Search

Generating landscape paintings expands the possibilities of artistic creativity and imagination. Traditional landscape painting methods involve using ink or colored ink on rice paper, which requires substantial time and effort. These methods are susceptible to errors and inconsistencies and lack precise control over lines and colors. This paper presents LPGen, a high-fidelity, controllable model for landscape painting generation, introducing a novel multi-modal framework that integrates image prompts into the diffusion model. We extract its edges and contours by computing canny edges from the target landscape image. These, along with natural language text prompts and drawing style references, are fed into the latent diffusion model as conditions. We implement a decoupled cross-attention strategy to ensure compatibility between image and text prompts, facilitating multi-modal image generation. A decoder generates the final image. Quantitative and qualitative analyses demonstrate that our method outperforms existing approaches in landscape painting generation and exceeds the current state-of-the-art. The LPGen network effectively controls the composition and color of landscape paintings, generates more accurate images, and supports further research in deep learning-based landscape painting generation.

Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent Scattering experiment (RELICS), a proposed reactor neutrino program using liquid xenon time projection chamber (LXeTPC) technology, aims to investigate the CEvNS process of antineutrinos off xenon atomic nuclei. In this work, the design of the experiment is studied and optimized based on Monte Carlo (MC) simulations. To achieve a sufficiently low energy threshold for CEvNS detection, an ionization-only analysis channel is adopted for RELICS. A high emission rate of delayed electrons after a big ionization signal is the major background, leading to an analysis threshold of 120 photo-electrons in the CEvNS search. The second largest background, nuclear recoils induced by cosmic-ray neutrons, is suppressed via a passive water shield. The physics potential of RELICS is explored with a 32 kg-yr exposure at a baseline of 25 m from a reactor core with a 3 GW thermal power. In an energy range of 120 to 240 PE, we expect 4902.4 CEvNS and 1318.4 background events. The sensitivity of RELICS to the weak mixing angle is investigated at a low momentum transfer. Our study shows that RELICS can further improve the constraints on the non-standard neutrino interaction (NSI) compared to the current best results.

We present OAKINK2, a dataset of bimanual object manipulation tasks for complex daily activities. In pursuit of constructing the complex tasks into a structured representation, OAKINK2 introduces three level of abstraction to organize the manipulation tasks: Affordance, Primitive Task, and Complex Task. OAKINK2 features on an object-centric perspective for decoding the complex tasks, treating them as a sequence of object affordance fulfillment. The first level, Affordance, outlines the functionalities that objects in the scene can afford, the second level, Primitive Task, describes the minimal interaction units that humans interact with the object to achieve its affordance, and the third level, Complex Task, illustrates how Primitive Tasks are composed and interdependent. OAKINK2 dataset provides multi-view image streams and precise pose annotations for the human body, hands and various interacting objects. This extensive collection supports applications such as interaction reconstruction and motion synthesis. Based on the 3-level abstraction of OAKINK2, we explore a task-oriented framework for Complex Task Completion (CTC). CTC aims to generate a sequence of bimanual manipulation to achieve task objectives. Within the CTC framework, we employ Large Language Models (LLMs) to decompose the complex task objectives into sequences of Primitive Tasks and have developed a Motion Fulfillment Model that generates bimanual hand motion for each Primitive Task. OAKINK2 datasets and models are available at https://oakink.net/v2., Comment: To be appeared in CVPR 2024. 26 pages

We construct equivalences among four notions associated to a reductive group scheme $G$: factorization super central extensions of the loop group of $G$ by $\mathbb G_m$ subject to a condition on the commutator, factorization super line bundles on the affine Grassmannian of $G$, rigidified sections of a quotient of $2$-truncated K-theory over the Zariski classifying stack of $G$, and combinatorial data defined by Brylinski and Deligne in a conjectural extension of their classification theorem., Comment: 49 pages

This paper surveys different publicly available neural network models used for detecting wildfires using regular visible-range cameras which are placed on hilltops or forest lookout towers. The neural network models are pre-trained on ImageNet-1K and fine-tuned on a custom wildfire dataset. The performance of these models is evaluated on a diverse set of wildfire images, and the survey provides useful information for those interested in using transfer learning for wildfire detection. Swin Transformer-tiny has the highest AUC value but ConvNext-tiny detects all the wildfire events and has the lowest false alarm rate in our dataset.

We prove the geometric Satake equivalence for \'etale metaplectic covers of reductive group schemes and extend the Langlands parametrization of V. Lafforgue to genuine cusp forms defined on their associated covering groups., Comment: 64 pages, comments welcome!

Given a reductive group scheme $G$, we give a linear algebraic description of reduced \'etale $4$-cocycles on its classifying stack $\mathrm B(G)$. These cocycles form a $2$-groupoid, which we interpret as parameters of metaplectic covers of $G$. We use our linear algebraic description to define the Langlands dual of a metaplectic cover., Comment: 78 pages, a substantial revision of "metaplectic group schemes"

With the development of social media, various rumors can be easily spread on the Internet and such rumors can have serious negative effects on society. Thus, it has become a critical task for social media platforms to deal with suspected rumors. However, due to the lack of effective tools, it is often difficult for platform administrators to analyze and validate rumors from a large volume of information on a social media platform efficiently. We have worked closely with social media platform administrators for four months to summarize their requirements of identifying and analyzing rumors, and further proposed an interactive visual analytics system, RumorLens, to help them deal with the rumor efficiently and gain an in-depth understanding of the patterns of rumor spreading. RumorLens integrates natural language processing (NLP) and other data processing techniques with visualization techniques to facilitate interactive analysis and validation of suspected rumors. We propose well-coordinated visualizations to provide users with three levels of details of suspected rumors: an overview displays both spatial distribution and temporal evolution of suspected rumors; a projection view leverages a metaphor-based glyph to represent each suspected rumor and further enable users to gain a quick understanding of their overall characteristics and similarity with each other; a propagation view visualizes the dynamic spreading details of a suspected rumor with a novel circular visualization design, and facilitates interactive analysis and validation of rumors in a compact manner. By using a real-world dataset collected from Sina Weibo, one case study with a domain expert is conducted to evaluate

As a measure of the long-term contribution produced by customers in a service or product relationship, life-time value, or LTV, can more comprehensively find the optimal strategy for service delivery. However, it is challenging to accurately abstract the LTV scene, model it reasonably, and find the optimal solution. The current theories either cannot precisely express LTV because of the single modeling structure, or there is no efficient solution. We propose a general LTV modeling method, which solves the problem that customers' long-term contribution is difficult to quantify while existing methods, such as modeling the click-through rate, only pursue the short-term contribution. At the same time, we also propose a fast dynamic programming solution based on a mutated bisection method and the memoryless repeated experiments assumption. The model and method can be applied to different service scenarios, such as the recommendation system. Experiments on real-world datasets confirm the effectiveness of the proposed model and optimization method. In addition, this whole LTV structure was deployed at a large E-commerce mobile phone application, where it managed to select optimal push message sending time and achieved a 10\% LTV improvement.

Link prediction in structured-data is an important problem for many applications, especially for recommendation systems. Existing methods focus on how to learn the node representation based on graph-based structure. High-dimensional sparse edge features are not fully exploited. Because balancing precision and computation efficiency is significant for recommendation systems in real world, multiple-level feature representation in large-scale sparse graph still lacks effective and efficient solution. In this paper, we propose a practical solution about graph neural networks called Attributed Graph Convolutional Networks(AGCN) to incorporate edge attributes when apply graph neural networks in large-scale sparse networks. We formulate the link prediction problem as a subgraph classification problem. We firstly propose an efficient two-level projection to decompose topological structures to node-edge pairs and project them into the same interaction feature space. Then we apply multi-layer GCN to combine the projected node-edge pairs to capture the topological structures. Finally, the pooling representation of two units is treated as the input of classifier to predict the probability. We conduct offline experiments on two industrial datasets and one public dataset and demonstrate that AGCN outperforms other excellent baselines. Moreover, we also deploy AGCN method to important scenarios on Xianyu and AliExpress. In online systems, AGCN achieves over 5% improvement on online metrics.

We give sharp criteria for when a reductive group scheme satisfies Tannakian reconstruction. When the base scheme is Noetherian, we explicitly identify its Tannaka group scheme., Comment: 9 pages

Wide field small aperture telescopes (WFSATs) are commonly used for fast sky survey. Telescope arrays composed by several WFSATs are capable to scan sky several times per night. Huge amount of data would be obtained by them and these data need to be processed immediately. In this paper, we propose ARGUS (Astronomical taRGets detection framework for Unified telescopes) for real-time transit detection. The ARGUS uses a deep learning based astronomical detection algorithm implemented in embedded devices in each WFSATs to detect astronomical targets. The position and probability of a detection being an astronomical targets will be sent to a trained ensemble learning algorithm to output information of celestial sources. After matching these sources with star catalog, ARGUS will directly output type and positions of transient candidates. We use simulated data to test the performance of ARGUS and find that ARGUS can increase the performance of WFSATs in transient detection tasks robustly., Comment: To appear in Proc. of SPIE 2020, Paper Number (11449-80), Comments are welcome

Music-to-dance translation is a brand-new and powerful feature in recent role-playing games. Players can now let their characters dance along with specified music clips and even generate fan-made dance videos. Previous works of this topic consider music-to-dance as a supervised motion generation problem based on time-series data. However, these methods suffer from limited training data pairs and the degradation of movements. This paper provides a new perspective for this task where we re-formulate the translation problem as a piece-wise dance phrase retrieval problem based on the choreography theory. With such a design, players are allowed to further edit the dance movements on top of our generation while other regression based methods ignore such user interactivity. Considering that the dance motion capture is an expensive and time-consuming procedure which requires the assistance of professional dancers, we train our method under a semi-supervised learning framework with a large unlabeled dataset (20x than labeled data) collected. A co-ascent mechanism is introduced to improve the robustness of our network. Using this unlabeled dataset, we also introduce self-supervised pre-training so that the translator can understand the melody, rhythm, and other components of music phrases. We show that the pre-training significantly improves the translation accuracy than that of training from scratch. Experimental results suggest that our method not only generalizes well over various styles of music but also succeeds in expert-level choreography for game players., Comment: 14 pages, 8 figures

To maximize cumulative user engagement (e.g. cumulative clicks) in sequential recommendation, it is often needed to tradeoff two potentially conflicting objectives, that is, pursuing higher immediate user engagement (e.g., click-through rate) and encouraging user browsing (i.e., more items exposured). Existing works often study these two tasks separately, thus tend to result in sub-optimal results. In this paper, we study this problem from an online optimization perspective, and propose a flexible and practical framework to explicitly tradeoff longer user browsing length and high immediate user engagement. Specifically, by considering items as actions, user's requests as states and user leaving as an absorbing state, we formulate each user's behavior as a personalized Markov decision process (MDP), and the problem of maximizing cumulative user engagement is reduced to a stochastic shortest path (SSP) problem. Meanwhile, with immediate user engagement and quit probability estimation, it is shown that the SSP problem can be efficiently solved via dynamic programming. Experiments on real-world datasets demonstrate the effectiveness of the proposed approach. Moreover, this approach is deployed at a large E-commerce platform, achieved over 7% improvement of cumulative clicks.