Yu Zhou

Xiaoyi Liu, Hongjie Qiu, Muqing Li et al.

This paper introduces an innovative multi-modal fusion deep learning approach to overcome the drawbacks of traditional single-modal recognition techniques. These drawbacks include incomplete information and limited diagnostic accuracy. During the feature extraction stage, cutting-edge deep learning models including convolutional neural networks (CNN), recurrent neural networks (RNN), and transformers are applied to distill advanced features from image-based, temporal, and structured data sources. The fusion strategy component seeks to determine the optimal fusion mode tailored to the specific disease recognition task. In the experimental section, a comparison is made between the performance of the proposed multi-mode fusion model and existing single-mode recognition methods. The findings demonstrate significant advantages of the multimodal fusion model across multiple evaluation metrics.

Ryan Shea, Yunan Lu, Liang Qiu et al.

Evaluating multi-turn interactive agents is challenging due to the need for human assessment. Evaluation with simulated users has been introduced as an alternative, however existing approaches typically model generic users and overlook the domain-specific principles required to capture realistic behavior. We propose SAGE, a novel user Simulation framework for multi-turn AGent Evaluation that integrates knowledge from business contexts. SAGE incorporates top-down knowledge rooted in business logic, such as ideal customer profiles, grounding user behavior in realistic customer personas. We further integrate bottom-up knowledge taken from business agent infrastructure (e.g., product catalogs, FAQs, and knowledge bases), allowing the simulator to generate interactions that reflect users' information needs and expectations in a company's target market. Through empirical evaluation, we find that this approach produces interactions that are more realistic and diverse, while also identifying up to 33% more agent errors, highlighting its effectiveness as an evaluation tool to support bug-finding and iterative agent improvement.

Bo Li, Caiming Xiong, Tianfu Wu et al.

Chinese traditional painting is one of the most historical artworks in the world. It is very popular in Eastern and Southeast Asia due to being aesthetically appealing. Compared with western artistic painting, it is usually more visually abstract and textureless. Recently, neural network based style transfer methods have shown promising and appealing results which are mainly focused on western painting. It remains a challenging problem to preserve abstraction in neural style transfer. In this paper, we present a Neural Abstract Style Transfer method for Chinese traditional painting. It learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter (Modified version of the eXtended Difference-of-Gaussians) and three fully differentiable loss terms. To the best of our knowledge, there is little work study on neural style transfer of Chinese traditional painting. To promote research on this direction, we collect a new dataset with diverse photo-realistic images and Chinese traditional paintings. In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.

Yu Zhou

Cloud computing offers the potential to help scientists to process massive number of computing resources often required in machine learning application such as computer vision problems. This proposal would like to show that which benefits can be obtained from cloud in order to help medical image analysis users (including scientists, clinicians, and research institutes). As security and privacy of algorithms are important for most of algorithms inventors, these algorithms can be hidden in a cloud to allow the users to use the algorithms as a package without any access to see/change their inside. In another word, in the user part, users send their images to the cloud and configure the algorithm via an interface. In the cloud part, the algorithms are applied to this image and the results are returned back to the user. My proposal has two parts: (1) investigate the potential of cloud computing for computer vision problems and (2) study the components of a proposed cloud-based framework for medical image analysis application and develop them (depending on the length of the internship). The investigation part will involve a study on several aspects of the problem including security, usability (for medical end users of the service), appropriate programming abstractions for vision problems, scalability and resource requirements. In the second part of this proposal I am going to thoroughly study of the proposed framework components and their relations and develop them. The proposed cloud-based framework includes an integrated environment to enable scientists and clinicians to access to the previous and current medical image analysis algorithms using a handful user interface without any access to the algorithm codes and procedures.