Emotion classification has wide applications in education, robotics, virtual reality, etc.However, identifying subtle differences between fine-grained emotion categories remains challenging.Current methods typically aggregate numerous token embeddings of a sentence into a single vector, which, while being an efficient compressor, may not fully capture their complex semantic and temporal distributions.To solve this problem, we propose SEmantic ANchor Graph Neural Networks (SEAN-GNN) for fine-grained emotion classification.It learns a group of representative, multi-faceted semantic anchors in the token embedding space: using these anchors as global reference, any sentence can be projected onto them to form a "semantic-anchor graph", with node attributes and edge weights quantifying semantic and temporal information, respectively.The graph structure is well aligned across sentences and, importantly, allows for generating comprehensive emotion representations regarding K different anchors.Message passing on the anchor graph can further integrate the semantic and temporal information and refine the learned features.Empirically, SEAN-GNN produces meaningful semantic anchors and discriminative graph patterns, with promising classification results on 6 popular benchmark datasets against state-of-the-arts.

Contrastive learning is a powerful paradigm for representation learning with prominent success in computer vision and NLP, but how to extend its success to high-dimensional tensors remains a challenge. This is because tensor data often exhibit high-order mode-interactions that are hard to profile and with negative samples growing combinatorially faster than second-order contrastive learning; furthermore, many real-world tensors have ordinal entries that necessitate more delicate comparative levels. To solve the challenge, we propose High-Order Contrastive Tensor Completion (HOCTC), an innovative network to extend contrastive learning to sparse ordinal tensor data. HOCTC employs a novel attention-based strategy with query-expansion to capture high-order mode interactions even in case of very limited tokens, which transcends beyond second-order learning scenarios. Besides, it extends two-level comparisons (positive-vs-negative) to fine-grained contrast-levels using ordinal tensor entries as a natural guidance. Efficient sampling scheme is proposed to enforce such delicate comparative structures, generating comprehensive self-supervised signals for high-order representation learning. Extensive experiments show that HOCTC has promising results in sparse tensor completion in traffic/recommender applications.

Many complex social, biological, or physical systems are characterized as networks, and recovering the missing links of a network could shed important lights on its structure and dynamics. A good topological representation is crucial to accurate link modeling and prediction, yet how to account for the kaleidoscopic changes in link formation patterns remains a challenge, especially for analysis in cross-domain studies. We propose a new link representation scheme by projecting the local environment of a link into a "dipole plane", where neighboring nodes of the link are positioned via their relative proximity to the two anchors of the link, like a dipole. By doing this, complex and discrete topology arising from link formation is turned to differentiable point-cloud distribution, opening up new possibilities for topological feature-engineering with desired expressiveness, interpretability and generalization. Our approach has comparable or even superior results against state-of-the-art GNNs, meanwhile with a model up to hundreds of times smaller and running much faster. Furthermore, it provides a universal platform to systematically profile, study, and compare link-patterns from miscellaneous real-world networks. This allows building a global link-pattern atlas, based on which we have uncovered interesting common patterns of link formation, i.e., the bridge-style, the radiation-style, and the community-style across a wide collection of networks with highly different nature.

Scattered data fitting is always a challenging problem in the fields of geometric modeling and computer aided design. As the skeleton based three-dimensional solid model representation, the Ball B-Spline Curve is suitable to fit the tubular scattered data points. We study the problem of fitting the scattered data points with Ball B-spline curves (BBSCs) and propose the corresponding fitting algorithm based on the Particle Swarm Optimization (PSO) algorithm. In this process, we face three critical and difficult sub problems: (1) parameterization of the data points, (2) determination of the knot vector and (3) calculation of the control radii. All of them are multidimensional and nonlinear, especially the calculation of the parametric values. The parallelism of the PSO algorithm provides a high optimization, which is more suitable for solving nonlinear, nondifferentiable and multi-modal optimization problems. So we use it to solve the scattered data fitting problem. The PSO is applied in three steps to solve them. Firstly, we determine the parametric values of the data points with PSO. Then we compute the knot vector based on the parametric values of the data points. At last, we get the radius function. The experiments on the shell surface, the crescent surface and the real-world models verify the accuracy and flexibility of the method. The research can be widely used in the computer aided design, animation and model analysis.

The analysis of cerebrovascular shape is important for the diagnose and pathologic identification. But as the limitation of the segmentation algorithm, the complete cerebrovascular volume data are difficult to obtain. So the triangle mesh of the vessel model generated for the medical images may appear many gaps. In the paper, we present a extension algorithm for Ball B-Spline curve with G2 continuity to repair the cerebrovascular structure from time-of-flight (TOF) magnetic resonance angiography (MRA) data. Ball B-Spline curve has its distinct advantages in representing a 3D tube like organs. A ball Bezier segment is used to construct the extending part and G2-continuity is applied to describe the smoothness at the joints. Fairness of the extending ball Bezier curve segment is achieved by minimizing energy objective functions for the center curve and the radius function separately. New control balls are computed by unclamping algorithm to represent the whole extended ball B-Spline curve. The experimental results demonstrate the effectiveness of our algorithm. The final results show that the proposed method provides good blending result, especially for those blood vessels of small size.

Touch less interaction has received considerable attention in recent years with benefit of removing the burden of physical contact. To achieve mid-air interaction, several strategies are available. However, since most of these techniques directly map the 2D WIMP GUI to 3D user interface, they lead unnatural result. In this paper, interaction gestures and tools for exploring volume dataset are designed to perform the similar tasks in the real world. We mainly employ the idea of focus + context based on GPU volume ray casting by trapezoid-shaped transfer function when designing interaction tools. User studies are conducted to demonstrate the usability and intuitiveness of our method. The experimental results show a significant advantage in completion time after a short period of training.