Search

Designing stylized cinemagraphs is challenging due to the difficulty in customizing complex and expressive flow motions. To achieve intuitive and detailed control of the generated cinemagraphs, freehand sketches can provide a better solution to convey personalized design requirements than only text inputs. In this paper, we propose Sketch2Cinemagraph, a sketch-guided framework that enables the conditional generation of stylized cinemagraphs from freehand sketches. Sketch2Cinemagraph adopts text prompts for initial content generation and provides hand-drawn sketch controls for both spatial and motion cues. The latent diffusion model is adopted to generate target stylized landscape images along with realistic versions. Then, a pre-trained object detection model is utilized to segment and obtain masks for the flow regions. We proposed a novel latent motion diffusion model to estimate the motion field in the fluid regions of the generated landscape images. The input motion sketches serve as the conditions to control the generated vector fields in the masked fluid regions with the prompt. To synthesize the cinemagraph frames, the pixels within fluid regions are subsequently warped to the target locations for each timestep using a frame generator. The results verified that Sketch2Cinemagraph can generate high-fidelity and aesthetically appealing stylized cinemagraphs with continuous temporal flow from intuitive sketch inputs. We showcase the advantages of Sketch2Cinemagraph through quantitative comparisons against the state-of-the-art generation approaches., Comment: 14 pages, 20 figures

Bearing fault diagnosis technology has a wide range of practical applications in industrial production, energy and other fields. Timely and accurate detection of bearing faults plays an important role in preventing catastrophic accidents and ensuring product quality. Traditional signal analysis techniques and deep learning-based fault detection algorithms do not take into account the intricate correlation between signals, making it difficult to further improve detection accuracy. To address this problem, we introduced Graph Sampling and Aggregation (GraphSAGE) network and proposed GraphSAGE-based Bearing fault Diagnosis (GSABFD) algorithm. The original vibration signal is firstly sliced through a fixed size non-overlapping sliding window, and the sliced data is feature transformed using signal analysis methods; then correlations are constructed for the transformed vibration signal and further transformed into vertices in the graph; then the GraphSAGE network is used for training; finally the fault level of the object is calculated in the output layer of the network. The proposed algorithm is compared with five advanced algorithms in a real-world public dataset for experiments, and the results show that the GSABFD algorithm improves the AUC value by 5% compared with the next best algorithm.

Text-to-image models are showcasing the impressive ability to create high-quality and diverse generative images. Nevertheless, the transition from freehand sketches to complex scene images remains challenging using diffusion models. In this study, we propose a novel sketch-guided scene image generation framework, decomposing the task of scene image scene generation from sketch inputs into object-level cross-domain generation and scene-level image construction. We employ pre-trained diffusion models to convert each single object drawing into an image of the object, inferring additional details while maintaining the sparse sketch structure. In order to maintain the conceptual fidelity of the foreground during scene generation, we invert the visual features of object images into identity embeddings for scene generation. In scene-level image construction, we generate the latent representation of the scene image using the separated background prompts, and then blend the generated foreground objects according to the layout of the sketch input. To ensure the foreground objects' details remain unchanged while naturally composing the scene image, we infer the scene image on the blended latent representation using a global prompt that includes the trained identity tokens. Through qualitative and quantitative experiments, we demonstrate the ability of the proposed approach to generate scene images from hand-drawn sketches surpasses the state-of-the-art approaches., Comment: 12 pages, 8 figures

Recent advances in generative artificial intelligence (AI) technologies have been significantly driven by models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and denoising diffusion probabilistic models (DDPMs). Although architects recognize the potential of generative AI in design, personal barriers often restrict their access to the latest technological developments, thereby causing the application of generative AI in architectural design to lag behind. Therefore, it is essential to comprehend the principles and advancements of generative AI models and analyze their relevance in architecture applications. This paper first provides an overview of generative AI technologies, with a focus on probabilistic diffusion models (DDPMs), 3D generative models, and foundation models, highlighting their recent developments and main application scenarios. Then, the paper explains how the abovementioned models could be utilized in architecture. We subdivide the architectural design process into six steps and review related research projects in each step from 2020 to the present. Lastly, this paper discusses potential future directions for applying generative AI in the architectural design steps. This research can help architects quickly understand the development and latest progress of generative AI and contribute to the further development of intelligent architecture., Comment: 34 pages, 14 figures, accepted by Frontiers of Architectural Research

In this paper, we study asymptotic expansions of positive solutions of the conformal scalar curvature equation $$ - \Delta u = K(x) u^\frac{n + 2}{n - 2} ~~~~~~ \textmd{in} ~ B_1 \setminus \{ 0 \} $$ with an isolated singularity at the origin. Under certain flatness conditions on $K$, we establish a higher-order expansion of solutions near the origin. In particular, we give the refined second-order asymptotic expansion of solutions when $n \geq 6$. Moreover, we also obtain an arbitrary-order expansion of singular positive solutions of the anisotropic elliptic equation $$ - \,{\rm div} (|x|^{- 2 a} \nabla u) = |x|^{- b p} u^{p - 1} ~~~~~~ \textmd{in} ~ B_1 \setminus \{ 0 \}, $$ where $0 \leq a < \frac{n - 2}{2}$, $a \leq b < a + 1$ and $p = \frac{2 n}{n - 2 + 2 (b - a)}$. This equation is arising from the celebrated Caffarelli-Kohn-Nirenberg inequality., Comment: 40 pages

Online learning and academic conferences have become pervasive and essential for education and professional development, especially since the onset of pandemics. Academic presentations usually require well-designed slides that are easily understood. Sketches that visually represent design intentions and are readily accessible to the average users. To assist non-expert users in creating visually appealing academic slides, we propose DualSlide, a global and local two-stage sketching interface system that provides image retrieval and user guidance. At the global stage, DualSlide provides a heat map canvas to display the distribution of all slide layouts in a dataset, allowing users to explore the reference slides efficiently. At the local stage of the system, detailed references and guidance for designing slide content, such as diagrams and fonts, can be provided. We further propose a sketch-matching algorithm to compare the user's input sketch and similar diagrams. All user guidance can be adapted in real-time editing, and users can design slides with a high degree of freedom. We conducted a user study to verify the effectiveness and usability of the proposed DualSlide system confirming that DualSlide provides high retrieval accuracy and satisfactory design results with a good user experience. Video: https://youtu.be/lUI1zjxCdM0, Comment: 8 pages, 16 figures. accepted in NICOGRAPH International 2023

In this paper, we study existence of solutions to a conformally invariant integral equation involving Poisson-type kernels. Such integral equation has a stronger non-local feature and is not the dual of any PDE. We obtain the existence of solutions in the antipodal symmetry class.

Scene understanding is an essential and challenging task in computer vision. To provide the visually fundamental graphical structure of an image, the scene graph has received increased attention due to its powerful semantic representation. However, it is difficult to draw a proper scene graph for image retrieval, image generation, and multi-modal applications. The conventional scene graph annotation interface is not easy to use in image annotations, and the automatic scene graph generation approaches using deep neural networks are prone to generate redundant content while disregarding details. In this work, we propose SGDraw, a scene graph drawing interface using object-oriented scene graph representation to help users draw and edit scene graphs interactively. For the proposed object-oriented representation, we consider the objects, attributes, and relationships of objects as a structural unit. SGDraw provides a web-based scene graph annotation and generation tool for scene understanding applications. To verify the effectiveness of the proposed interface, we conducted a comparison study with the conventional tool and the user experience study. The results show that SGDraw can help generate scene graphs with richer details and describe the images more accurately than traditional bounding box annotations. We believe the proposed SGDraw can be useful in various vision tasks, such as image retrieval and generation., Comment: 16 pages, 9 figures, video is https://youtu.be/acy0SNLfahg, accepted in HCI International 2023

With the rapid growth in the number of devices of the Internet of Things (IoT), the volume and types of stream data are rapidly increasing in the real world. Unfortunately, the stream data has the characteristics of infinite and periodic volatility in the real world, which cause problems with the inefficient stream processing tasks. In this study, we report our recent efforts on this issue, with a focus on simulating stream data. Firstly, we explore the characteristics of the real-world stream data of the IoT, which helps us to understand the stream data in the real world. Secondly, the pipeline of simulating stream data is proposed, which can accurately and efficiently simulate the characteristics of the stream data to improve efficiency for specific tasks. Finally, we design and implement a novel framework that can simulate various stream data for related stream processing tasks. To verify the validity of the proposed framework, we apply this framework to stream processing task running in the stream processing system. The experimental results reveal that the related stream processing task is accelerated by at least 24 times using our proposed simulation framework with the premise of ensuring volatility and trends of stream data., Comment: 11 pages, 7 figures

Early detection of faults is of importance to avoid catastrophic accidents and ensure safe operation of machinery. A novel graph neural network-based fault detection method is proposed to build a bridge between AI and real-world running mechanical systems. First, the vibration signals, which are Euclidean structured data, are converted into graph (non-Euclidean structured data), so that the vibration signals, which are originally independent of each other, are correlated with each other. Second, inputs the dataset together with its corresponding graph into the GNN for training, which contains graphs in each hidden layer of the network, enabling the graph neural network to learn the feature values of itself and its neighbors, and the obtained early features have stronger discriminability. Finally, determines the top-n objects that are difficult to reconstruct in the output layer of the GNN as fault objects. A public datasets of bearings have been used to verify the effectiveness of the proposed method. We find that the proposed method can successfully detect faulty objects that are mixed in the normal object region., Comment: 8 pages, 7 figures

Outlier detection is an important topic in machine learning and has been used in a wide range of applications. Outliers are objects that are few in number and deviate from the majority of objects. As a result of these two properties, we show that outliers are susceptible to a mechanism called fluctuation. This article proposes a method called fluctuation-based outlier detection (FBOD) that achieves a low linear time complexity and detects outliers purely based on the concept of fluctuation without employing any distance, density or isolation measure. Fundamentally different from all existing methods. FBOD first converts the Euclidean structure datasets into graphs by using random links, then propagates the feature value according to the connection of the graph. Finally, by comparing the difference between the fluctuation of an object and its neighbors, FBOD determines the object with a larger difference as an outlier. The results of experiments comparing FBOD with seven state-of-the-art algorithms on eight real-world tabular datasets and three video datasets show that FBOD outperforms its competitors in the majority of cases and that FBOD has only 5% of the execution time of the fastest algorithm. The experiment codes are available at: https://github.com/FluctuationOD/Fluctuation-based-Outlier-Detection., Comment: 20pages,11figures

3D modeling based on point clouds is an efficient way to reconstruct and create detailed 3D content. However, the geometric procedure may lose accuracy due to high redundancy and the absence of an explicit structure. In this work, we propose a human-in-the-loop sketch-based point cloud reconstruction framework to leverage users cognitive abilities in geometry extraction. We present an interactive drawing interface for 3D model creation from point cloud data with the help of user sketches. We adopt an optimization method in which the user can continuously edit the contours extracted from the obtained 3D model and retrieve the model iteratively. Finally, we verify the proposed user interface for modeling from sparse point clouds. see video here https://www.youtube.com/watch?v=0H19NyXDRJE ., Comment: 6 pages, 5 figures, accepted in Proceedings of International Workshop on Advanced Image Technology 2022

We show a convergence result of the fractional Laplacian for sequences of nonnegative functions without uniform boundedness near infinity. As an application, we construct a sequence of solutions to the fractional Nirenberg problem that blows up in the region where the prescribed functions are negative. This is a different phenomenon from the classical Nirenberg problem., Comment: 10 pages

We study positive solutions to the fractional semi-linear elliptic equation $$ (- \Delta)^\sigma u = K(x) u^\frac{n + 2 \sigma}{n - 2 \sigma} ~~~~~~ in ~ B_2 \setminus \{ 0 \} $$ with an isolated singularity at the origin, where $K$ is a positive function on $B_2$, the punctured ball $B_2 \setminus \{ 0 \} \subset \mathbb{R}^n$ with $n \geq 2$, $\sigma \in (0, 1)$, and $(- \Delta)^\sigma$ is the fractional Laplacian. In lower dimensions, we show that, for any $K \in C^1 (B_2)$, a positive solution $u$ always satisfies that $u(x) \leq C |x|^{ - (n - 2 \sigma)/2 }$ near the origin. In contrast, we construct positive functions $K \in C^1 (B_2)$ in higher dimensions such that a positive solution $u$ could be arbitrarily large near the origin. In particular, these results also apply to the prescribed boundary mean curvature equations on $\mathbb{B}^{n+1}$., Comment: 34 pages. Fixed some typos. arXiv admin note: text overlap with arXiv:2009.02069

In this paper, we study the existence of positive functions $K \in C^1(\mathbb{S}^n)$ such that the conformal $Q$-curvature equation \begin{equation}\label{001} P_m (v) =K v^{\frac{n+2m}{n-2m}}~~~~~~ {on} ~ \mathbb{S}^n \{equation} has a singular positive solution $v$ whose singular set is a single point, where $m$ is an integer satisfying $1 \leq m < n/2$ and $P_m$ is the intertwining operator of order $2m$. More specifically, we show that when $n\geq 2m+4$, every positive function in $C^1(\mathbb{S}^n)$ can be approximated in the $C^1(\mathbb{S}^n)$ norm by a positive function $K\in C^1(\mathbb{S}^n)$ such that the conformal $Q$-curvature equation has a singular positive solution whose singular set is a single point. Moreover, such a solution can be constructed to be arbitrarily large near its singularity. This is in contrast to the well-known results of Lin \cite{Lin1998} and Wei-Xu \cite{Wei1999} which show that the conformal $Q$-curvature equation, with $K$ identically a positive constant on $\mathbb{S}^n$, $n > 2m$, does not exist a singular positive solution whose singular set is a single point., Comment: 24 pages; fixed some typos

We study some properties of positive solutions to the higher order conformally invariant equation with a singular set $$ (-\Delta)^m u = u^{\frac{n+2m}{n-2m}} ~~~~~~ \textmd{in} ~ \Omega \backslash \Lambda, $$ where $\Omega \subset \mathbb{R}^n$ is an open domain, $\Lambda$ is a closed subset of $\mathbb{R}^n$, $1 \leq m < n/2$ and $m$ is an integer. We first establish an asymptotic blow up rate estimate for positive solutions near the singular set $\Lambda$ when $\Lambda \subset \Omega$ is a compact set with the upper Minkowski dimension $\overline{\textmd{dim}}_M(\Lambda) < \frac{n-2m}{2}$, or is a smooth $k$-dimensional closed manifold with $k\leq \frac{n-2m}{2}$. We also show the asymptotic symmetry of singular positive solutions suppose $\Lambda \subset \Omega$ is a smooth $k$-dimensional closed manifold with $k\leq \frac{n-2m}{2}$. Finally, a global symmetry result for solutions is obtained when $\Omega$ is the whole space and $\Lambda$ is a $k$-dimensional hyperplane with $k\leq \frac{n-2m}{2}$., Comment: 34 pages