다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The PASCAL Visual Object Classes Challenge

A morphable model for the synthesis of 3D faces

This survey aims at providing multimedia researchers with a state-of-the-art overview of fusion strategies, which are used for combining multiple modalities in order to accomplish various multimedia analysis tasks. The existing literature on multimodal fusion research is presented through several classifications based on the fusion methodology and the level of fusion (feature, decision, and hybrid). The fusion methods are described from the perspective of the basic concept, advantages, weaknesses, and their usage in various analysis tasks as reported in the literature. Moreover, several distinctive issues that influence a multimodal fusion process such as, the use of correlation and independence, confidence level, contextual information, synchronization between different modalities, and the optimal modality selection are also highlighted. Finally, we present the open issues for further research in the area of multimodal fusion.

/pdf/multimodal-fusion-for-multimedia-analysis-a-survey-5f9wxprbby.pdf

Multimodal fusion for multimedia analysis: a survey

Intuitively, integrating information from multiple visual cues, such as texture, stereo disparity, and image motion, should improve performance on perceptual tasks, such as object detection. On the other hand, the additional effort required to extract and represent information from additional cues may increase computational complexity. In this work, we show that using biologically inspired integrated representation of texture and stereo disparity information for a multi-view facial detection task leads to not only improved detection performance, but also reduced computational complexity. Disparity information enables us to filter out 90% of image locations as being less likely to contain faces. Performance is improved because the filtering rejects 32% of the false detections made by a similar monocular detector at the same recall rate. Despite the additional computation required to compute disparity information, our binocular detector takes only 42ms to process a pair of 640x480 images, 35% of the time required by the monocular detector. We also show that this integrated detector is computationally more efficient than a detector with similar performance where texture and stereo information is processed separately.

Combining texture and stereo disparity cues for real-time face detection

Engagement is a key factor in gaming. Especially, in gamification applications, users’ engagement levels have to be assessed in order to determine the usability of the developed games. The authors first present computer vision-based game design for physical exercise. All games are played with gesture controls. The authors conduct user studies in order to evaluate the perception of the games using a game engagement questionnaire. Participants state that the games are interesting and they want to play them again. Next, as a use case, the authors integrate one of these games into a robot-assisted rehabilitation system. The authors perform additional user studies by employing self-assessment manikin to assess the difficulty levels that can range from boredom to excitement. The authors observe that with the increasing difficulty level, users’ arousal increases. Additionally, the authors perform psychophysiological signal analysis of the participants during the execution of the game under two distinctive difficulty levels. The authors derive features from the signals obtained from blood volume pulse (BVP), skin conductance, and skin temperature sensors. As a result of analysis of variance and sequential forward selection, the authors find that changes in the temperature and frequency content of BVP provide useful information to estimate the players’ engagement.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-cvi.2017.0122

Vision-based game design and assessment for physical exercise in a robot-assisted rehabilitation system

In this work, we exploit the regression trees-based ranking model, which has been successfully applied in the domain of web-search ranking, to build appearance models for face alignment. The model is an ensemble of regression trees which is learned with gradient boosting. The MCT (Modified Census Transform) as well as its unbinarized version PCT (Pseudo Census Transform) are used as features due to their robustness to illumination changes. To avoid the overfitting problem in gradient boosting, we use random trees to initialize the boosting. The Nelder Mead’s simplex method is applied for fitting the learned model. We compare the proposed regression trees-based pointwise ranking model to pairwise ranking model. Experiments show that the proposed model improves both robustness and accuracy for face alignment.

http://www.quaero.org/media/files/bibliographie/gao_face_alignment_bmvc2012.pdf

Face Alignment Using a Ranking Model based on Regression Trees.

Employee training in fast-food restaurants is a long, practice-based process, which is mainly done on the job. Employee performance during training directly affects service quality and customer satisfaction. In this study, we optimize the training process in fast-food restaurants with the use of augmented reality glasses. We increase the quality of the training by gamifying and personalizing the process. We also aim to help businesses lower the labor costs by shortening or possibly fully eliminating one-on-one training sessions instructed by senior employees. We implemented a new training system on a game engine with the aid of various sensors such as gyroscope, accelerometer and audial & visual inputs. We also intend to eliminate the culture of high employee turnover rates of the fast-food sector by increasing the quality of the training. The outcome of this study will be used to fully train and supervise employees in the future.

Personalized Training in Fast-Food Restaurants Using Augmented Reality Glasses

In this paper, we present a person identification system for vehicular environments. The proposed system uses face images of the driver and utilizes local appearance-based face recognition over the video sequence. To perform local appearance-based face recognition, the input face image is decomposed into non-overlapping blocks and on each local block discrete cosine transform is applied to extract the local features. The extracted local features are then combined to construct the overall feature vector. This process is repeated for each video frame. The distribution of the feature vectors over the video are modelled using a Gaussian distribution function at the training stage. During testing, the feature vector extracted from each frame is compared to each person’s distribution, and individual likelihood scores are generated. Finally, the person is identified as the one who has maximum joint-likelihood score. To assess the performance of the developed system, extensive experiments are conducted on different identification scenarios, such as closed set identification, open set identification and verification. For the experiments a subset of the CIAIR-HCC database, an in-vehicle data corpus that is collected at the Nagoya University, Japan is used. We show that, despite varying environment and illumination conditions, that commonly exist in vehicular environments, it is possible to identify individuals robustly from their face images.

/pdf/video-based-driver-identification-using-local-appearance-154cvdi28b.pdf

Hazim Kemal Ekenel

Papers

Combining texture and stereo disparity cues for real-time face detection

Vision-based game design and assessment for physical exercise in a robot-assisted rehabilitation system

Face Alignment Using a Ranking Model based on Regression Trees.

Personalized Training in Fast-Food Restaurants Using Augmented Reality Glasses

Video-based driver identification using local appearance face recognition