EC-Bench: Enumeration and Counting Benchmark for Ultra-Long Videos.

Fumihiko Tsuchiya, Taiki Miyanishi, Mahiro Ukai, Nakamasa Inoue, Shuhei Kurita, Yusuke Iwasawa, Yutaka Matsuo

CoRR   abs/2603.29943   2026.3

PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models.

Hisayuki Yokomizo, Taiki Miyanishi, Yan Gang, Shuhei Kurita, Nakamasa Inoue, Yusuke Iwasawa

CoRR   abs/2603.16958   2026.3

DISCODE: Distribution-Aware Score Decoder for Robust Automatic Evaluation of Image Captioning Reviewed

Nakamasa Inoue, Kanoko Goto, Masanari Ohi, Martyna Gruszka, Mahiro Ukai, Takumi Hirose, Yusuke Sekikawa

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)   2026.1

Contracted Gram Tensor Distillation for Object Detection Reviewed

Takumi Karasawa, Rei Kawakami, Nakamasa Inoue

Proceedings of the ACM Asian Conference on Multimedia (MMAsia)   1471 - 1476   2025.12

Masked Gated Linear Unit Reviewed

Yukito Tajima, Nakamasa Inoue, Yusuke Sekikawa, Ikuro Sato, Rio Yokota

Proceedings of Neural Information Processing Systems (NeurIPS)   abs/2506.23225   2025.11

STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models Reviewed

Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue

Proceedings of ACM Multimedia (ACMMM)   4718 - 4727   2025.10

GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields Reviewed

Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Masato Taki, Yutaka Matsuo

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)   abs/2506.23352   9737 - 9748   2025.10

AgroBench: Vision-Language Model Benchmark in Agriculture Reviewed

Risa Shinoda, Nakamasa Inoue, Hirokatsu Kataoka, Masaki Onishi, Yoshitaka Ushiku

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)   abs/2507.20519   7634 - 7644   2025.10

AnimalClue: Recognizing Animals by their Traces Reviewed

Risa Shinoda, Nakamasa Inoue, Iro Laina, Christian Rupprecht, Hirokatsu Kataoka

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)   abs/2507.20240   14776 - 14786   2025.10

CityNav: A Large-Scale Dataset for Real-World Aerial Navigation Reviewed

Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, Nakamasa Inoue

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)   5912 - 5922   2025.10

Referring Expression Comprehension for Small Objects Reviewed

Kanoko Goto, Takumi Hirose, Mahiro Ukai, Shuhei Kurita, Nakamasa Inoue

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)   21231 - 21242   2025.10

Collision Avoidance with Differentiable Occupancy Functions in Object Rearrangement Reviewed

Roma Satoh, Nakamasa Inoue, Rei Kawakami

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)   2025.10

GASR: Generated Artwork dataset for Image Super-Resolution Reviewed

Noritake Kodama, Go Ohtani, Yuto Matsuo, Rintaro Yanagi, Nakamasa Inoue, Yoshimitsu Aoki, Hirokatsu Kataoka

Proceedings of the CVPR Workshop on Synthetic Data for Computer Vision (SynData4CV)   2025.6

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis Reviewed

Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue

Proceedings of the International Conference on Learning Representations (ICLR)   2025.4

Multi-Point Positional Insertion Tuning for Small Object Detection Reviewed

Kanoko Goto, Takumi Karasawa, Takumi Hirose, Rei Kawakami, Nakamasa Inoue

Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   1 - 5   2025.4

Binary Stochastic Flip Optimization for Training Binary Neural Networks Reviewed

Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, Ikuro Sato

Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   1 - 5   2025.4

ContextualCoder: Adaptive In-context Prompting for Programmatic Visual Question Answering Reviewed International journal

Ruoyue Shen, Nakamasa Inoue, Dayan Guan, Rizhao Cai, Alex C. Kot, Koichi Shinoda

IEEE Transactions on Multimedia (TMM)   27   4936 - 4949   2025.4

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process.

Shun Iwase, Shuya Takahashi, Nakamasa Inoue, Rio Yokota, Ryo Nakamura, Hirokatsu Kataoka

CoRR   abs/2503.02302   2025.3

Diffusion-based Generative Regularization for Supervised Discriminative Learning Reviewed

Takuya Asakura, Nakamasa Inoue, Koichi Shinoda

Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)   8897 - 8908   2025.2

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks Reviewed

Ryo Moriai, Nakamasa Inoue, Masayuki Tanaka, Rei Kawakami, Satoshi Ikehata, Ikuro Sato

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)   19554 - 19562   2025.2

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks.

Ryo Moriai, Nakamasa Inoue, Masayuki Tanaka 0001, Rei Kawakami, Satoshi Ikehata, Ikuro Sato

CoRR   abs/2502.14003   2025.2

ContextualCoder: Adaptive In-Context Prompting for Programmatic Visual Question Answering.

Ruoyue Shen, Nakamasa Inoue, Dayan Guan, Rizhao Cai, Alex C. Kot, Koichi Shinoda

IEEE Trans. Multim.   27   4936 - 4949   2025

A Simple Fine-Tuning Strategy Based on Bias-Variance Ratios of Layer-Wise Gradients Reviewed

Mao Tomita, Ikuro Sato, Rei Kawakami, Nakamasa Inoue, Satoshi Ikehata, Masayuki Tanaka

Proceedings of Asian Conference on Computer Vision (ACCV)   192 - 209   2024.12

On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning Process Reviewed

Shun Iwase, Shuya Takahashi, Nakamasa Inoue, Rio Yokota, Ryo Nakamura, Hirokatsu Kataoka, Eisaku Maeda

Proceedings of International Conference on Pattern Recognition (ICPR)   95 - 109   2024.12

AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering Reviewed

Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto, Yoshitaka Ushiku, Nakamasa Inoue

Proceedings of ACM Multimedia (ACMMM)   9234 - 9243   2024.10

Spatiality-aware Prompt Tuning for Few-shot Small Object Detection Reviewed

Takumi Karasawa, Nakamasa Inoue, Rei Kawakami

Proceedings of IEEE International Conference on Image Processing (ICIP)   305 - 311   2024.10

Pyramid Coder: Hierarchical Code Generation for Compositional Visual Question Answering Reviewed

Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda

Proceedings of IEEE International Conference on Image Processing (ICIP)   430 - 436   2024.10

Rethinking Image Super Resolution from Training Data Perspectives Reviewed

Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki

Proceedings of European Conference on Computer Vision (ECCV)   19 - 36   2024.9

Scaling Backwards: Minimal Synthetic Pre-training Reviewed

Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka

Proceedings of European Conference on Computer Vision (ECCV)   153 - 171   2024.9

Formula-Supervised Visual-Geometric Pre-training Reviewed

Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka, Koshi Makihara, Nakamasa Inoue, Rio Yokota, Yutaka Satoh

Proceedings of European Conference on Computer Vision (ECCV)   57 - 74   2024.9

Locally Aligned Rectified Flow Model for Speech Enhancement Towards Single-Step Diffusion Reviewed

Li Zhengxiao, Nakamasa Inoue

Proceedings of Interspeech   2024.9

Augmenting Pass Prediction via Imitation Learning in Soccer Simulations Reviewed

Takeshi Kaneko, Rei Kawakami, Takeshi Naemura, Nakamasa Inoue

Proceedings of CVPR Workshop on Computer Vision in Sports (CVsports)   3194 - 3203   2024.6

SIFTer: Self-improving Synthetic Datasets for Pre-training Classification Models Reviewed

Ryo Hayamizu, Shota Nakamura, Sora Takashima, Hirokatsu Kataoka, Ikuro Sato, Nakamasa Inoue, Rio Yokota

Proceedings of CVPR Workshop on Synthetic Data for Computer Vision (SynData4CV)   2024.6

PolarDB: Formula-Driven Dataset for Pre-Training Trajectory Encoders Reviewed

Sota Miyamoto, Takuma Yagi, Yuto Makimoto, Mahiro Ukai, Yoshitaka Ushiku, Atsushi Hashimoto, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   5465 - 5469   2024.4

Pseudo-outlier Synthesis Using q-Gaussian Distributions for Out-of-distribution Detection Reviewed

Ryo Nakamura, Ryu Tadokoro, Eisuke Yamagata, Yusuke Kondo, Kensho Hara, Hirokatsu Kataoka, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   3120 - 3124   2024.4

Cubic Knowledge Distillation for Speech Emotion Recognition Reviewed

Zhibo Lou, Shinta Otake, Zhengxiao Li, Rei Kawakami, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   5705 - 5709   2024.4

ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks Reviewed International journal

Nakamasa Inoue, Shinta Otake, Takumi Hirose, Masanari Ohi, Rei Kawakami

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)   32   3867 - 3880   2024.4

Efficient Target Propagation by Deriving Analytical Solution Reviewed

Yanhao Bao, Tatsukichi Shibuya, Ikuro Sato, Rei Kawakami, Nakamasa Inoue

Proceedings of AAAI Conference on Artificial Intelligence (AAAI)   11016 - 11023   2024.2

Multi-Point Positional Insertion Tuning for Small Object Detection.

Kanoko Goto, Takumi Karasawa, Takumi Hirose, Rei Kawakami, Nakamasa Inoue

CoRR   abs/2412.18090   2024

HarmonicEval: Multi-modal, Multi-task, Multi-criteria Automatic Evaluation Using a Vision Language Model.

Masanari Ohi, Masahiro Kaneko, Naoaki Okazaki, Nakamasa Inoue

CoRR   abs/2412.14613   2024

Scaling Backwards: Minimal Synthetic Pre-training?

Ryo Nakamura, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht 0001, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka

CoRR   abs/2408.00677   2024

ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks.

Nakamasa Inoue, Shinta Otake, Takumi Hirose, Masanari Ohi, Rei Kawakami

CoRR   abs/2407.21066   2024

Pyramid Coder: Hierarchical Code Generator for Compositional Visual Question Answering.

Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda

CoRR   abs/2407.20563   2024

AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering.

Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto 0001, Yoshitaka Ushiku, Nakamasa Inoue

CoRR   abs/2407.19410   2024

CityNav: Language-Goal Aerial Navigation Dataset with Geographic Information.

Jungdae Lee, Taiki Miyanishi, Shuhei Kurita, Koya Sakamoto, Daichi Azuma, Yutaka Matsuo, Nakamasa Inoue

CoRR   abs/2406.14240   2024

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis.

Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue

CoRR   abs/2410.04380   2024

Formula-Supervised Visual-Geometric Pre-training.

Ryosuke Yamada, Kensho Hara, Hirokatsu Kataoka, Koshi Makihara, Nakamasa Inoue, Rio Yokota, Yutaka Satoh

CoRR   abs/2409.13535   2024

Rethinking Image Super-Resolution from Training Data Perspectives.

Go Ohtani, Ryu Tadokoro, Ryosuke Yamada, Yuki M. Asano, Iro Laina, Christian Rupprecht 0001, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka, Yoshimitsu Aoki

CoRR   abs/2409.00768   2024

CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data Reviewed

Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita, Jungdae Lee, Motoaki Kawanabe, Nakamasa Inoue

Proceedings of Neural Information Processing Systems (NeurIPS)   77758 - 77770   2023.12

Scale-space Tokenization for Improving the Robustness of Vision Transformers Reviewed

Lei Xu, Rei Kawakami, Nakamasa Inoue

Proceedings of ACM Multimedia (ACMMM)   2684 - 2693   2023.10

Pre-training Vision Transformers with Very Limited Synthesized Images Reviewed

Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima, Edgar Josafat Martinez-Noriega, Rio Yokota, Nakamasa Inoue

Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV)   abs/2307.14710   20360 - 20369   2023.10

SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning Reviewed

Risa Shinoda, Ryo Hayamizu, Kodai Nakashima, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka

Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV)   abs/2309.17083   20054 - 20063   2023.10

Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves Reviewed

Sora Takashima, Ryo Hayamizu, Nakamasa Inoue, Hirokatsu Kataoka, Rio Yokota

Proceedings of IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)   18579 - 18588   2023.6

Step Restriction for Improving Adversarial Attacks Reviewed

Keita Goto, Shinta Otake, Rei Kawakami, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   1 - 5   2023.6

Parameter Efficient Transfer Learning for Various Speech Processing Tasks Reviewed

Shinta Otake, Rei Kawakami, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   1 - 5   2023.6

Learning with Partial Forgetting in Modern Hopfield Networks Reviewed

Toshihiro Ota, Ikuro Sato, Rei Kawakami, Masayuki Tanaka, Nakamasa Inoue

Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS)   6661 - 6673   2023.4

Fixed-Weight Difference Target Propagation Reviewed

Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, Ikuro Sato

Proceedings of AAAI Conference on Artificial Intelligence (AAAI)   9811 - 9819   2023.2

Text-Guided Object Detector for Multi-modal Video Question Answering Reviewed

Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda

Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)   1032 - 1042   2023.1

CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data.

Taiki Miyanishi, Fumiya Kitamori, Shuhei Kurita, Jungdae Lee, Motoaki Kawanabe, Nakamasa Inoue

CoRR   abs/2310.18773   2023

Pre-training Vision Transformers with Very Limited Synthesized Images.

Ryo Nakamura, Hirokatsu Kataoka, Sora Takashima, Edgar Josafat Martinez-Noriega, Rio Yokota, Nakamasa Inoue

IEEE/CVF International Conference on Computer Vision(ICCV)   20303 - 20312   2023

SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning.

Risa Shinoda, Ryo Hayamizu, Kodai Nakashima, Nakamasa Inoue, Rio Yokota, Hirokatsu Kataoka

IEEE/CVF International Conference on Computer Vision(ICCV)   19997 - 20006   2023

Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves.

Sora Takashima, Ryo Hayamizu, Nakamasa Inoue, Hirokatsu Kataoka, Rio Yokota

CoRR   abs/2303.01112   2023

PoF: Post-Training of Feature Extractor for Improving Generalization Reviewed

Ikuro Sato, Ryota Yamada, Masayuki Tanaka, Nakamasa Inoue, Rei Kawakami

Proceedings of International Conference on Machine Learning (ICML)   19221 - 19230   2022.7

Replacing Labeled Real-image Datasets with Auto-generated Contours Reviewed

Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota

Proceedings of IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)   abs/2206.09132   21232 - 21241   2022.6

Downstream Augmentation Generation for Contrastive Learning Reviewed

Tomohiro Hayase, Suguru Yasutomi, Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   2115 - 2119   2022.5

Pre-training without Natural Images Reviewed International journal

Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

International Journal of Computer Vision (IJCV)   130 ( 4 )   990 - 1007   2022.4

Can Vision Transformers Learn without Natural Images? Reviewed

Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto, Kenji Iwata, Nakamasa Inoue, Yutaka Satoh

Proceedings of AAAI Conference on Artificial Intelligence (AAAI)   1990 - 1998   2022.2

Spatiotemporal Initialization for 3D CNNs with Generated Motion Patterns Reviewed

Hirokatsu Kataoka, Kensho Hara, Ryusuke Hayashi, Eisuke Yamagata, Nakamasa Inoue

Proceedings of IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)   1279 - 1288   2022.1

Fixed-Weight Difference Target Propagation.

Tatsukichi Shibuya, Nakamasa Inoue, Rei Kawakami, Ikuro Sato

CoRR   abs/2212.10352   2022

Parameter Efficient Transfer Learning for Various Speech Processing Tasks.

Shinta Otake, Rei Kawakami, Nakamasa Inoue

CoRR   abs/2212.02780   2022

PoF: Post-Training of Feature Extractor for Improving Generalization.

Ikuro Sato, Ryota Yamada, Masayuki Tanaka 0001, Nakamasa Inoue, Rei Kawakami

CoRR   abs/2207.01847   2022

Replacing Labeled Real-image Datasets with Auto-generated Contours.

Hirokatsu Kataoka, Ryo Hayamizu, Ryosuke Yamada, Kodai Nakashima, Sora Takashima, Xinyu Zhang, Edgar Josafat Martinez-Noriega, Nakamasa Inoue, Rio Yokota

IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR)   21200 - 21209   2022

Augmentation-Agnostic Regularization for Unsupervised Contrastive Learning with Its Application to Speaker Verification Reviewed

Nakamasa Inoue, Tsubasa Maruyama, Keita Goto

Proceedings of Asia-Pacific Signal and Information Processing Association Annual Conference (APSIPA)   1993 - 1998   2021.12

Formula-Driven Supervised Learning with Recursive Tiling Patterns Reviewed

Hirokatsu Kataoka, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Yutaka Satoh

Proceedings of ICCV HTCV Workshop   4098 - 4105   2021.10

Disentangling Latent Groups of Factors Reviewed

Nakamasa Inoue, Ryota Yamada, Rei Kawakami, Ikuro Sato

Proceedings of IEEE International Conference on Image Processing (ICIP)   2548 - 2552   2021.9

Learning VAE with Categorical Labels for Generating Conditional Handwritten Characters Reviewed

Keita Goto, Nakamasa Inoue

Proceedings of International Conference on Machine Vision Applications (MVA)   1 - 5   2021.7

Self-supervised Continual Pretraining for Class Incremental Image Classification Reviewed

Hikaru Nakata, Nakamasa Inoue, Rio Yokota

Proceedings of IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) CLVISION Workshop   2021.6

Teacher-Assisted Mini-Batch Sampling for Blind Distillation using Metric Learning Reviewed

Nakamasa Inoue

Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)   4160 - 4164   2021.6

Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network Reviewed International journal

Mariana Rodrigues Makiuchi, Tifani Warnita, Nakamasa Inoue, Koichi Shinoda, Michitaka Yoshimura, Momoko Kitazawa, Kei Funaki, Yoko Eguchi, Taishiro Kishimoto

IEICE Trans. on Information and Systems   E104–D ( 11 )   1930 - 1940   2021.4

Data Driven Analysis and Prediction of MILD Combustion Mode Reviewed International journal

Kherlen Jigjid, Chitoshi Tamaoki, Yuki Minamoto, Ryota Nakazawa, Nakamasa Inoue, Mamoru Tanahashi

Combustion and Flame   223   475 - 485   2021.4

Species Reaction Rate Modelling based on Physics-Guided Machine Learning Reviewed International journal

Ryota Nakazawa, Yuki Minamoto, Nakamasa Inoue, Mamoru Tanahashi

Combustion and Flame   235   1 - 11   2021.4

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data Reviewed

Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka

Proceedings of International Conference on Pattern Recognition (ICPR)   1023 - 1028   2021.1

Augmented Cyclic Consistency Regularization for Unpaired Image-To-Image Translation Reviewed

Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue

Proceedings of International Conference on Pattern Recognition (ICPR)   362 - 369   2021.1

Pre-training without Natural Images.

Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

CoRR   abs/2101.08515   2021

Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data.

Nakamasa Inoue, Eisuke Yamagata, Hirokatsu Kataoka

CoRR   abs/2101.07406   2021

Can Vision Transformers Learn without Natural Images?

Kodai Nakashima, Hirokatsu Kataoka, Asato Matsumoto, Kenji Iwata, Nakamasa Inoue

CoRR   abs/2103.13023   2021

Quasi-Newton Adversarial Attacks on Speaker Verification Systems Reviewed

Keita Goto, Nakamasa Inoue

Proceedings of Asia-Pacific Signal and Information Processing Association Annual Conference (APSIPA)   527 - 531   2020.12

Optimizing Speaker Embeddings using Meta-Training Sets Reviewed

Nakamasa Inoue, Keita Goto

Proceedings of Asia-Pacific Signal and Information Processing Association Annual Conference (APSIPA)   600 - 604   2020.12

Closed-Form Pre-Training for Small-Sample Environmental Sound Recognition Reviewed

Nakamasa Inoue, Keita Goto

Proceedings of Asia-Pacific Signal and Information Processing Association Annual Conference (APSIPA)   1693 - 1697   2020.12

Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition Reviewed

Nakamasa Inoue, Keita Goto

Proceedings of Asia-Pacific Signal and Information Processing Association Annual Conference (APSIPA)   1641 - 1646   2020.12

Graph Grouping Loss for Metric Learning of Face Image Representations Reviewed

Nakamasa Inoue

Proceedings of IEEE International Conference on Visual Communications and Image Processing (VCIP)   152 - 155   2020.12

Pre-training without Natural Images Reviewed

Hirokatsu Kataoka, Kazushige Okayasu, Asato Matsumoto, Eisuke Yamagata, Ryosuke Yamada, Nakamasa Inoue, Akio Nakamura, Yutaka Satoh

Proceedings of Asian Conference on Computer Vision (ACCV)   583 - 600   2020.11

Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition.

Nakamasa Inoue, Keita Goto

CoRR   abs/2006.04326   2020

Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation.

Takehiko Ohkawa, Naoto Inoue, Hirokatsu Kataoka, Nakamasa Inoue

CoRR   abs/2003.00187   2020

Deep Video Understanding of Character Relationships in Movies.

Yang Lu, Asri Rizki Yuliani, Keisuke Ishikawa, Ronaldo Prata Amorim, Roland Hartanto, Nakamasa Inoue, Kuniaki Uto, Koichi Shinoda

Companion Publication of the 2020 International Conference on Multimodal Interaction   120 - 129   2020

Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network.

Tifani Warnita, Mariana Rodrigues Makiuchi, Nakamasa Inoue, Koichi Shinoda, Michitaka Yoshimura, Momoko Kitazawa, Kei Funaki, Yoko Eguchi, Taishiro Kishimoto

CoRR   abs/2004.07992   2020

Tokyo Tech at TRECVID 2020: Relation Modeling for Video Action Detection.

Ronaldo Prata Amorim, Nakamasa Inoue, Koichi Shinoda

2020 TREC Video Retrieval Evaluation(TRECVID)   2020

Sequence-level Knowledge Distillation for Model Compression of Attention-based Sequence-to-sequence Speech Recognition.

Raden Mu'az Mun'im, Nakamasa Inoue, Koichi Shinoda

IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP)   6151 - 6155   2019

A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition.

Thao Le Minh, Nakamasa Inoue, Koichi Shinoda

British Machine Vision Conference 2018(BMVC)   227 - 227   2018

Detecting Alzheimer's Disease Using Gated Convolutional Neural Network from Audio Data.

Tifani Warnita, Nakamasa Inoue, Koichi Shinoda

19th Annual Conference of the International Speech Communication Association(INTERSPEECH)   1706 - 1710   2018

Multi-Task Autoencoder for Noise-Robust Speech Recognition.

Haoyi Zhang, Conggui Liu, Nakamasa Inoue, Koichi Shinoda

2018 IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP)   5599 - 5603   2018

I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification.

Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda

19th Annual Conference of the International Speech Communication Association(INTERSPEECH)   3613 - 3617   2018

Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition.

Raden Mu'az Mun'im, Nakamasa Inoue, Koichi Shinoda

CoRR   abs/1811.04531   2018

Few-Shot Adaptation for Multimedia Semantic Indexing.

Nakamasa Inoue, Koichi Shinoda

CoRR   abs/1807.07203   2018

A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition.

Thao Le Minh, Nakamasa Inoue, Koichi Shinoda

CoRR   abs/1805.11790   2018

Detecting Alzheimer's Disease Using Gated Convolutional Neural Network from Audio Data.

Tifani Warnita, Nakamasa Inoue, Koichi Shinoda

CoRR   abs/1803.11344   2018

I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification.

Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda

CoRR   abs/1804.00290   2018

VANT at TRECVID 2018.

Nakamasa Inoue, Chihiro Shiraishi, Aleksandr Drozd, Koichi Shinoda, Shi-wook Lee, Alex ChiChung Kot

2018 TREC Video Retrieval Evaluation(TRECVID)   2018

Few-Shot Adaptation for Multimedia Semantic Indexing.

Nakamasa Inoue, Koichi Shinoda

2018 ACM Multimedia Conference on Multimedia Conference   1110 - 1118   2018

Cross-view human action recognition from depth maps using spectral graph sequences.

Tommi Kerola, Nakamasa Inoue, Koichi Shinoda

Computer Vision and Image Understanding   154   108 - 126   2017

TokyoTech-AIST at TRECVID 2017: Multimedia Event Detection Using Deep CNNs and Zero-Shot Classiers.

Nakamasa Inoue, Ryosuke Yamamoto, Na Rong, Satoshi Kanai, Junsuke Masada, Chihiro Shiraishi, Shi-wook Lee, Koichi Shinoda

2017 TREC Video Retrieval Evaluation(TRECVID)   2017

CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos.

Mengxi Lin, Nakamasa Inoue, Koichi Shinoda

Proceedings of the on Thematic Workshops of ACM Multimedia 2017   393 - 401   2017

User adaptation of convolutional neural network for human activity recognition.

Shinya Matsui, Nakamasa Inoue, Yuko Akagi, Goshu Nagino, Koichi Shinoda

25th European Signal Processing Conference(EUSIPCO)   753 - 757   2017

A unified network for multi-speaker speech recognition with multi-channel recordings.

Conggui Liu, Nakamasa Inoue, Koichi Shinoda

2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference(APSIPA)   1304 - 1307   2017

Multimodal speech recognition using mouth images from depth camera.

Yuki Yasui, Nakamasa Inoue, Koji Iwano, Koichi Shinoda

2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference(APSIPA)   1233 - 1236   2017

Fast Coding of Feature Vectors Using Neighbor-to-Neighbor Search.

Nakamasa Inoue, Koichi Shinoda

IEEE Transactions on Pattern Analysis and Machine Intelligence   38 ( 6 )   1170 - 1184   2016

TokyoTech at TRECVID 2016.

Nakamasa Inoue, Ryosuke Yamamoto, Na Rong, Koichi Shinoda

2016 TREC Video Retrieval Evaluation(TRECVID)   2016

Adaptation of Word Vectors using Tree Structure for Visual Semantics.

Nakamasa Inoue, Koichi Shinoda

Proceedings of the 2016 ACM Conference on Multimedia Conference   277 - 281   2016

Tokyo Tech at MediaEval 2016 Multimodal Person Discovery in Broadcast TV task.

Fumito Nishi, Nakamasa Inoue, Koji Iwano, Koichi Shinoda

Working Notes Proceedings of the MediaEval 2016 Workshop(MediaEval)   2016

Graph regularized implicit pose for 3D human action recognition.

Tommi Kerola, Nakamasa Inoue, Koichi Shinoda

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference(APSIPA)   1 - 4   2016

TokyoTech at TRECVID 2015.

Nakamasa Inoue, Hai Dang Tran, Ryosuke Yamamoto, Koichi Shinoda

2015 TREC Video Retrieval Evaluation(TRECVID)   2015

Vocabulary Expansion Using Word Vectors for Video Semantic Indexing.

Nakamasa Inoue, Koichi Shinoda

Proceedings of the 23rd Annual ACM Conference on Multimedia Conference   851 - 854   2015

Combining Audio Features and Visual I-Vector @ MediaEval 2015 Multimodal Person Discovery in Broadcast TV.

Fumito Nishi, Nakamasa Inoue, Koichi Shinoda

Working Notes Proceedings of the MediaEval 2015 Workshop(MediaEval)   2015

TokyoTech-Waseda at TRECVID 2014.

Nakamasa Inoue, Zhuolin Liang, Mengxi Lin, Hai Dang Tran, Koichi Shinoda, Xuefeng Zhang, Kazuya Ueki

2014 TREC Video Retrieval Evaluation(TRECVID)   2014

Event Detection by Velocity Pyramid.

Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda

MultiMedia Modeling - 20th Anniversary International Conference   353 - 364   2014

n-gram Models for Video Semantic Indexing.

Nakamasa Inoue, Koichi Shinoda

Proceedings of the ACM International Conference on Multimedia   777 - 780   2014

Spectral Graph Skeletons for 3D Action Recognition.

Tommi Kerola, Nakamasa Inoue, Koichi Shinoda

Computer Vision - ACCV 2014 - 12th Asian Conference on Computer Vision   417 - 432   2014

TokyoTechCanon at TRECVID 2013.

Nakamasa Inoue, Kotaro Mori, Zhuolin Liang, Mengxi Lin, Koichi Shinoda, Shunsuke Sato

2013 TREC Video Retrieval Evaluation(TRECVID)   2013

q-Gaussian mixture models for image and video semantic indexing.

Nakamasa Inoue, Koichi Shinoda

Journal of Visual Communication and Image Representation   24 ( 8 )   1450 - 1457   2013

Event detection in consumer videos using GMM supervectors and SVMs.

Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda

EURASIP Journal on Image and Video Processing   2013   51 - 51   2013

Neighbor-to-Neighbor Search for Fast Coding of Feature Vectors.

Nakamasa Inoue, Koichi Shinoda

IEEE International Conference on Computer Vision(ICCV)   1233 - 1240   2013

Reusing Speech Techniques for Video Semantic Indexing [Applications Corner].

Koichi Shinoda, Nakamasa Inoue

IEEE Signal Processing Magazine   30 ( 2 )   118 - 122   2013

A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors.

Nakamasa Inoue, Koichi Shinoda

IEEE Transactions on Multimedia   14 ( 4 )   1196 - 1205   2012

TokyoTechCanon at TRECVID 2012.

Nakamasa Inoue, Yusuke Kamishima, Kotaro Mori, Koichi Shinoda

2012 TREC Video Retrieval Evaluation(TRECVID)   2012

Multimedia event detection using GMM supervectors and SVMS.

Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda, Shunsuke Sato

19th IEEE International Conference on Image Processing(ICIP)   3089 - 3092   2012

q-Gaussian Mixture Models Based on Non-extensive Statistics for Image and Video Semantic Indexing.

Nakamasa Inoue, Koichi Shinoda

Computer Vision - ACCV 2012   499 - 510   2012

A fast MAP adaptation technique for gmm-supervector-based video semantic indexing systems.

Nakamasa Inoue, Koichi Shinoda

Proceedings of the 19th International Conference on Multimedia 2011   1357 - 1360   2011

TokyoTech+Canon at TRECVID 2011.

Nakamasa Inoue, Toshiya Wada, Yusuke Kamishima, Koichi Shinoda, Shunsuke Sato

2011 TREC Video Retrieval Evaluation(TRECVID)   2011

High-Level Feature Extraction Using SIFT GMMs and Audio Models.

Nakamasa Inoue, Tatsuhiko Saito, Koichi Shinoda, Sadaoki Furui

20th International Conference on Pattern Recognition(ICPR)   3220 - 3223   2010

TT+GT at TRECVID 2010 Workshop.

Nakamasa Inoue, Toshiya Wada, Yusuke Kamishima, Koichi Shinoda, Ilseo Kim, Byungki Byun, Chin-Hui Lee

TRECVID 2010 workshop participants notebook papers(TRECVID)   2010

TITGT at TRECVID 2009 Workshop.

Nakamasa Inoue, Shanshan Hao, Tatsuhiko Saito, Koichi Shinoda, Ilseo Kim, Chin-Hui Lee

TRECVID 2009 workshop participants notebook papers(TRECVID)   2009