no code implementations • 12 Apr 2024 • Kai Kohyama, Shintaro Shiba, Yoshimitsu Aoki
The experimental results show that the proposed method outperforms conventional frame-based methods in the estimation accuracy of both pose and body mesh.
no code implementations • 19 Mar 2024 • Haruya Ishikawa, Takumi Iida, Yoshinori Konishi, Yoshimitsu Aoki
In this work, we address these challenges by leveraging the abundance of unlabeled data available.
1 code implementation • 17 Mar 2024 • Yasufumi Kawano, Yoshimitsu Aoki
Unsupervised and open-vocabulary segmentation, proposed to tackle these issues, faces challenges, including the inability to assign specific class labels to clusters and the necessity of user-provided text queries for guidance.
1 code implementation • 17 Mar 2024 • Yasufumi Kawano, Yoshimitsu Aoki
Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning.
2 code implementations • 1 Nov 2023 • Shintaro Shiba, Friedhelm Hamann, Yoshimitsu Aoki, Guillermo Gallego
Schlieren imaging is an optical technique to observe the flow of transparent media, such as air or water, without any particle seeding.
1 code implementation • 19 Apr 2023 • Haruya Ishikawa, Yoshimitsu Aoki
Motivated by the recent development in improving semantic segmentation by incorporating boundaries as auxiliary tasks, we propose a multi-task framework that uses semantic boundary detection (SBD) as an auxiliary task.
1 code implementation • 16 Mar 2023 • Haruya Ishikawa, Yoshimitsu Aoki
With the increase in demands for service robots and automated inspection, agents need to localize in its surrounding environment to achieve more natural communication with humans by shared contexts.
no code implementations • CVPR 2023 • Yuto Shibata, Yutaka Kawashima, Mariko Isogawa, Go Irie, Akisato Kimura, Yoshimitsu Aoki
Aiming to capture subtle sound changes to reveal detailed pose information, we explicitly extract phase features from the acoustic signals together with typical spectrum features and feed them into our human pose estimation network.
no code implementations • 23 Dec 2022 • Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego
Event cameras are novel bio-inspired sensors that offer advantages over traditional cameras (low latency, high dynamic range, low power, etc.).
1 code implementation • 14 Dec 2022 • Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego
We hope our work opens the door for future applications that unlocks the advantages of event cameras.
1 code implementation • 2022 2022 • Yuhi Matsuo, Naofumi Akimoto, Yoshimitsu Aoki
In this paper, we present a large-scale and diverse dataset called fully synthetic document shadow removal dataset (FSDSRD) that does not require capturing documents.
1 code implementation • 20 Jul 2022 • Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego
Event cameras respond to scene dynamics and offer advantages to estimate motion.
1 code implementation • 8 Jul 2022 • Shintaro Shiba, Yoshimitsu Aoki, Guillermo Gallego
Contrast maximization (CMax) is a framework that provides state-of-the-art results on several event-based computer vision tasks, such as ego-motion or optical flow estimation.
1 code implementation • CVPR 2022 • Naofumi Akimoto, Yuhi Matsuo, Yoshimitsu Aoki
To improve the properties of a 360-degree image on an output image, we also propose WS-perceptual loss and circular inference.
2 code implementations • 14 Jul 2020 • Yuchi Ishikawa, Seito Kasai, Yoshimitsu Aoki, Hirokatsu Kataoka
Our model architecture consists of a long-term feature extractor and two branches: the Action Segmentation Branch (ASB) and the Boundary Regression Branch (BRB).
Ranked #10 on Action Segmentation on GTEA
1 code implementation • 19 May 2020 • Seito Kasai, Yuchi Ishikawa, Masaki Hayashi, Yoshimitsu Aoki, Kensho Hara, Hirokatsu Kataoka
In this paper, we present a framework that jointly retrieves and spatiotemporally highlights actions in videos by enhancing current deep cross-modal retrieval methods.
no code implementations • CVPR 2020 • Naofumi Akimoto, Huachun Zhu, Yanghua Jin, Yoshimitsu Aoki
We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions.
no code implementations • CVPR 2018 • Tomoyuki Suzuki, Hirokatsu Kataoka, Yoshimitsu Aoki, Yutaka Satoh
In this paper, we propose a novel approach for traffic accident anticipation through (i) Adaptive Loss for Early Anticipation (AdaLEA) and (ii) a large-scale self-annotated incident database for anticipation.
no code implementations • 1 May 2016 • Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic
Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities.
no code implementations • CVPR 2015 • Kiyoshi Matsuo, Yoshimitsu Aoki
Our method is composed of two steps, a calculation of the local tangents and surface reconstruction.