10 citations · 31 across the 8 of their papers we have counts for
8 papers
Joint learning of images and videos with a single Vision Transformer
Shuki Shimizu, Toru Tamaki
In this study, we propose a method for jointly learning of images and videos using a single model. In general, images and videos are often trained by separate models. We propose in…
Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Tomoya Nitta, Tsubasa Hirakawa, Hironobu Fujiyoshi +1
In this paper we propose an extension of the Attention Branch Network (ABN) by using instance segmentation for generating sharper attention maps for action recognition. Methods for…
Performance Evaluation of Action Recognition Models on Low Quality Videos
Aoi Otani, Ryota Hashiguchi, Kazuki Omi +2
In the design of action recognition models, the quality of videos is an important issue; however, the trade-off between the quality and performance is often ignored. In general, ac…
Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
Kazuki Omi, Jun Kimata, Toru Tamaki
In this paper, we propose a multi-domain learning model for action recognition. The proposed method inserts domain-specific adapters between layers of domain-independent layers of…
Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition
Ryota Hashiguchi, Toru Tamaki
Feature shifts have been shown to be useful for action recognition with CNN-based models since Temporal Shift Module (TSM) was proposed. It is based on frame-wise feature extractio…
Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning
Sora Iwamoto, Bisser Raytchev, Toru Tamaki +1
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 ar…
Rephrasing visual questions by specifying the entropy of the answer distribution
Kento Terao, Toru Tamaki, Bisser Raytchev +2
Visual question answering (VQA) is a task of answering a visual question that is a pair of question and image. Some visual questions are ambiguous and some are clear, and it may be…
Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features
Toru Tamaki, Shoji Sonoyama, Tsubasa Hirakawa +6
In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN). In this comparative study, we…