28 citations · 101 across the 12 of their papers we have counts for
12 papers
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers
Yuya Yoshikawa, Tomoharu Iwata
The quality of explanations for the predictions made by complex machine learning predictors is often measured using insertion and deletion metrics, which assess the faithfulness of…
Action Class Relation Detection and Classification Across Multiple Video Datasets
Yuya Yoshikawa, Yutaro Shigeto, Masashi Shimbo +1
The Meta Video Dataset (MetaVD) provides annotated relations between action classes in major datasets for human action recognition in videos. Although these annotated relations ena…
Learning Decorrelated Representations Efficiently Using Fast Fourier Transform
Yutaro Shigeto, Masashi Shimbo, Yuya Yoshikawa +1
Barlow Twins and VICReg are self-supervised representation learning models that use regularizers to decorrelate features. Although these models are as effective as conventional rep…
Training Deep Models to be Explained with Fewer Examples
Tomoharu Iwata, Yuya Yoshikawa
Although deep models achieve high predictive performance, it is difficult for humans to understand the predictions they made. Explainability is important for real-world application…
Gaussian Process Regression with Local Explanation
Yuya Yoshikawa, Tomoharu Iwata
Gaussian process regression (GPR) is a fundamental model used in machine learning. Owing to its accurate prediction with uncertainty and versatility in handling various data struct…
Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretability
Yuya Yoshikawa, Tomoharu Iwata
For reliability, it is important that the predictions made by machine learning methods are interpretable by human. In general, deep neural networks (DNNs) can provide accurate pred…
Video Caption Dataset for Describing Human Actions in Japanese
Yutaro Shigeto, Yuya Yoshikawa, Jiaqing Lin +1
In recent years, automatic video caption generation has attracted considerable attention. This paper focuses on the generation of Japanese captions for describing human actions. Wh…
STAIR Actions: A Video Dataset of Everyday Home Actions
Yuya Yoshikawa, Jiaqing Lin, Akikazu Takeuchi
A new large-scale video dataset for human action recognition, called STAIR Actions is introduced. STAIR Actions contains 100 categories of action labels representing fine-grained e…
A Nonparametric Delayed Feedback Model for Conversion Rate Prediction
Yuya Yoshikawa, Yusaku Imai
Predicting conversion rates (CVRs) in display advertising (e.g., predicting the proportion of users who purchase an item (i.e., a conversion) after its corresponding ad is clicked)…
Learning from Noisy Label Distributions
Yuya Yoshikawa
In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector bel…
STAIR Captions: Constructing a Large-Scale Japanese Image Caption Dataset
Yuya Yoshikawa, Yutaro Shigeto, Akikazu Takeuchi
In recent years, automatic generation of image descriptions (captions), that is, image captioning, has attracted a great deal of attention. In this paper, we particularly consider…
Collaboration on Social Media: Analyzing Successful Projects on Social Coding
Yuya Yoshikawa, Tomoharu Iwata, Hiroshi Sawada
Social Coding Sites (SCSs) are social media services for sharing software development projects on the Web, and many open source projects are currently being developed on SCSs. One…