural Networks, International Display Workshop (IDW), Nagoya, Japan (2018/12). [invited]
• Yuki Izumi, Daichi Horita, Ryosuke Tanno and Keiji Yanai: Real-Time Image Classification and Transformation Apps on iOS by “Chainer2MPSNNGraph”, NIPS 2018 Workshop on Machine Learning on the Phone and other Consumer Devices (MLPCD), Motreal, Canada (2018/12).
• Asato Matsumoto and Keiji Yanai: Continual Learning for an Encoder-Decoder CNN Using “Piggyback”, NIPS2018 Continual Learning Workshop, Montreal, Canada (2018/12).
  
• Shu Naritmo, Ryosuke Tanno, Takumi Ege and Keiji Yanai: FoodChangeLens: CNN-based Food Transformation on HoloLens, Proc. of International Workshop on Interface and Experience Design with AI for VR/AR (DAIVAR), Taichung, Taiwan (2018/12). (Demo paper)
• Yu Sugiyama and Keiji Yanai: Word-Conditioned Image Style Transfer, Proc. of ACCV Workshop on AI Aesthetics in Art and Media (AIAM), Perth, Australia (2018/12).
• Atsushi Narusawa, Wataru Shimoda and Keiji Yanai: Font Style Transfer Using Neural Style Transfer and Unsupervised Cross-domain Transfer, Proc. of ACCV Workshop on AI Aesthetics in Art and Media, Perth, Australia (2018/12).
• Daichi Horita, Jaehyeong Cho, Takumi Ege and Keiji Yanai: CNN-based Photo Transformation for Improving Attractiveness of Ramen Photos, ACM Symposium on Virtual Reality Software and Technology (VRST), Tokyo, Japan (2018/11). (Poster paper)
• Ryosuke Tanno, Takumi Ege and Keiji Yanai: AR DeepCalorieCam V2: Food Calorie Estimation with CNN and AR-based Actual Size Estimation, ACM Symposium on Virtual Reality Software and Technology (VRST), Tokyo, Japan (2018/11). (Demo paper)
• Ryosuke Tanno, Daichi Horita, Wataru Shimoda and Keiji Yanai: Magical Rice Bowl: Real-time Food Category Changer, Proc. of ACM Multimedia, Seoul, Korea (2018/10). (Demo paper)
• Takumi Ege and Keiji Yanai: Multi-task Learning of Dish Detection and Calorie Estimation, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADIMA), Stockholm, Sweden (2018/07).
• Daichi Horita, Ryosuke Tanno, Wataru Shimoda and Keiji Yanai: Food Category Transfer with Conditional Cycle GAN and a Large-scale Food Image Dataset, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADIMA), Stockholm, Sweden (2018/07).
• Yoshifumi Ito, Wataru Shimoda and Keiji Yanai: Food Image Generation using A Large Amount of Food Images with Conditional GAN: RamenGAN and RecipeGAN, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADIMA), Stockholm, Sweden (2018/07).

2017年度

• Shin Matsuo and Keiji Yanai: Style-based Artistic Image Retrieval Using Neural Style Vector, IEICE Transactions on Information and Systems (Japanese Edition) Vol.J100-D No.8 pp.742-749 (2017/08).
• Ryosuke Tanno and Keiji Yanai: AR DeepCalorieCam: An iOS App for Food Calorie Estimation with Augmented Reality, Proc. of the International Multimedia Modeling Conference (MMM), Bangkok, Thailand (2018/02). (Demo paper)
• Wataru Shimoda and Keiji Yanai: Predicting Segmentation "Easiness" from the Consistency for Weakly-Supervised Segmentation, Proc. of Asian Conference on Pattern Recognition (ACPR), Nanjing, China (2017/11).
• Takumi Ege and Keiji Yanai: Estimating Food Calories for Multiple-dish Food Photos, Proc. of Asian Conference on Pattern Recognition (ACPR), Nanjing, China (2017/11).
• Toshiki Nakamura, Anna Zhu, Keiji Yanai,and Seiichi Uchida: Scene Text Eraser, Proc. of the International Conference on Document Analysis and Recognitino (ICDAR) (2017/11).
• Gantugs Atarsaikhan, Brian Kenji Iwana, Atsushi Narusawa, Keiji Yanai and Seiichi Uchida: Neural Font Style Transfer, Proc. of ICDAR Workshop on Machine Learning (2017/11).
• Takumi Ege and Keiji Yanai: Image-Based Food Calorie Estimation Using Knowledge on Food Categories, Ingredients and Cooking Directions, Proc. of ACM Multimedia Thematic Workshops on Understanding, Mountain View, CA, USA (2017/10). (PDF)
• Takumi Ege and Keiji yanai: Comparison of Two Approaches for Direct Food Calorie Estimation, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADIMA), Catania, Italy (2017/09).
• Shin Matsuo, Wataru Shimoda and Keiji Yanai: Partial Style Transfer Using Weakly-Supervised Semantic Segmentation, Proc. of ICME Workshop on Multimedia Artworks Analysis (MMArt), Hong Kong (2017/07).
• Keiji Yanai and Ryosuke Tanno: Conditional Fast Style Transfer Network, Proc. of ACM International Conference on Multimedia Retrieval (ICMR), Bucharest, Romania (2017/06).
• Takumi Ege and Keiji Yanai: Simultaneous Estimation of Food Categories and Calories with Multi-task CNN, Proc. of IAPR International Conference on Machine Vision Applications (MVA), Nagoya, Japan (2017/05). (PDF)
• Keiji Yanai: Unseen Style Transfer Based on a Conditional Fast Style Transfer Network, Proc. International Conference on Learning Representation Workshop Track (ICLR WS), Toulon, France (2017/04). (paper)
• Shin Matsuo, Wataru Shimoda and Keiji Yanai: Twitter Photo Geo-Localization Using Both Textual and Visual Features, Proc. of International Conference on Multimedia Big Data (BIGMM), Laguna Hills, CA, USA (2017/04).
• Wataru Shimoda and Keiji Yanai: Learning Food Image Similarity for Food Image Retrieval, Proc. of International Conference on Multimedia Big Data (BIGMM), Laguna Hills, CA, USA (2017/04).

2016年度

• Do Hang Nga and Keiji Yanai: Automatic Retrieval of Action Video Shots from the Web using Density-based Cluster Analysis and Outlier Detection, IEICE Transactions on Information and Systems, Vol. E99-D, No.11, pp.- (2016/11).
• Takamu Kaneko and Keiji Yanai: Event Photo Mining from Twitter Using Keyword Bursts and Image Clustering, Neurocomputing, Elsevier, Vol.172, pp.143–158 (2016/08). (http://dx.doi.org/10.1016/j.neucom.2015.02.081) (pre-print)
• Ryosuke Tanno and Keiji Yanai: DeepStyleCam:DeepStyleCam: A Real-time Style Transfer App on iOS, Proc. of International Conference on Multimedia Modelling (MMM), Reykjavik, Iceland (2017/01). (Best Demo Award)
• Wataru Shimoda and Keiji Yanai: Weakly-Supervised Segmentation by Combining CNN
  Feature Maps and Object Saliency Maps, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Cancun, Mexico (2016/12).
• Ryosuke Tanno, Keiji Yanai: Caffe2C: A Framework for Easy Implementation of CNN-based Mobile Applications, International Workshop On Mobile Ubiquitous Systems, Infras- tructures, Communications, And AppLications (MUSICAL 2016), Hiroshima, Japan (2016/11).
• Wataru Shimoda and Keiji Yanai: Distinct Class Saliency Maps for Weakly Supervised Semantic Segmentation, Proc. of European Conference on Computer Vision (ECCV), Amsterdam, Netherlands (2016/10).
• Wataru Shimoda and Keiji Yanai:Foodness proposal for webly supervised food detection, Proc. of ACM MM Workshop on Multimedia Assisted Dietary Management (MADiMa), Amsterdam, Netherlands (2016/10).
• Koichi Okamoto and Keiji Yanai:An Automatic Calorie Estimation System of Food Images on a Smartphone, Proc. of ACM MM Workshop on Multimedia Assisted Dietary Management (MADiMa), Amsterdam, Netherlands (2016/10).
• >Ryosuke Tanno, Koichi Okamoto, Keiji Yanai:DeepFoodCam: A DCNN-based Real-time Mobile Food Recognition System, Proc. of ACM MM Workshop on Multimedia Assisted Dietary Management (MADiMa), demo paper, Amsterdam, Netherlands (2016/10).
• Keiji Yanai, Ryosuke Tanno and Koichi Okamoto: Efficient Mobile Implementation of A CNN-based Object Recognition System, Proc. of ACM Multimedia, Amsterdam, Netherlands (2016/10).
• Shin Matsuo and Keiji Yanai: CNN-based Style Vector for Style Image Retrieval, Proc. of ACM International Conference on Multimedia Retrieval (ICMR), New York, NY, USA (2016/06).
• Takao Kakimori, Makoto Okabe, Keiji Yanai, Rikio Onai: A System to Help Amateurs Take Pictures of Delicious Looking Food, Proc. of IEEE BigMM Workshop on Attractiveness Computing, Taipei, Taiwan (2016/05).
• Keiji Yanai and Takamu Kaneko: Visual Event Mining from the Twitter Stream, Proc. of the Twelfth International World Wide Web Conference (WWW), Poster Paper, Montreal, Canada (2016/04).
• Koichi Okamoto and Keiji Yanai: GrillCam: A Real-time Eating Action Recognition System, Proc. of International Conference on Multimedia Modelling (MMM), Miami, FL, USA (2016/01).

2015年度

• Keiji Yanai: A Review of Web Image Mining, ITE Transactions on Media Technology and Applications, Vol.3, No.3, pp.156-169 (2015/07). (open acess at J-Stage) (invited paper)
• Yoshiyuki Kawano and Keiji Yanai, FoodCam: A Real-time Food Recognition System on a Smartphone, Multimedia Tools and Applications, Springer, Vol. 74, Issue 14, pp 5263-5287 (2015/07). (http://dx.doi.org/10.1007/s11042-014-2000-8) (pre-print)
• Yoshiyuki Kawano and Keiji Yanai: Automatic Expansion of a Food Image Dataset Leveraging Existing Categories and Crowdsourcing, IEICE Transactions D-II, vol. J98-D, no.4 (2015/04). (in Japanese)
• Koichi Okamoto and Keiji Yanai: GrillCam: A Real-time Eating Action Recognition System, Proc. of International Conference on Multimedia Modelling (MMM), Miami, FL, USA (2016/01).
• Takao Kakimori, Makoto Okabe, Keiji Yanai and Rikio Onai: A system to support the amateurs to take a delicious-looking picture of foods, Proc. of SIGGRAPH ASIA Symposium on Mobile Graphics and Interactive Applications, Kobe, Japan (2015/11).
• Yoshiyuki Kawano and Keiji Yanai: Low-Bit Representation of Linear Classifier Weights for Mobile Large-Scale Image Classification, Proc. of Asian Conference on Pattern Recognition (ACPR), Kuala Lumpur, Malaysia (2015/11).
• Nga Do and Keiji Yanai: Automatic Action Dataset Construction from Web using Density-based Cluster Analysis and Outlier Detection, Proc. of Pacific Rim Symposium on Image and Video Technology (PSIVT), Auckland, New Zealand (2015/11).
• Wataru Shimoda and Keiji Yanai: CNN-Based Food Image Segmentation, Proc. of International Workshop on Multimedia Assisted Dietary Management (MADIMA), Genova, Italy (2015/09).
• Takamu Kaneko, Nga Do Hang, Keiji Yanai : Twitter Event Photo Detection Using Geotagged Tweets and Non-geotagged Photo Tweets, Proc. of Pacific-Rim Conference on Multimedia (PCM), Gwanju, Korea (2015/09).
• Wataru Shimoda, Keiji Yanai: A Visual Analysis on Recognizability and Discriminability of Onomatopoeia Words with DCNN Features, Proc. of IEEE International Conference on Multimedia and Expo (ICME), Torino, Italy (2015/06).
• Keiji Yanai, Yoshiyuki Kawano: Food Image Recognition using Deep Convolutional Network with Pre-training and Fine-tuining, Proc. ICME Workshop on Multimedia for Cooking and eating Activities (CEA), Trino, Italy (2015/06).

2014年度

• Do Hang Nga and Keiji Yanai:VisualTextualRank: An Extension of VisualRank to Large-Scale Video Shot Extraction exploiting Tag Co-occurrence, IEICE Transactions on Information and Systems, Vol. E98-D, No.1, pp.166-172 (2015/01). (http://dx.doi.org/10.1587/transinf.2014EDP7106)
• Yasuki Mukai and Keiji Yanai: Automamtic Construction of Geotagged Travel Movie Databases from TV Travel Programs, IEICE Transactions D-II, vol. J98-D, no.1,pp.269-274 (2015/01). (in Japanese)
  
• Masaya Okamoto and Keiji Yanai: Summarization of Egocentric Moving Videos for Generating Walking Route Guidance Videos, IEICE Transactions D-II, Vol.J97-D, No.8, pp.1237-1249 (2014/08) (in Japanese).
• Yoshiyuki Kawano and Keiji Yanai: ILSVRC on a Smartphone, IPSJ Transaction on Computer Vision and Applications, Vol.6, pp.83-87 (2014/07).
• Keiji Yanai, Takamu Kaneko and Yoshiyuki Kawano: Real-time Photo Mining from the Twitter Stream: Event Photo Discovery and Food Photo Detection, Proc. of IEEE International Symposium on Multimedia (ISM), Taichung, Taiwan (2014/12). (invited paper)
• Wataru Shimoda, Keiji Yanai: An Analysis on Visual Recognizability of Onomatopoeia Using Web Images and DCNN features, Proc. of PCM Workshop on Multimedia Big Data Analytics (MBDA), (2014/12). 
• Mizuki Akiyama, Yoshiyuki Kawano and Keiji Yanai: Object Categorization by Local Feature Matching with a Large Number of Web Images, Proc. of PCM Workshop on Multimedia Big Data Analytics (MBDA), (2014/12).
• Keiji Yanai and Yoshiyuki Kawano: Real-time Food Image Mining and Analysis from the Twitter, Proc. of Pacific-Rim Conference on Multimedia (PCM), Kuching, Malaysia (2014/12).
• Do Hang Nga and Keiji Yanai: Hand detection and tracking in videos for finegrained action recognition, Proc. of ACCV Workshop on Human Gait and Action Analysis in the Wild: Challenges and Applications, Singapore (2014/11).
• Yoshiyuki Kawano and Keiji Yanai: FoodCam-256: A Large-scale Real-time Mobile Food Recognition System employing High-Dimensional Features and Compression of Classifier Weights, Proc. of ACM Multimedia, demo paper, Orland, FL, USA (2014/11).
• Yoshiyuki Kawano and Keiji Yanai: Food Image Recognition with Deep Convolutional Features, Proc. of ACM UbiComp Workshop on Smart Technology for Cooking and Eating Activities (CEA), Seattle, WA, USA (2014/09).
• Yoshiyuki Kawano and Keiji Yanai: Automatic Expansion of a Food Image Dataset Leveraging Existing Categories with Domain Adaptation, Proc. of ECCV Workshop on on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), Zurich, Switzerland (2014/09).
• Koichi Okamoto and Keiji Yanai: Real-Time Eating Action Recognition System on A Smartphone, Proc. ICME WS on Mobile Multimedia Computing, Chengdu, China (2014/07). (invited paper)
• Yoshiyuki Kawano and Keiji Yanai: Offline 1000 Class Classification on a Smartphone,
  Proc. of IEEE CVPR International Workshop on Mobile Vision, Columbus, OH, USA (2014/06).

2013年度

• Do Hang Nga and Keiji Yanai: Automatic Extraction of Relevant Video Shots of Specific Actions Exploiting Web Data, Computer Vision and Image Understanding, Elsevier, Vol. 118, pp. 2-15 (2014/01). (PDF) (http://dx.doi.org/10.1016/j.cviu.2013.03.009)
• Yuji Matsuda and Keiji Yanai: Multiple-Food Image Recognition Considering Co-occurrence, IEICE Transactions D-II, Vol.J96-D, No.8, pp.1724-1730 (2013/08) (in Japanese).
• Do Hang Nga and Keiji Yanai: A Dense SURF and Triangulation based Spatio-Temporal Feature for Action Recognition, Proc. of Multimedia Modeling Conference (MMM), Dublin, Ireland (2014/01).
• Yoshiyuki Kawano and Keiji Yanai: FoodCam: A Real-time Mobile Food Recognition System employing Fisher Vector, Proc. of Multimedia Modeling Conference (MMM), Demo Paper, Dublin, Ireland (2014/01). (Best Demo Award)
• Do Hang Nga and Keiji Yanai: A Spatio-Temporal Feature based on Triangulation of Dense SURF, Proc. of ICCV Workshop on Action Recognition with a Large Number of Classes, Sydney, Australia (2013/12).
• Yoshiyuki Kawano and Keiji Yanai: Rapid Mobile Food Recognition using Fisher Vector, Proc. of Asian Conference on Pattern Recognition (ACPR), Naha, Okinawa, Japan (2013/11).
• Masaya Okamoto and Keiji Yanai: Summarization of Egocentric Moving Videos for Generating Walking Route Guidance, Proc. of Pacific-rim Symposium on Image and Vision Technology (PSIVT), Guanajuato, Mexico (2013/10).
• Do Hang Nga and Keiji Yanai: Large-scale Web Video Shot Ranking Based on Visual Features and Tag Co-occurrence, Proc. of ACM Multimedia, Barcelona, Spain (2013/10).
• Yoshiyuki Kawano, Takanori Sato, Takuma Maruyama, Keiji Yanai: MIRURECIPE: A Mobile Cooking Recipe Recommendation System with Food Ingredient Recognition, Proc. of International Conference on Multimedia and Expo, Demo Paper, San Jone, CA, USA (2013/07).
• Takamu Kaneko, Hiroyoshi Harada, Keiji Yanai: Twitter Visual Event Mining System, Proc. of International Conference on Multimedia and Expo, Demo Paper, San Jone, CA, USA (2013/07).
• Takamu Kaneko and Keiji Yanai: Visual Event Mining from Geo-Tweet Photos, Proc. of ICME WS on Social Multimedia Research, San Jone, CA, USA (2013/07).
  
• Yoshiyuki Kawano and Keiji Yanai: Real-time Mobile Food Recognition System, Proc. of CVPR WS on Mobile Vision, Portland, OR, USA (2013/06).

2012年度

• Yuji Matsuda, Hajime Hoashi and Keiji Yanai: Recognition of Multiple-Food Images by Detecting Candidate Regions, IEICE Transactions D-II, Vol.J95-D No.8, pp.1554-1564 (2012/08) (in Japanese).
• Keiji Yanai, Hidetoshi Kawakubo and Kobus Barnard: Entropy-based Analysis of Visual Concepts, In "Multimedia Information Extraction", Wiley-IEEE Computer Society Press, (2012/05) .
• Yuya Kohaya and Keiji Yanai: Visual Analysis of Tag Co-occurrence on Nouns and Adjectives, Proc. of Multimedia Modelling Conference (MMM), Huangshan, China (2013/01).
• Yuji Matsuda and Keiji Yanai: Multiple-Food Recognition Considering Co-occurrence employing Manifold Ranking, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Tsukuba, Japan (2012/11).
• Takuma Maruyama and Keiji Yanai: Real-time Mobile Recipe Suggestion System using Food Ingredient Recognition, ACM MM WS on Interactive Multimedia on Mobile and Portable Devices (IMMPD), Nara, Japan (2012/11).
• Yusuke Nakaji and Keiji Yanai: Visualization of Real-World Events with Tweet Photos, Proc. of IEEE ICME Workshop on Social Media Computing, Melbourn, Australia (2012/07).
• Yuji Matsuda and Keiji Yanai: Recognition of Multiple Food Images by Detecting Candidate Regions, Proc. of IEEE International Conference on Multimedia and Expo (ICME), Melbourn, Australia (2012/07). (UEC-FOOD dataset)
• Do Hang Nga and Keiji Yanai: Automatic Collection ofWeb Video Shots Corresponding to Specific Actions using Web Images, Proc. of IEEE CVPR Workshop on Large-Scale Video Search and Mining, Province, USA (2012/06)
• Keiji Yanai: World Seer: A Realtime Geo-Tweet Photo Mapping System, Proc. of ACM International Conference on Multimedia Retrieval (ICMR), Demo Paper, Hong Kong (2012/06).

2011年度

• Kohya Okuyama and Keiji Yanai: A Travel Planning System Based on Travel Trajectories Extracted from a Large Number of Geotagged Photos on the Web, Proc. of Pacific-Rim Conference on Multimedia, Sydney, Australia (2011/12).
• Do Hang Nga and Keiji Yanai: Automatic Construction of an Action Video Shot Database using Web Videos, Proc. of IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain (2011/11). (PDF)
  
• Yuta Akima, Hidetoshi Kawakubo, Keiji Yanai: Folksonomy-Based Automatic Construction of Visual Ontology Using Visual Features and Tag Co-occurrence, IEICE Transactions D-II, Vol.J94-D No.8, pp.1248-1259 (2011/08) (in Japanese).

2010年度

• Hidetoshi Kawakubo and Keiji Yanai: GeoVisualRank: A Ranking Method of Geotagged Images Considering Visual Similarity and Geo-location Proximity, Proc. of the Nineteenth International World Wide Web Conference (WWW), Poster Paper, Hyderabad, India (2011/03). (PDF)
  
• Hidetoshi Kawakubo, Yuuta Akima and Keiji Yanai: Automatic Construction of A Folksonomy-based Visual Ontology, Proc. of the Sixth IEEE International Workshop on Multimedia Information Processing and Retrieval (MIPR), Taichu, Taiwan (2010/12).
• Hajime Hoashi, Taichi Joutou and Keiji Yanai: Image Recognition of 85 Food Categories by Feature Fusion, Proc. of the Second Workshop on Multimedia for Cooking and Eating Activities, Taichu, Taiwan (2010/12).
• Keita Yaegashi and Keiji Yanai: Geotagged Image Recognition by Combining Three Different Kinds of Geolocation Features, Proc. of Asian Conference on Computer Vision (ACCV), Queenstown, New Zealand (2010/11). (PDF)
• Akitsugu Noguchi and Keiji Yanai: A SURF-based Spatio-Temporal Feature for Feature-fusion-based Action Recognition, Proc. of ECCV WS on Human Motion: Understanding, Modeling, Capture and Animation, Crete, Greece (2010/09). (PDF)
• Keita Yaegashi and Keiji Yanai: Geotagged Photo Recognition using Corresponding Aerial Photos with Multiple Kernel Learning, Proc. of IAPR International Conference on Pattern Recognition (ICPR), Istanbul, Turkey (2010/08).
• Keiji Yanai and Bingyu Qiu: Mining Regional Representative Photos from a Consumer-Generated Geotagged Photo Database, In "Handbook of Social Network Technologies and Applications", Springer, (2010/10).
• Taichi Joutou, Hajime Hoashi, Keiji Yanai: 50-Class Food-Image Recognition Employing Multiple Kernel Learning, IEICE Transactions D-II, Vol.J93-D No.8, pp.1397-1406 (2010/08) (in Japanese).
• Hidetoshi KAWAKUBO, Keiji YANAI: An Analysis of the Relation between Visual Concepts and Geo-Locations, IEICE Transactions D-II, Vol.J93-D No.8, pp.1417-1428 (2010/08) (in Japanese).

2009年度

• Keiji Yanai and Kobus Barnard: Region-based Automatic Web Image Selection, Proc. of ACM International Conference on Multimedia Information Retrieval (MIR), Philadelphia, USA (2010/03).
  
• Akio Kitahara and Keiji Yanai: Detecting ``In-play'' Photos from Web Sports News Photos, Proc. of the Pacific-Rim Conference on Multimedia, Bangkok, Thailand (2009/12).
• Taichi Joutou and Keiji Yanai: A Food Image Recognition System with Multiple Kernel Learning, Proc. of International Conference on Image Processing (ICIP), Cairo, Egypt (2009/11).
• Akitsugu Noguchi and Keiji Yanai: Extracting Spatio-temporal Local Features Considering Consecutiveness of Motions, Proc. of Asian Conference on Computer Vision (ACCV), Xian, China (2009/09). (PDF file)
• Keiji Yanai, Hidetoshi Kawakubo and Qiu Bingyu: A Visual Analysis of the Relationship between Word Concepts and Geographical Locations, Proc. of ACM International Conference of Image and Video Retrieval (CIVR), Santorini, Greece (2009/07). (PDF)
• Keiji Yanai: Web Image Gathering with Region-based Bag-of-Features and Multiple Instance Learning, IEEE International Conference on Multimedia and Expo (ICME), New York, USA (2009/07).
• Hidetoshi Kawakubo and Keiji Yanai: An Analysis of the Relation between Visual Concepts and Geo-locations using Geotagged Images on the Web, IEEE ICME WS on Internet Multimedia Search and Mining, New York, USA (2009/07).
• Keiji Yanai and Bingyu Qiu: Mining Cultural Differences from a Large Number of Geotagged Photo, Proc. of the Seventeenth International World Wide Web Conference, Poster Paper (WWW), Madrid, Spain (2009/04). (PDF file)
• Akio Kitahara and Keiji Yanai: Associating faces and names in Japanese photo news articles, Progress in Informatics, Vol. 7, pp.73-80, (2010/03).

2008年度

• Keita Yaegashi and Keiji Yanai: Can Geotags Help Image Recognition ?, Proc. of Pacific-Rim Symposium on Image and Video Technology, Tokyo, Japan (2009/01).
  
• Bingyu Qiu and Keiji Yanai: Objects over the World, Proc. of the Pacific-Rim Conference on Multimedia, Tainan, Taiwan (2008/12).
• Akitsugu Noguchi and Keiji yanai: Rushes Summarization Based on Color, Motion and Face, Proc. of ACMMM Workshop on TRECVID Rush Summarization, Vancouver, Canada (2008/10).
• Keisuke Takada and Keiji Yanai: Web Video Retrieval Based on the Earch Mover's Distance by Integrating Color, Motion and Sound Features, Proc. of the ICIP Workshop on Multimedia Information Retrieval, San Diego, CA, USA (2008/10).
• Keiji Yanai: Web Image Selection by PLSA, Proc. of the International Conference on Multimedia and Expo, Hanover, Germany (2008/06).
• Keiji Yanai: Automatic Web Image Selection with a Probabilistic Latent Topic Model, Proc. of the Seventeenth International World Wide Web Conference, Poster Paper, Beijing, China (2008/04).

2007年度

• Akio Kitahara and Keiji Yanai: Associating Faces and Names in Japanese Photo News Articles on the Web, Proc. of the 2008 IEEE International Symposium on Mining the Asian Web, Okinawa, Japan (2008/03).
• Keiji Yanai: Web Image Gathering witha Part-based Object Recognition Method, Proc. of the International Multimedia Modelling Conference, Kyoto, Japan, (2008/01).
• Iyota Tatsuya and Keiji Yanai: The News Flusher: a Photo News Clustering Browser, Proc. of the Pacific-Rim Conference on Multimedia, Hong Kong (2007/12). (PDF file)
• Keiji Yanai: Web Image Gathering with A Spatial Pyramid Kernel, Proc. of the IEEE Workshop on Multimedia Information Processing and Retrieval, Taichung, Taiwan (2007/12).
• Keiji Yanai: Image Collector III: A Web Image-Gathering System with Bag-of-Keypoints, Proc. of the Sixteenth International World Wide Web Conference, Poster Paper, Banff, AB, Canada (2007/05). (HTML)
• Keiji Yanai: Current State and Future Directions on Generic Object Recognition, IPSJ Transaction on Computer Vision and Image Media, Vol.48, No.SIG (CVIM19), (2007/11) (in Japanese).

2006年度

• Keiji Yanai: Image Classification by a Probabilistic Model Learned from Imperfect Training Data on the Web, Proc. of ACM Knowledge Discovery and Data Mining (KDD) Workshop on Multimedia Data Mining, pp.75-82 Philadelphia, USA (2006/08). (PDF file)
• Keiji Yanai and Kobus Barnard: Finding Visual Concept by Web Image Mining, Proc. of the Fifteenth International World Wide Web Conference, Poster Paper, Edinburgh, Scotland, UK (2006/05). (HTML)
  
• Kobus Barnard and Keiji Yanai: Mutual Information Between Words and Pictures, Proc. of Workshop on Information Theory and Applications, La Jolla, California USA, (2006/02). (PDF file) (invited paper)
• Keiji Yanai and Takehisa Hayashiyama: Automatic ``Go'' Record Generation from a TV Program, Proc. of the 12th International Multimedia Modelling Conference, Beijing, China, pp.414-417 (2006/01). (PDF file)
  
• Kobus Barnard, Keiji Yanai, Matthew Johnson and Prasad Gabbur: Cross Modal Disambiguation, In "Toward Category-Level Object Recognition", Lecture Note on Computer Science (LNCS), No.4170, pp.246-265 (2007/02).
• Keiji Yanai and Kobus Barnard: An Analysis of ``Visualness'' of Word Concepts, IPSJ Transactions on Computer Vision and Image Media, Vol.48, No.SIG (CVIM17), (2007/02) (in Japanese).
• Keiji Yanai: Web Image Gathering with Probabilistic Models, Transaction of the Japanese Society of Artificial Intelligence, Vol.21, No.1, pp.10-18 (2007/01) (in Japanese). (PDF file)

2005年度

• Keiji Yanai and Kobus Barnard: Image Region Entropy: A Measure of "Visualness" of Web Images Associated with One Concept, Proc. of ACM Multimedia 2005, Singapore, (2005/11). (PDF file) (poster)
• Keiji Yanai and Kobus Barnard: Probabilistic Web Image Gathering, Proc. of ACM Multimedia Workshop on Multimedia Information Retrieval (MIR) 2005, Singapore, (2005/11). (PDF file) (slides) (results)
• Keiji Yanai, Nikhil V. Shirahatti, Prasad Gabbur and Kobus Barnard: Evaluation Strategies for Image Understanding and Retrieval, Proc. of ACM Multimedia Workshop on Multimedia Information Retrieval (MIR) 2005, Singapore, (2005/11). (PDF file) (slides) (invited paper)
• Keiji Yanai: Image Collector II: A System to Gather a Large Number of Images from the Web, IEICE Transactions on Information and Systems, Vol.E88-D, No.10, pp.2432-2436 (2005/10).

2004年度以前

• Keiji Yanai: Mining Visual Knowledge on the World Wide Web for Generic Image Classification, Transaction of the Japanese Society of Artificial Intelligence, Vol.19, No.5, pp.429-439 (2004/10) (in Japanese). (PDF file)
• Keiji Yanai: Web Image Mining: Can We Gather Visual Knowledge for Image Recognition from the Web ?, Proc. of the 2003 Pacific-Rim International Conference on Multimedia, Singapore, pp.1B1-2 (2003/12). (PDF file) (invited paper)
• Keiji Yanai: Generic Image Classification Using Visual Knowledge on the Web, Proc. of ACM Multimedia 2003, Berkeley USA, pp.67-76 (2003/11). (ACM Digital Library) (PDF file) (acceptance rate: 16.9%)
• Keiji Yanai: Image Collector II: A System for Gathering More Than One Thousand Images from the Web for One Keyword, Proc. of IEEE International Conference on Multimedia and Expo, Baltimore USA, (2003/07). (PDF file)
• Keiji Yanai: Web Image Mining toward Generic Image Recognition, Proc. of the Twelfth International World Wide Web Conference, Poster Paper, Budapest Hungary, (2003/05). (HTML file)
• Keiji Yanai: Image Collector II: An Over-One-Thousand-Image-Gathering System, Proc. of the Twelfth International World Wide Web Conference, Poster Paper, Budapest Hungary, (2003/05). (HTML file)
• Keiji Yanai, Masaya Shindo, Kohei Noshita: A Fast Image-Gathering System on the World-Wide Web Using a PC Cluster, Image and Vision Computing, Vol.22, No.1, pp.59-71 (2004/01). (PDF file)
• Keiji Yanai: An Experiment on Generic Image Classification Using Web Images, Proc. of the 2002 Pacific-Rim International Conference on Multimedia (Springer LNCS no.2532), Shinchu Taiwan, pp.303-310 (2002/12). (PDF file)
• Keiji Yanai: Image Classification by Web Images, Proc. of the Seventh Pacific-Rim International Conference on Artificial Intelligence (Springer LNAI no.2417), Tokyo, Japan, pp.613-614 (2002/08).
• Keiji Yanai and Koichiro Deguchi: Recognition of Indoor Images Employing Supporting Relation between Objects, Systems and Computers in Japan, Vol.33, No.10, pp.14-26 (2002/10). (PDF file)
• Keiji Yanai: An Automatic Image-Gathering System for the World-Wide Web by Integration of Keywords and Image Features, Proc. of 4th International Conference on Computational Intelligence and Multimedia Applications, Yokosuka, Japan, pp.303-307 (2001/10).
• Keiji Yanai, Masaya Shindo, Kohei Noshita: A Fast Image-Gathering System on the World-Wide Web Using a PC Cluster, Proc. of the 2001 International Conference on Web Intelligence (Springer LNAI no.2198), Maebashi Japan, Full Paper, pp.324-334 (2001/10). (PDF file) (acceptance rate: 19.0%)
• Keiji Yanai: Image Collector: An Image-Gathering System from the World-Wide Web Employing Keyword-based Search Engines, Proc. of IEEE International Conference on Multimedia and Expo, Tokyo, Japan, pp.704-707 (2001/08). (PDF file)
• Yoshio Hoshi, Kohei Noshita and Keiji Yanai: A new algorithm for solving the cooperative Tsume-shogi based on iterative-deepening search, Transaction of Information Processing Society of Japan, Vol.43, No.1, pp.11-19 (2002/01) (in Japanese). (PDF file)
• Keiji Yanai and Koichiro Deguchi: A Multi-resolution Image Understanding System Based on Multi-agent Architecture for High-resolution Images, IEICE Transactions on Information and Systems, Vol.E84-D, No.12 (2001/12). (PDF file)
• Keiji Yanai: An Image Gathering System from WWW Employing Keywords and Image Features, IPSJ Transactions on Databases, Vol.42, No.SIG10(TOD11), pp.79-91 (2001/09) (in Japanese). (PDF file)
• Keiji Yanai and Koichiro Deguchi: Recognition of Indoor Images Employing Supporting Relation between Objects, IEICE Transactions D-II, Vol.84-DII, No.8, pp.1741-1752 (2001/08) (in Japanese). (PDF file)
• Keiji Yanai and Koichiro Deguchi: A Multi-resolution Image Understanding System Based on Multi-agent Architecture for High-resolution Images, Proc. of IAPR Workshop on Machine Vision and Applications (MVA), Tokyo, Japan, pp.291-294 (2000/11). (PDF file)
• Keiji Yanai and Koichiro Deguchi: Recognition of Indoor Images Employing Qualitative Model Fitting and Supporting Relation between Objects, Proc. of International Conference on Pattern Recognition (ICPR), Barcelona Spain, Vol.I, pp.964-967 (2000/09). (PDF file)
• Keiji Yanai: An Image Understanding System for Various Images Based on Multi-Agent Architecture, Proc. of 3rd International Conference on Computational Intelligence and Multimedia Applications, New Dehli India, pp.186-190 (1999/09). (PDF file)
  
• Keiji Yanai and Koichiro Deguchi: An Architecture of Object Recognition System for Various Images Based on Multi-Agent, Proc. of International Conference on Pattern Recognition (ICPR), Brisbane Australia, Vol.I, pp.643-646 (1998/08). (PDF file)
• Keiji Yanai and Koichiro Deguchi: A Multi-Agent Architecture of Object Recognition System for Various Image, Transaction of Information Processing Society of Japan, Vol.39, No.2, pp.170-177 (1998/02) (in Japanese). (PDF file)
  
  

Last modified: 2024-11-05 22:36