Yoshitaka Ushiku

5.9k total citations · 1 hit paper
55 papers, 1.2k citations indexed

About

Yoshitaka Ushiku is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Materials Chemistry. According to data from OpenAlex, Yoshitaka Ushiku has authored 55 papers receiving a total of 1.2k indexed citations (citations by other indexed papers that have themselves been cited), including 39 papers in Computer Vision and Pattern Recognition, 18 papers in Artificial Intelligence and 6 papers in Materials Chemistry. Recurrent topics in Yoshitaka Ushiku's work include Multimodal Machine Learning Applications (19 papers), Advanced Image and Video Retrieval Techniques (17 papers) and Video Analysis and Summarization (10 papers). Yoshitaka Ushiku is often cited by papers focused on Multimodal Machine Learning Applications (19 papers), Advanced Image and Video Retrieval Techniques (17 papers) and Video Analysis and Summarization (10 papers). Yoshitaka Ushiku collaborates with scholars based in Japan, United States and Switzerland. Yoshitaka Ushiku's co-authors include Tatsuya Harada, Takumi Karasawa, Kohei Watanabe, Yasuo Kuniyoshi, Masataka Yamaguchi, Kuniaki Saito, Yutaka Maruyama, Ayori Mitsutake, Ryo Igarashi and Atsushi Hashimoto and has published in prestigious journals such as SHILAP Revista de lepidopterología, IEEE Access and Frontiers in Psychology.

In The Last Decade

Yoshitaka Ushiku

47 papers receiving 1.2k citations

Hit Papers

align trajectories sort by overperformance

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes

2017 389 citations Kohei Watanabe, Takumi Karasawa et al. profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Yoshitaka Ushiku Japan	17	813	243	238	170	58	55	1.2k
Jiaxu Leng China	14	465 0.6×	177 0.7×	84 0.4×	149 0.9×	34 0.6×	62	743
Guanghai Liu China	23	1.8k 2.3×	205 0.8×	629 2.6×	115 0.7×	75 1.3×	99	2.4k
Zeyi Huang United States	10	522 0.6×	290 1.2×	114 0.5×	73 0.4×	57 1.0×	27	1.3k
Yen‐Cheng Liu Taiwan	15	648 0.8×	283 1.2×	141 0.6×	122 0.7×	20 0.3×	39	1.1k
Xuyu Xiang China	24	1.1k 1.4×	267 1.1×	149 0.6×	49 0.3×	83 1.4×	94	1.6k
Jiaohua Qin China	24	1.3k 1.6×	310 1.3×	169 0.7×	37 0.2×	97 1.7×	103	1.8k
Mansour Jamzad Iran	19	908 1.1×	183 0.8×	244 1.0×	67 0.4×	47 0.8×	104	1.2k
Muhammad Uzair Pakistan	19	448 0.6×	233 1.0×	227 1.0×	59 0.3×	108 1.9×	54	1.0k
Ni Zhang China	13	495 0.6×	171 0.7×	100 0.4×	121 0.7×	28 0.5×	55	986

Countries citing papers authored by Yoshitaka Ushiku

Since Specialization

Citations

This map shows the geographic impact of Yoshitaka Ushiku's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Yoshitaka Ushiku with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Yoshitaka Ushiku more than expected).

Fields of papers citing papers by Yoshitaka Ushiku

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Yoshitaka Ushiku. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Yoshitaka Ushiku. The network helps show where Yoshitaka Ushiku may publish in the future.

Co-authorship network of co-authors of Yoshitaka Ushiku

This figure shows the co-authorship network connecting the top 25 collaborators of Yoshitaka Ushiku. A scholar is included among the top collaborators of Yoshitaka Ushiku based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Yoshitaka Ushiku. Yoshitaka Ushiku is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

Hatakeyama‐Sato, Kan, Toshihiko Nishida, Koji Kitamura, et al.. (2025). Perspective on utilizing foundation models for laboratory automation in materials research. SHILAP Revista de lepidopterología. 5(1).

Yoshida, Shigeo, et al.. (2025). VisDev: A Stroke Deviation Visualization System Using Point-Set Registration for Handwriting Training. 1–7.

Ito, Yoshiro, Tatsunori Taniai, Ryo Igarashi, Yoshitaka Ushiku, & Kanta Ono. (2025). CrystalFramer: Rethinking the Role of Frames for SE(3)-Invariant Crystal Structure Modeling. ArXiv.org. 1 indexed citations

Shirai, Keisuke, Masashi Hamaya, Atsushi Hashimoto, et al.. (2024). Vision-Language Interpreter for Robot Task Planning. 2051–2058. 10 indexed citations

Yoshida, Shigeo, et al.. (2024). Toward AI-Mediated Avatar-Based Telecommunication: Investigating Visual Impression of Switching Between User- and AI-Controlled Avatars in Video Chat. IEEE Access. 12. 113372–113383. 2 indexed citations

Ushiku, Yoshitaka, et al.. (2024). Unsupervised Domain Adaptation for Human and Animal Chest X-Ray Bone Suppression. 1–5.

Suzuki, Yuta, Tatsunori Taniai, Ryo Igarashi, et al.. (2023). Neural structure fields with application to crystal structure autoencoders. Communications Materials. 4(1). 2 indexed citations

Ushiku, Yoshitaka, et al.. (2022). Edge Computing-Assisted DNN Image Recognition System With Progressive Image Retransmission. IEEE Access. 10. 91253–91262. 5 indexed citations

Yu, Qing, Atsushi Hashimoto, & Yoshitaka Ushiku. (2021). Divergence Optimization for Noisy Universal Domain Adaptation. 2515–2524. 18 indexed citations

10.

Hashimoto, Atsushi, et al.. (2020). Visual Grounding Annotation of Recipe Flow Graph. Language Resources and Evaluation. 4275–4284. 5 indexed citations

11.

Hashimoto, Atsushi, et al.. (2020). Structure-Aware Procedural Text Generation From an Image Sequence. IEEE Access. 9. 2125–2141. 12 indexed citations

12.

Yonetani, Ryo, Tomohiro Takahashi, Atsushi Hashimoto, & Yoshitaka Ushiku. (2019). Decentralized Learning of Generative Adversarial Networks from Multi-Client Non-iid Data.. arXiv (Cornell University). 7 indexed citations

13.

Tanaka, M., et al.. (2019). Generating Easy-to-Understand Referring Expressions for Target Identifications. 5793–5802. 11 indexed citations

14.

Ushiku, Yoshitaka, et al.. (2018). Learning from Between-class Examples for Deep Sound Recognition. arXiv (Cornell University). 38 indexed citations

15.

Ushiku, Yoshitaka, et al.. (2017). WebDNN. 1213–1216. 16 indexed citations

16.

Watanabe, Kohei, et al.. (2017). MFNet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. 5108–5115. 389 indexed citations breakdown →

17.

Yamaguchi, Masataka, Kuniaki Saito, Yoshitaka Ushiku, & Tatsuya Harada. (2017). Spatio-Temporal Person Retrieval via Natural Language Queries. 1462–1471. 45 indexed citations

18.

Ushiku, Yoshitaka, et al.. (2015). Common Subspace for Model and Similarity: Phrase Learning for Caption Generation from Images. 2668–2676. 44 indexed citations

19.

Ushiku, Yoshitaka, et al.. (2012). ISI at ImageCLEF 2012: Scalable System for Image Annotation.. 6 indexed citations

20.

Ushiku, Yoshitaka, Tatsuya Harada, & Yasuo Kuniyoshi. (2011). Understanding images with natural sentences. 679–682. 6 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact