32 citations · 52 across the 13 of their papers we have counts for
13 papers · 1 filter
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition
Jun Kimata, Tomoya Nitta, Toru Tamaki
In this paper, we propose a data augmentation method for action recognition using instance segmentation. Although many data augmentation methods have been proposed for image recogn…
An Entropy Clustering Approach for Assessing Visual Question Difficulty
Kento Terao, Toru Tamaki, Bisser Raytchev +2
We propose a novel approach to identify the difficulty of visual questions for Visual Question Answering (VQA) without direct supervision or annotations to the difficulty. Prior wo…
On-line non-overlapping camera calibration net
Zhao Fangda, Toru Tamaki, Takio Kurita +2
We propose an easy-to-use non-overlapping camera calibration method. First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames. Nex…
Meaning guided video captioning
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 sen…
Improved Activity Forecasting for Generating Trajectories
Daisuke Ogawa, Toru Tamaki, Tsubasa Hirakawa +3
An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting. We modify reward function with norm and propose c…
Semantic segmentation of trajectories with improved agent models for pedestrian behavior analysis
Toru Tamaki, Daisuke Ogawa, Bisser Raytchev +1
In this paper, we propose a method for semantic segmentation of pedestrian trajectories based on pedestrian behavior models, or agents. The agents model the dynamics of pedestrian…
Biomedical Image Segmentation by Retina-like Sequential Attention Mechanism Using Only A Few Training Images
Shohei Hayashi, Bisser Raytchev, Toru Tamaki +1
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 ac…
Survey on Vision-based Path Prediction
Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki +1
Path prediction is a fundamental task for estimating how pedestrians or vehicles are going to move in a scene. Because path prediction as a task of computer vision uses video as in…
Semantic segmentation of trajectories with agent models
Daisuke Ogawa, Toru Tamaki, Bisser Raytchev +1
In many cases, such as trajectories clustering and classification, we often divide a trajectory into segments as preprocessing. In this paper, we propose a trajectory semantic segm…
Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
Kenji Matsui, Toru Tamaki, Gwladys Auffret +2
We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT). The TS feature encodes only trajectories around densely sampl…
Development of a Real-time Colorectal Tumor Classification System for Narrow-band Imaging zoom-videoendoscopy
Tsubasa Hirakawa, Toru Tamaki, Bisser Raytchev +5
Colorectal endoscopy is important for the early detection and treatment of colorectal cancer and is used worldwide. A computer-aided diagnosis (CAD) system that provides an objecti…
Domain Adaptation with L2 constraints for classifying images from different endoscope systems
Toru Tamaki, Shoji Sonoyama, Takio Kurita +8
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…
Transfer Learning for Endoscopic Image Classification
Shoji Sonoyama, Toru Tamaki, Tsubasa Hirakawa +6
In this paper we propose a method for transfer learning of endoscopic images. For transferring between features obtained from images taken by different (old and new) endoscopes, we…