no code implementations • 26 Jan 2024 • Kodai Kamiya, Toru Tamaki
We propose a new method for learning videos by aggregating multiple models by sequentially extracting video clips from untrimmed video.
no code implementations • 23 Oct 2023 • Taiki Sugiura, Toru Tamaki
Action recognition is a well-established area of research in computer vision.
no code implementations • 21 Aug 2023 • Shuki Shimizu, Toru Tamaki
In this study, we propose a method for jointly learning of images and videos using a single model.
no code implementations • 27 Jul 2022 • Tomoya Nitta, Tsubasa Hirakawa, Hironobu Fujiyoshi, Toru Tamaki
Experimental results with UCF101 and SSv2 shows that the generated maps by the proposed method are much clearer qualitatively and quantitatively than those of the original ABN.
no code implementations • 19 Apr 2022 • Aoi Otani, Ryota Hashiguchi, Kazuki Omi, Norishige Fukushima, Toru Tamaki
In general, action recognition models are trained on high-quality videos, hence it is not known how the model performance degrades when tested on low-quality videos, and how much the quality of training videos affects the performance.
no code implementations • 15 Apr 2022 • Kazuki Omi, Jun Kimata, Toru Tamaki
In this paper, we propose a multi-domain learning model for action recognition.
no code implementations • 1 Apr 2022 • Ryota Hashiguchi, Toru Tamaki
We also investigate other variants in which the proposed MSCA is used along the patch dimension of ViT, instead of the head dimension.
no code implementations • 1 Apr 2022 • Jun Kimata, Tomoya Nitta, Toru Tamaki
In this paper, we propose a data augmentation method for action recognition using instance segmentation.
1 code implementation • 26 Aug 2021 • Sora Iwamoto, Bisser Raytchev, Toru Tamaki, Kazufumi Kaneda
In this paper we propose a novel method which leverages the uncertainty measures provided by Bayesian deep networks through curriculum learning so that the uncertainty estimates are fed back to the system to resample the training data more densely in areas where uncertainty is high.
1 code implementation • 12 Apr 2020 • Kento Terao, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Shun'ichi Satoh
Then we use state-of-the-art methods to determine the accuracy and the entropy of the answer distributions for each cluster.
no code implementations • 10 Apr 2020 • Kento Terao, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Shun'ichi Satoh
The proposed model rephrases a source question given with an image so that the rephrased question has the ambiguity (or entropy) specified by users.
no code implementations • 19 Feb 2020 • Zhao Fangda, Toru Tamaki, Takio Kurita, Bisser Raytchev, Kazufumi Kaneda
First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames.
no code implementations • 12 Dec 2019 • Daisuke Ogawa, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Ken Yoda
An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting.
no code implementations • 12 Dec 2019 • Toru Tamaki, Daisuke Ogawa, Bisser Raytchev, Kazufumi Kaneda
In this paper, we propose a method for semantic segmentation of pedestrian trajectories based on pedestrian behavior models, or agents.
1 code implementation • 12 Dec 2019 • Rushi J. Babariya, Toru Tamaki
Current video captioning approaches often suffer from problems of missing objects in the video to be described, while generating captions semantically similar with ground truth sentences.
no code implementations • 27 Sep 2019 • Shohei Hayashi, Bisser Raytchev, Toru Tamaki, Kazufumi Kaneda
In this paper we propose a novel deep learning-based algorithm for biomedical image segmentation which uses a sequential attention mechanism able to shift the focus of attention across the image in a selective way, allowing subareas which are more difficult to classify to be processed at increased resolution.
no code implementations • 1 Nov 2018 • Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki, Hironobu Fujiyoshi
Because path prediction as a task of computer vision uses video as input, various information used for prediction, such as the environment surrounding the target and the internal state of the target, need to be estimated from the video in addition to predicting paths.
no code implementations • 27 Feb 2018 • Daisuke Ogawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda
Next, using learned behavior models and a hidden Markov model, we segment a trajectory into semantic segments.
1 code implementation • 28 Nov 2017 • Kenji Matsui, Toru Tamaki, Gwladys Auffret, Bisser Raytchev, Kazufumi Kaneda
We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT).
no code implementations • 15 Dec 2016 • Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka
A computer-aided diagnosis (CAD) system that provides an objective measure to endoscopists during colorectal endoscopic examinations would be of great value.
no code implementations • 8 Nov 2016 • Toru Tamaki, Shoji Sonoyama, Takio Kurita, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka, Kazuaki Chayama
This paper proposes a method for domain adaptation that extends the maximum margin domain transfer (MMDT) proposed by Hoffman et al., by introducing L2 distance constraints between samples of different domains; thus, our method is denoted as MMDTL2.
no code implementations • 24 Aug 2016 • Shoji Sonoyama, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka
In this paper we propose a method for transfer learning of endoscopic images.
no code implementations • 24 Aug 2016 • Toru Tamaki, Shoji Sonoyama, Tsubasa Hirakawa, Bisser Raytchev, Kazufumi Kaneda, Tetsushi Koide, Shigeto Yoshida, Hiroshi Mieno, Shinji Tanaka
In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN).