研究者詳細 - 出口　大輔

論文 - 出口　大輔

分割表示 253 件中 1 - 20 件目／全件表示 >>

Semantic matters: A constrained approach for zero-shot video action recognition 査読有り

Zhenzhen Quan, Jialei Chen, Daisuke Deguchi, Jie Sun, Chenkai Zhang, Yujun Li, Hiroshi Murase

Pattern Recognition 162 巻頁： 111402 2025年6月

A Cross-Modal Knowledge Distillation Approach for RGB-to-Infrared Video Action Recognition 査読有り

Zhenzhen Quan, Daisuke Deguchi, Jialei Chen, Chenkai Zhang, Yujun Li, Seigo Ito, Hiroshi Murase

Proceedings of Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2025) 2025年2月

Multi-group Vision Semantic Centroid for Semantic Segmentation 査読有り

Jialei Chen, Daisuke Deguchi, Chenkai Zhang, Zhenzhen Quan, Seigo Ito, Hiroshi Murase

Proceedings of Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2025) 2025年2月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Multi-media processing has achieved great success based on
semantic segmentation. Semantic segmentation can be viewed as pixel-
clustering based on semantic prototypes. However, existing methods fo-
cus more on consistent semantics while ignoring the consistency in vi-
sion, making this task challenging. Motivated by the success of discrete
visual representation learning, we propose Multi-group Visual Semantic
Centroid (MVSC) to better cluster the pixels while maintaining consis-
tent semantics of the dense features for any image encoder. Specifically,
we randomly initialize multiple groups of prototypes as multi-groups in
visual space. The visual features are also randomly split into the same
groups and forced to be aligned with the corresponding prototypes. Then
these visual prototypes are projected into the semantic space and super-
vised by the same classifier as the dense features. Compared with existing
methods, MVSC further considers the visual space and thus facilitates
the task. Experimental results on COCO-Stu! show great improvements
compared with previous methods.

CROCODILE: Crop-based Contrastive Discriminative Learning for Enhancing Explainability of End-to-End Driving Models 査読有り

Chenkai Zhang, Daisuke Deguchi, Jialei Chen, Zhenzhen Quan, Hiroshi Murase

Proceedings of ACCV Workshop on Machine Learning and Computing for Visual Semantic Analysis (MLCSA2024) 頁： 378 - 393 2024年12月

Early prediction of At-risk students through Learning-Activity Forecasting 査読有り

Yuya Ozaki, Daisuke Deguchi, Haruya Kyutoku, Hiroshi Murase

Proceedings of 32nd International Conference on Computers in Education (ICCE2024) 2024年11月

Toward Explainable End-to-End Driving Models via Simplified Objectification Constraints 査読有り

Chenkai Zhang, Daisuke Deguchi, Jialei Chen, Hiroshi Murase

IEEE Transactions on Intelligent Transportation Systems 25 巻 ( 10 ) 頁： 14521 - 14534 2024年10月

記述言語：英語掲載種別：研究論文（学術雑誌）

The end-to-end driving models (E2EDMs) convert environmental information into driving actions using a complex transformation which makes E2EDMs have high prediction accuracy. Due to the black-box nature of transformation, the E2EDMs have low explainability. To solve this problem, explanation methods are used to generate explanations for observation. Based on current explanation methods, previous studies tried to further improve the explainability of E2EDMs by integrating an object detection module, however, these methods have many problems: Firstly, due to the requirement of the object detection module, they lack flexibility. Secondly, they neglect an essential property, i.e. , simplicity, to improve explainability. In this paper, since humans prefer object-level and simple explanations in driving tasks, we argue that explainability is decided by two properties which are the objectification degree (the extent to which driving related-object features are utilized) and simplification degree (the simplicity of the explanation), thus we propose Simplified Objectification Branches (SOB) to improve the explainability of E2EDMs. Firstly, this structure could be integrated into any existing E2EDMs and thus have high flexibility. Secondly, the SOB explicitly improves the simplification degree without sacrificing the objectification degree of the explanations. By designing several indicators, i.e. , heatmap satisfaction, driving action reproduction score, deception level, etc. , we proved that SOB could help E2EDMs generate better explanations. Notably, the SOB could also further enhance E2EDMs’ prediction accuracy.

DOI： 10.1109/TITS.2024.3385754

Frozen is better than learning: A new design of prototype-based classifier for semantic segmentation 査読有り

Jialei Chen, Daisuke Deguchi, Chenkai Zhang, Xu Zheng, Hiroshi Murase

Pattern Recognition 152 巻 2024年8月

記述言語：英語掲載種別：研究論文（学術雑誌）

Semantic segmentation models comprise an encoder to extract features and a classifier for prediction. However, the learning of the classifier suffers from the ambiguity which is caused by two factors: (1) the weights of a classifier for similar categories may have positive similarities lowing the performance for similar categories, named correlation ambiguity, and (2) the classifier is prone to predict the category with a larger L2 norm and vice versa, termed prior ambiguity. To comedy the issues, we propose Category-Basis Prototype (CBP), frozen and mutually orthogonalized prototypes with equal L2 norm. Orthogonalization prevents the prototypes from being similar to each other and the equality decouples the prediction from the L2 norm. To better shape the feature space, we propose Online Centroid Contrastive Loss (OCCL) equipped with centroid and category- level losses. Experiments show that our method yields compelling results over two widely applied benchmarks indicating the effectiveness of our methods.

DOI： 10.1016/j.patcog.2024.110431

Eye-contact Transformer: シーンコンテクストを考慮した遠方歩行者のアイコンタクト検出

畑隆聖, 出口大輔, 平山高嗣, 川西康友, 村瀬洋

電子情報通信学会論文誌 J107-D 巻 ( 4 ) 頁： 231 - 242 2024年4月

記述言語：日本語掲載種別：研究論文（学術雑誌）

歩行者が自車に気づいているかどうかの判断は，安全に車両を運転する上でとても重要である．このような自車への気付きの判断において，歩行者とのアイコンタクトは重要な役割を担っている．従来，このようなアイコンタクト検出には眼球計測により得られる視線推定結果が広く用いられており，道路環境のように歩行者と車両の距離が遠く歩行者の眼球を高解像度に計測できない場合は適用できない．そこで本論文では，歩行者の骨格系列と周囲環境の特徴を統合利用することにより，複雑な交通環境であっても歩行者とのアイコンタクトを精度良く検出可能な手法を提案する．具体的には，歩行者の骨格系列と周囲環境の特徴間の関係性をTransformerベースのモデルで捉えるEye-contact Transformerを構築する．車載カメラ画像群に対してアイコンタクトのアノテーションを付与したデータセットを用いた実験により，提案手法の有効性を確認した．

DOI： 10.14923/transinfj.2023PDP0024

Centroid Module for Shaping Feature Space in Semantic Segmentation

Jialei Chen, Daisuke Deguchi, Chenkai Zhang, Hiroshi Murase

Proceedings of 3rd Asia Conference on Cloud Computing, Computer Vision and Image Processing (3CVIP 2024) 2024年3月

Subjective Baggage-Weight Estimation Based on Human Walking Behavior 査読有り

Masaya Mizuno, Tomohiro Fujita, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

IEEE Access 12 巻頁： 39390 - 39398 2024年3月

Category-Level Object Pose Estimation in Heavily Cluttered Scenes by Generalized Two-Stage Shape Reconstructor 査読有り

Hiroki Tatemichi, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase

IEEE Access 12 巻頁： 33440 - 33448 2024年3月

Comprehensive Evaluation of End-to-End Driving Model Explanations for Autonomous Vehicles 査読有り

Chenkai Zhang, Daisuke Deguchi, Jialei Chen, Hiroshi Murase

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) 2024 2 巻 ( 2184-4321 ) 頁： 509 - 518 2024年2月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

Deep learning technology has rapidly advanced, leading to the development of End-to-End driving models (E2EDMs) for autonomous vehicles with high prediction accuracy. To comprehend the prediction results of these E2EDMs, one of the most representative explanation methods is attribution-based. There are two kinds of attribution-based explanation methods: pixel-level and object-level. Usually, the heatmaps illustrate the importance of pixels and objects in the prediction results, serving as explanations for E2EDMs. Since there are many attribution-based explanation methods, evaluation methods are proposed to determine which one is better at improving the explainability of E2EDMs.
Fidelity measures the explanation's faithfulness to the model's prediction method, which is a bottommost property. However, no evaluation method could measure the fidelity difference between object-level and pixel-level explanations, making the current evaluation incomplete. In addition, without considering fidelity, previous evaluation methods may advertise manipulative explanations that solely seek human satisfaction (persuasibility). Therefore, we propose an evaluation method that further considers fidelity, our method enables a comprehensive evaluation that proves the object-level explanations genuinely outperform pixel-level explanations in fidelity and persuasibility, thus could better improve the explainability of the E2EDMs.

Pedestrian's Gaze Object Detection in Traffic Scene 査読有り

Hiroto Murakami, Jialei Chen, Daisuke Deguchi, Takatsugu Hirayama, Yasutomo Kawanishi, Hiroshi Murase

Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) 2024 2 巻頁： 333 - 340 2024年2月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In this paper, we present a new task of detecting an object that a target pedestrian is gazing at in a traffic scene called PEdestrian's Gaze Object (PEGO). We argue that the detection of gaze object can provide important information for pedestrian's behavior prediction and can contribute to the realization of automated vehicles. For this task, we construct a dataset of in-vehicle camera images with annotations of the objects that pedestrians are gazing at. Also, we propose a Transformer-based method called PEGO Transformer to solve the PEGO detection task. The PEGO Transformer directly performs gaze object detection with the utilization of whole-body features without a high-resolution head image and a gaze heatmap which the traditional methods rely on. Experimental results showed that the proposed method could estimate pedestrian's gaze object accurately even if various objects exist in the scene.

Texture-guided transfer learning for low-quality face recognition 査読有り

Meng Zhang, Rujie Liu, Daisuke Deguchi, Hiroshi Murase

IEEE Transactions on Image Processing 2023年11月

記述言語：英語掲載種別：研究論文（学術雑誌）

Although many advanced works have achieved significant progress for face recognition with deep learning and large-scale face datasets, low-quality face recognition remains a challenging problem in real-word applications, especially for unconstrained surveillance scenes. We propose a texture-guided (TG) transfer learning approach under the knowledge distillation scheme to improve low-quality face recognition performance. Unlike existing methods in which distillation loss is built on forward propagation; e.g., the output logits and intermediate features, in this study, the backward propagation gradient texture is used. More specifically, the gradient texture of low-quality images is forced to be aligned to that of its high-quality counterpart to reduce the feature discrepancy between the high-and low-quality images. Moreover, attention is introduced to derive a soft-attention (SA) version of transfer learning, termed as SA-TG, to focus on informative regions. Experiments on the benchmark low-quality face DB’s TinyFace and QMUL-SurFace confirmed the superiority of the proposed method, especially more than 6.3% Rank1 accuracy improvement is achieved on TinyFace.

DOI： 10.1109/TIP.2023.3335830

Computational measurement of perceived pointiness from pronunciation 査読有り

Chihaya Matsuhira, Marc A. Kastner, Takahiro Komamizu, Ichiro Ide, Takatsugu Hirayama, Yasutomo Kawanishi, Keisuke Doman, Daisuke Deguchi

Multimedia Tools and Applications 2023年8月

Refined Objectification for Improving End-to-End Driving Model Explanation Persuasibility 査読有り

Chenkai Zhang, Daisuke Deguchi, Hiroshi Murase

Proceedings of 2023 IEEE Intelligent Vehicles Symposium (IV2023) 2023年6月

観衆の顔向きの時空間統合による注目対象の位置及び被注目度の推定査読有り

武田一馬, 川西康友, 平山高嗣, 出口大輔, 井手一郎, 村瀬洋, 柏野邦夫

電子情報通信学会論文誌 J106-A 巻 ( 3 ) 頁： 58 - 69 2023年3月

End-to-End gaze grounding from a person pictured from behind 査読有り

Hayato Yumiya, Daisuke Deguchi, Yasutomo Kawanishi, Hiroshi Murase

Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications 5 巻頁： 898 - 905 2023年2月

Subjective Baggage-Weight Estimation from Gait: Can You Estimate How Heavy the Person Feels? 査読有り

Masaya Mizuno, Tomohiro Fujita, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP) 2023 5 巻頁： 567 - 574 2023年2月

A Preliminary Study on View Independent Panoptic Scene Change Detection 査読有り

Jiaxin Li, Yasutomo Kawanishi, Daisuke Deguchi, Hiroshi Murase

Proceedings of International Workshop on Advanced Image Technology (IWAIT) 2023 2023年1月

　前のページ - 次のページ　

<出口 大輔>

論文 - 出口 大輔

<出口　大輔>

論文 - 出口　大輔