Search

Emotion recognition can enhance humanized machine responses to user commands, while voiceprint-based perception systems can be easily integrated into commonly used devices like smartphones and stereos. Despite having the largest number of speakers, there is a noticeable absence of high-quality corpus datasets for emotion recognition using Chinese voiceprints. Hence, this paper introduces the VCEMO dataset to address this deficiency. The proposed dataset is constructed from everyday conversations and comprises over 100 users and 7,747 textual samples. Furthermore, this paper proposes a multimodal-based model as a benchmark, which effectively fuses speech, text, and external knowledge using a co-attention structure. The system employs contrastive learning-based regulation for the uneven distribution of the dataset and the diversity of emotional expressions. The experiments demonstrate the significant improvement of the proposed model over SOTA on the VCEMO and IEMOCAP datasets. Code and dataset will be released for research., Comment: 12 pages, 4 figures

Let $M$ be a complex manifold with boundary $X$, which admits a holomorphic Lie group $G$-action preserving $X$. We establish a full asymptotic expansion for the $G$-invariant Bergman kernel under certain assumptions. As an application, we get $G$-invariant version of Fefferman's result about regularity of biholomorphic maps on strongly pseudoconvex domains of $\mathbb C^n$. Moreover, we show that the Guillemin-Sternberg map on a complex manifold with boundary is Fredholm by developing reduction to boundary technique, which establish ``quantization commutes with reduction" in this case., Comment: 36 pages

Let $M$ be a relatively compact connected open subset with smooth connected boundary of a complex manifold $M'$. Let $(L,h^L)\rightarrow M'$ be a positive line bundle over $M'$. Suppose that $M'$ admits a holomorphic $\mathbb{R}$-action which preserves the boundary of $M$ and lifts to $L$. We establish the asymptotic expansion of a partial Bergman kernel associated to a package of Fourier modes of high frequency with respect to the $\mathbb{R}$-action in the high powers of $L$. As an application, we establish an $\mathbb{R}$-equivariant analogue of Fefferman's and Bell-Ligocka's result about smooth extension up to the boundary of biholomorphic maps between weakly pseudoconvex domains in $\mathbb{C}^n$. Another application concerns the embedding of pseudoconcave manifolds., Comment: 55 pages; revised version, new results about smooth extension up to the boundary of biholomorphic maps between weakly pseudoconvex domains with $\mathbb{R}$-action in $\mathbb{C}^n$ added

We give simple and unified proofs of weak holomorhpic Morse inequalities on complete manifolds, $q$-convex manifolds, pseudoconvex domains, weakly $1$-complete manifolds and covering manifolds. This paper is essentially based on the asymptotic Bergman kernel functions and the Bochner-Kodaira-Nakano formulas.

In this work, we perform semantic segmentation of multiple defect types in electron microscopy images of irradiated FeCrAl alloys using a deep learning Mask Regional Convolutional Neural Network (Mask R-CNN) model. We conduct an in-depth analysis of key model performance statistics, with a focus on quantities such as predicted distributions of defect shapes, defect sizes, and defect areal densities relevant to informing modeling and understanding of irradiated Fe-based materials properties. To better understand the performance and present limitations of the model, we provide examples of useful evaluation tests which include a suite of random splits, and dataset size-dependent and domain-targeted cross validation tests. Overall, we find that the current model is a fast, effective tool for automatically characterizing and quantifying multiple defect types in microscopy images, with a level of accuracy on par with human domain expert labelers. More specifically, the model can achieve average defect identification F1 scores as high as 0.8, and, based on random cross validation, have low overall average (+/- standard deviation) defect size and density percentage errors of 7.3 (+/- 3.8)% and 12.7 (+/- 5.3)%, respectively. Further, our model predicts the expected material hardening to within 10-20 MPa (about 10% of total hardening), which is about the same error level as experiments. Our targeted evaluation tests also suggest the best path toward improving future models is not expanding existing databases with more labeled images but instead data additions that target weak points of the model domain, such as images from different microscopes, imaging conditions, irradiation environments, and alloy types. Finally, we discuss the first phase of an effort to provide an easy-to-use, open-source object detection tool to the broader community for identifying defects in new images.

Let $\Omega$ be a Stein space with a compact smooth strongly pseudoconvex boundary. We prove that the boundary is spherical if its Bergman metric over $\hbox{Reg}(\Omega)$ is K\"ahler-Einstein., Comment: 21 pages, comments are welcome

We study the stable embedding problem for a CR family of 3-dimensional strongly pseudoconvex CR manifolds with each fiber bounding a stein manifold., Comment: 14 pages, to appear in Journal of Geometric Analysis

Background: Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, excretion prediction models still have limited accuracy. Aim: This study aims to construct an integrated transfer learning and multitask learning approach for developing quantitative structure-activity relationship models to predict four human pharmacokinetic parameters. Methods: A pharmacokinetic dataset included 1104 U.S. FDA approved small molecule drugs. The dataset included four human pharmacokinetic parameter subsets (oral bioavailability, plasma protein binding rate, apparent volume of distribution at steady-state and elimination half-life). The pre-trained model was trained on over 30 million bioactivity data. An integrated transfer learning and multitask learning approach was established to enhance the model generalization. Results: The pharmacokinetic dataset was split into three parts (60:20:20) for training, validation and test by the improved Maximum Dissimilarity algorithm with the representative initial set selection algorithm and the weighted distance function. The multitask learning techniques enhanced the model predictive ability. The integrated transfer learning and multitask learning model demonstrated the best accuracies, because deep neural networks have the general feature extraction ability, transfer learning and multitask learning improved the model generalization. Conclusions: The integrated transfer learning and multitask learning approach with the improved dataset splitting algorithm was firstly introduced to predict the pharmacokinetic parameters. This method can be further employed in drug discovery and development.