Search Results for author:
Found 23 papers, 4 papers with code
Multi-model learning by sequential reading of untrimmed videos for action recognition
We propose a new method for learning videos by aggregating multiple models by sequentially extracting video clips from untrimmed video.
S3Aug: Segmentation, Sampling, and Shift for Action Recognition
Action recognition is a well-established area of research in computer vision.
Joint learning of images and videos with a single Vision Transformer
In this study, we propose a method for jointly learning of images and videos using a single model.
Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
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.
Performance Evaluation of Action Recognition Models on Low Quality Videos
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.
Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
In this paper, we propose a multi-domain learning model for action recognition.
ObjectMix: Data Augmentation by Copy-Pasting Objects in Videos for Action Recognition
In this paper, we propose a data augmentation method for action recognition using instance segmentation.
Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition
We also investigate other variants in which the proposed MSCA is used along the patch dimension of ViT, instead of the head dimension.
Improving the Reliability of Semantic Segmentation of Medical Images by Uncertainty Modeling with Bayesian Deep Networks and Curriculum Learning
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.
An Entropy Clustering Approach for Assessing Visual Question Difficulty
Then we use state-of-the-art methods to determine the accuracy and the entropy of the answer distributions for each cluster.
Rephrasing visual questions by specifying the entropy of the answer distribution
The proposed model rephrases a source question given with an image so that the rephrased question has the ambiguity (or entropy) specified by users.
On-line non-overlapping camera calibration net
First, successive images are fed to a PoseNet-based network to obtain ego-motion of cameras between frames.
Semantic segmentation of trajectories with improved agent models for pedestrian behavior analysis
In this paper, we propose a method for semantic segmentation of pedestrian trajectories based on pedestrian behavior models, or agents.
Meaning guided video captioning
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.
Improved Activity Forecasting for Generating Trajectories
An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting.
Biomedical Image Segmentation by Retina-like Sequential Attention Mechanism Using Only A Few Training Images
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.
Survey on Vision-based Path Prediction
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.
Semantic segmentation of trajectories with agent models
Next, using learned behavior models and a hidden Markov model, we segment a trajectory into semantic segments.
Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories
We propose a feature for action recognition called Trajectory-Set (TS), on top of the improved Dense Trajectory (iDT).
Development of a Real-time Colorectal Tumor Classification System for Narrow-band Imaging zoom-videoendoscopy
A computer-aided diagnosis (CAD) system that provides an objective measure to endoscopists during colorectal endoscopic examinations would be of great value.
Domain Adaptation with L2 constraints for classifying images from different endoscope systems
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.
Transfer Learning for Endoscopic Image Classification
In this paper we propose a method for transfer learning of endoscopic images.
Computer-Aided Colorectal Tumor Classification in NBI Endoscopy Using CNN Features
In this paper we report results for recognizing colorectal NBI endoscopic images by using features extracted from convolutional neural network (CNN).
