Search

Sports highlights are becoming increasingly popular on video-sharing platforms. Yet, crafting sport highlight videos is challenging, which requires producing engaging narratives from different angles, and conforming to different platform affordances with constantly changing audiences. Many content creators therefore create derivative work of the original sports video through manga styles to enhance its expressiveness. But manually creating and inserting tailored manga-style content can still be time-consuming. We introduce Sportoonizer, a system embedding the pipeline for automatic generation of manga-style animations for highlights in sports videos and insertion into original videos. It seamlessly merges dynamic manga sequences with live-action footage, enriching the visual tapestry and deepening narrative scope. By leveraging genAIs, Sportoonizer crafts compelling storylines encapsulating the intensity of sports moments and athletes' personal journeys. Our evaluation study demonstrates that integrating manga B-rolls significantly enhances viewer engagement, visual interest, and emotional connection towards athletes' stories in the viewing experience.

With the development of generative AI technology, a vast array of AI-generated paintings (AIGP) have gone viral on social media like TikTok. However, some negative news about AIGP has also emerged. For example, in 2022, numerous painters worldwide organized a large-scale anti-AI movement because of the infringement in generative AI model training. This event reflected a social issue that, with the development and application of generative AI, public feedback and feelings towards it may have been overlooked. Therefore, to investigate public interactions and perceptions towards AIGP on social media, we analyzed user engagement level and comment sentiment scores of AIGP using human painting videos as a baseline. In analyzing user engagement, we also considered the possible moderating effect of the aesthetic quality of Paintings. Utilizing topic modeling, we identified seven reasons, including looks too real, looks too scary, ambivalence, etc., leading to negative public perceptions of AIGP. Our work may provide instructive suggestions for future generative AI technology development and avoid potential crises in human-AI collaboration., Comment: 13 pages

As the demand for computer science (CS) skills grows, mastering foundational concepts is crucial yet challenging for novice learners. To address this challenge, we present KoroT-3E, an AI-based system that creates personalized musical mnemonics to enhance both memory retention and understanding of concepts in CS. KoroT-3E enables users to transform complex concepts into memorable lyrics and compose melodies that suit their musical preferences. We conducted semi-structured interviews (n=12) to investigate why novice learners find it challenging to memorize and understand CS concepts. The findings, combined with constructivist learning theory, established our initial design, which was then refined following consultations with CS education experts. An empirical experiment(n=36) showed that those using KoroT-3E (n=18) significantly outperformed the control group (n=18), with improved memory efficiency, increased motivation, and a positive learning experience. These findings demonstrate the effectiveness of integrating multimodal generative AI into CS education to create personalized and interactive learning experiences., Comment: 26 pages , 2 tables,7 figures, undereview

In this paper, we introduce a novel first-order derivative for functions on a lattice graph, which extends the discrete Laplacian and generalizes the theory of discrete PDEs on the lattices. First, we establish the well-posedness of generalized quasilinear Schr\"odinger equations and give a new proof of the global well-posedness of semilinear Schr\"odinger equations. Then we provide explicit expressions of higher order derivatives of the solution map and prove the analytic dependence between solution and initial data. At the end, we show the existence of wave operator and prove the asymptotic completeness in low dimensions., Comment: 24 pages, no figure

Bound states in the continuum (BICs) are exotic optical topological singularities that defy the typical radiation within the continuum of radiative modes and carry topological polarization vortices in momentum space. Enabling ultrahigh quality factors, BICs have been applied in realizing lasing and Bose-Einstein condensation via micro-/nano- photonic structures, and their momentum-space vortex topologies have been exploited in passive systems, revealing novel spin-orbit photonic effects. However, as representative topological properties, the spin-orbit-related phenemona of BICs in active systems have not yet been explored. Here, we demonstrate the inherent spin-orbit locking in topological BIC lasing. Utilizing photonic crystal (PhC) slabs with square (C4v) and triangular (C6v) lattices, we achieve distinct spin-orbit locking combinations in topological BIC lasing of +1 and -2 topological charges. These BIC lasing profiles manifest as vortex and high-order anti-vortex polarization configurations, directly tied to the topological properties of BICs. Our experimental results directly reveal the spin-orbit locking phenomena through momentum-space spin-dependent self-interference patterns and real-space spin separations of the lasing emissions. This study not only highlights the inherent spin-orbit-locking behaviours of topological BIC lasing but also opens new possibilities for dynamically switchable orbital angular momentum (OAM) lasing by controlling photonic spin, presenting significant potential for advancements in topological photonic source applications.

Bound states in the continuum (BICs), which are confined optical modes exhibiting infinite quality factors and carrying topological polarization configurations in momentum space, have recently sparked significant interest across both fundamental and applied physics.} Here we show that breaking time-reversal symmetry by external magnetic field enables a new form of chiral BICs with spin-orbit locking. Applying a magnetic field to a magneto-optical photonic crystal slab lifts doubly degenerate BICs into a pair of chiral BICs carrying opposite pseudo-spins and orbital angular momenta. Multipole analysis verifies the non-zero angular momenta and reveals the spin-orbital-locking behaviors. In momentum space, we observe ultrahigh quality factors and near-circular polarization surrounding chiral BICs, enabling potential applications in spin-selective nanophotonics. Compared to conventional BICs, the magnetically-induced chiral BICs revealed here exhibit distinct properties and origins, significantly advancing the topological photonics of BICs by incorporating broken time-reversal symmetry.

In this paper, we introduce a novel first-order derivative for functions on a lattice graph, and establish its weak (1, 1) estimate as well as strong (p, p) estimate for p > 1 in weighted spaces. This derivative is designed to reconstruct the discrete Laplacian, enabling an extension of the theory of nonlinear wave equations, including quasilinear wave equations, to lattice graphs. We prove the local well-posedness of generalized quasilinear wave equations and the long-time well-posedness of these equations for small initial data. Furthermore, we prove the global well-posedness of defocusing semilinear wave equations for large initial data., Comment: 23 pages and no figure

Accurate segmentation of tumors in PET/CT images is important in computer-aided diagnosis and treatment of cancer. The key issue of such a segmentation problem lies in the effective integration of complementary information from PET and CT images. However, the quality of PET and CT images varies widely in clinical settings, which leads to uncertainty in the modality information extracted by networks. To take the uncertainty into account in multi-modal information fusion, this paper proposes a novel Multi-modal Evidential Fusion Network (MEFN) comprising a Cross-Modal Feature Learning (CFL) module and a Multi-modal Trusted Fusion (MTF) module. The CFL module reduces the domain gap upon modality conversion and highlights common tumor features, thereby alleviating the needs of the segmentation module to handle modality specificity. The MTF module utilizes mutual attention mechanisms and an uncertainty calibrator to fuse modality features based on modality uncertainty and then fuse the segmentation results under the guidance of Dempster-Shafer Theory. Besides, a new uncertainty perceptual loss is introduced to force the model focusing on uncertain features and hence improve its ability to extract trusted modality information. Extensive comparative experiments are conducted on two publicly available PET/CT datasets to evaluate the performance of our proposed method whose results demonstrate that our MEFN significantly outperforms state-of-the-art methods with improvements of 2.15% and 3.23% in DSC scores on the AutoPET dataset and the Hecktor dataset, respectively. More importantly, our model can provide radiologists with credible uncertainty of the segmentation results for their decision in accepting or rejecting the automatic segmentation results, which is particularly important for clinical applications. Our code will be available at https://github.com/QPaws/MEFN.

Controllable text-to-image (T2I) diffusion models have shown impressive performance in generating high-quality visual content through the incorporation of various conditions. Current methods, however, exhibit limited performance when guided by skeleton human poses, especially in complex pose conditions such as side or rear perspectives of human figures. To address this issue, we present Stable-Pose, a novel adapter model that introduces a coarse-to-fine attention masking strategy into a vision Transformer (ViT) to gain accurate pose guidance for T2I models. Stable-Pose is designed to adeptly handle pose conditions within pre-trained Stable Diffusion, providing a refined and efficient way of aligning pose representation during image synthesis. We leverage the query-key self-attention mechanism of ViTs to explore the interconnections among different anatomical parts in human pose skeletons. Masked pose images are used to smoothly refine the attention maps based on target pose-related features in a hierarchical manner, transitioning from coarse to fine levels. Additionally, our loss function is formulated to allocate increased emphasis to the pose region, thereby augmenting the model's precision in capturing intricate pose details. We assessed the performance of Stable-Pose across five public datasets under a wide range of indoor and outdoor human pose scenarios. Stable-Pose achieved an AP score of 57.1 in the LAION-Human dataset, marking around 13% improvement over the established technique ControlNet. The project link and code is available at https://github.com/ai-med/StablePose.

We give an algorithm for computing the knot Floer homology of a $ (1,1) $ knot from a particular presentation of its fundamental group., Comment: 24 pages, 14 figures

Interactive volume visualization using a mixed reality (MR) system helps provide users with an intuitive spatial perception of volumetric data. Due to sophisticated requirements of user interaction and vision when using MR head-mounted display (HMD) devices, the conflict between the realisticness and efficiency of direct volume rendering (DVR) is yet to be resolved. In this paper, a new MR visualization framework that supports interactive realistic DVR is proposed. An efficient illumination estimation method is used to identify the high dynamic range (HDR) environment illumination captured using a panorama camera. To improve the visual quality of Monte Carlo-based DVR, a new spatio-temporal denoising algorithm is designed. Based on a reprojection strategy, it makes full use of temporal coherence between adjacent frames and spatial coherence between the two screens of an HMD to optimize MR rendering quality. Several MR development modules are also developed for related devices to efficiently and stably display the DVR results in an MR HMD. Experimental results demonstrate that our framework can better support immersive and intuitive user perception during MR viewing than existing MR solutions., Comment: 6 pages, 6 figures

Wireless sensor networks (WSNs), one of the fundamental technologies of the Internet of Things (IoT), can provide sensing and communication services efficiently for IoT-based applications, especially energy-limited applications. Clustering routing protocol plays an important role in reducing energy consumption and prolonging network lifetime. The cluster formation and cluster head selection are the key to improving the performance of the clustering routing protocol. An energy-efficient routing protocol based on multi-threshold segmentation (EERPMS) was proposed in this paper to improve the rationality of cluster formation and cluster head selection. In the stage of cluster formation, inspired by multi-threshold image segmentation, an innovative node clustering algorithm was developed. In the stage of cluster head selection, aiming at minimizing the network energy consumption, a calculation theory of the optimal number and location of cluster heads was established. Furthermore, a novel cluster head selection algorithm was constructed based on the residual energy and optimal location of cluster heads. Simulation results show that EERPMS can improve the distribution uniformity of cluster heads, prolong the network lifetime and save up to 64.50%, 58.60%, and 56.15% network energy as compared to RLEACH, CRPFCM, and FIGWO protocols respectively., Comment: 16 pages, 24 figure, 4 tables

In the present paper, we show that the minimal length of closed geodesics on finite-type hyperbolic surfaces with self-intersection number $k$ has order $2\log k$ as $k$ gets large., Comment: 12 pages, 6 figures