Yuki Saito

Orcid: 0000-0003-0492-414X

Affiliations:
  • ZOZO Research, Chiba City, Japan


According to our database1, Yuki Saito authored at least 15 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Transferring Visual Explainability of Self-Explaining Models through Task Arithmetic.
CoRR, July, 2025

Static Word Embeddings for Sentence Semantic Representation.
CoRR, June, 2025

Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation.
Proceedings of the ACM on Web Conference 2025, 2025

Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Set representative vector and its asymmetric attention-based transformation for heterogeneous set-to-set matching.
Neurocomputing, 2024

A Fashion Item Recommendation Model in Hyperbolic Space.
CoRR, 2024

Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property.
CoRR, 2024

On permutation-invariant neural networks.
CoRR, 2024

An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation.
Proceedings of the SIGGRAPH Asia 2024 Technical Communications, 2024

2023
Fashion intelligence system: An outfit interpretation utilizing images and rich abstract tags.
Expert Syst. Appl., 2023

Outfit Completion via Conditional Set Transformation.
CoRR, 2023

SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shifts.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2020
Exchangeable Deep Neural Networks for Set-to-Set Matching and Learning.
Proceedings of the Computer Vision - ECCV 2020, 2020

2019
Deep Set-to-Set Matching and Learning.
CoRR, 2019

2018
2.5D Faster R-CNN for Distance Estimation.
Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, 2018


  Loading...