| Dualnet: Domain-invariant network for visual question answering K Saito, A Shin, Y Ushiku, T Harada 2017 IEEE International Conference on Multimedia and Expo (ICME), 829-834, 2017 | 80 | 2017 |
| Beyond caption to narrative: Video captioning with multiple sentences A Shin, K Ohnishi, T Harada 2016 IEEE International conference on image processing (ICIP), 3364-3368, 2016 | 40 | 2016 |
| Perspectives and prospects on transformer architecture for cross-modal tasks with language and vision A Shin, M Ishii, T Narihira International journal of computer vision 130 (2), 435-454, 2022 | 39 | 2022 |
| Image Captioning with Sentiment Terms via Weakly-Supervised Sentiment Dataset. A Shin, Y Ushiku, T Harada BMVC, 2016 | 23 | 2016 |
| Melody generation for pop music via word representation of musical properties A Shin, L Crestel, H Kato, K Saito, K Ohnishi, M Yamaguchi, M Nakawaki, ... arXiv preprint arXiv:1710.11549, 2017 | 20 | 2017 |
| Reference-based video colorization with spatiotemporal correspondence N Akimoto, A Hayakawa, A Shin, T Narihira arXiv preprint arXiv:2011.12528, 2020 | 13 | 2020 |
| Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives T Narihira, J Alonsogarcia, F Cardinaux, A Hayakawa, M Ishii, K Iwaki, ... arXiv preprint arXiv:2102.06725, 2021 | 12 | 2021 |
| The color of the cat is gray: 1 million full-sentences visual question answering (fsvqa) A Shin, Y Ushiku, T Harada arXiv preprint arXiv:1609.06657, 2016 | 12 | 2016 |
| Dense image representation with spatial pyramid vlad coding of cnn for locally robust captioning A Shin, M Yamaguchi, K Ohnishi, T Harada arXiv preprint arXiv:1603.09046, 2016 | 10 | 2016 |
| Customized image narrative generation via interactive visual question generation and answering A Shin, Y Ushiku, T Harada Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 9 | 2018 |
| True-negative label selection for large-scale multi-label learning A Kanehira, A Shin, T Harada 2016 23rd International Conference on Pattern Recognition (ICPR), 3673-3678, 2016 | 5 | 2016 |
| Large language models lack understanding of character composition of words A Shin, K Kaneko arXiv preprint arXiv:2405.11357, 2024 | 4 | 2024 |
| Context-Dependent Automatic Response Generation Using Statistical Machine Translation Techniques A Shin, R Sasano, T Hiroya, M Okumura NAACL-HLT 2015, 1345-1350, 2015 | 4 | 2015 |
| Transformer-exclusive cross-modal representation for vision and language A Shin, T Narihira Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 …, 2021 | 2 | 2021 |
| Control device, control method, and program A Irie, H Suzuki, T Kasai, M Nakamura, A Shin US Patent App. 17/263,854, 2021 | 2 | 2021 |
| Training system and data collection device A Shin, Y Kobayashi, K Suzuki US Patent App. 17/906,761, 2023 | 1 | 2023 |
| Information processing device, information processing method, and computer program A Shin, N Ide US Patent App. 17/275,671, 2022 | 1 | 2022 |
| The Lost Melody: Empirical Observations on Text-to-Video Generation From A Storytelling Perspective A Shin, Y Mori, K Kaneko arXiv preprint arXiv:2405.08720, 2024 | | 2024 |
| Minimum Steiner Tree Approximation for Extracting Unknown Information via Avoiding High-Centrality Nodes R Nishiyama, A Shin, N Matsumoto, K Kaneko 2024 International Conference on Information Networking (ICOIN), 581-586, 2024 | | 2024 |
| Cache-Efficient Approach for Index-Free Personalized PageRank K Tsuchida, N Matsumoto, A Shin, K Kaneko IEEE Access 11, 6944-6957, 2023 | | 2023 |
Tatsuya HaradaThe University of TokyoVerified email at mi.t.u-tokyo.ac.jp
