The process is formalized below.

Wide-angle cameras, despite their popularity for content creation, suffer from distortion-induced facial stretching-especially at the edge of the lens-which degrades visual appeal. To address this issue, we propose an image portrait correction framework using diffusion models named ImagePD. It integrates the long-range awareness of transformer and multi-step denoising of diffusion models into a unified framework, achieving global structural robustness and local detail refinement. Besides, considering the high cost of obtaining video labels, we then repurpose ImagePD for unlabeled wide-angle videos (termed VideoPD), by spatiotemporal diffusion adaption with spatial consistency and temporal smoothness constraints. For the former, we encourage the denoised image to approximate pseudo labels following the wide-angle distortion distribution pattern, while for the latter, we derive rectification trajectories with backward optical flows and smooth them. Compared with ImagePD, VideoPD maintains high-quality facial corrections in space and mitigates the potential temporal shakes sequentially. Finally, to establish an evaluation benchmark and train the framework, we establish a video portrait dataset with a large diversity in people number, lighting conditions, and background. Experiments demonstrate that the proposed methods outperform existing solutions quantitatively and qualitatively, contributing to high-fidelity wide-angle videos with stable and natural portraits. The codes and dataset will be available.

As lunar exploration missions grow increasingly complex, ensuring safe and autonomous rover-based surface exploration has become one of the key challenges in lunar exploration tasks. In this work, we have developed a lunar surface simulation system called the Lunar Exploration Simulator System (LESS) and the LunarSeg dataset, which provides RGB-D data for lunar obstacle segmentation that includes both positive and negative obstacles. Additionally, we propose a novel two-stage segmentation network called LuSeg. Through contrastive learning, it enforces semantic consistency between the RGB encoder from Stage I and the depth encoder from Stage II. Experimental results on our proposed LunarSeg dataset and additional public real-world NPO road obstacle dataset demonstrate that LuSeg achieves state-of-the-art segmentation performance for both positive and negative obstacles while maintaining a high inference speed of approximately 57\,Hz. We have released the implementation of our LESS system, LunarSeg dataset, and the code of LuSeg at:https://github.com/nubot-nudt/LuSeg.

Laplace Neural Operators (LNOs) have recently emerged as a promising approach in scientific machine learning due to the ability to learn nonlinear maps between functional spaces. However, this framework often requires substantial amounts of high-fidelity (HF) training data, which is often prohibitively expensive to acquire. To address this, we propose multi-fidelity Laplace Neural Operators (MF-LNOs), which combine a low-fidelity (LF) base model with parallel linear/nonlinear HF correctors and dynamic inter-fidelity weighting. This allows us to exploit correlations between LF and HF datasets and achieve accurate inference of quantities of interest even with sparse HF data. We further incorporate a modified replica exchange stochastic gradient Langevin algorithm, which enables a more effective posterior distribution estimation and uncertainty quantification in model predictions. Extensive validation across four canonical dynamical systems (the Lorenz system, Duffing oscillator, Burgers equation, and Brusselator reaction-diffusion system) demonstrates the framework's effectiveness. The results show significant improvements, with testing losses reduced by 40% to 80% compared to traditional approaches. This validates MF-LNO as a versatile tool for surrogate modeling in parametric PDEs, offering significant improvements in data efficiency and uncertainty-aware prediction.

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the result-oriented performance but neglect the underlying principles in knowledge acquisition and generalization. Inspired by human-like mathematical reasoning, we introduce WE-MATH, the first benchmark specifically designed to explore the problem-solving principles beyond end-to-end performance. We meticulously collect and categorize 6.5K visual math problems, spanning 67 hierarchical knowledge concepts and five layers of knowledge granularity. We decompose composite problems into sub-problems according to the required knowledge concepts and introduce a novel four-dimensional metric, namely Insufficient Knowledge (IK), Inadequate Generalization (IG), Complete Mastery (CM), and Rote Memorization (RM), to hierarchically assess inherent issues in LMMs' reasoning process. With WE-MATH, we conduct a thorough evaluation of existing LMMs in visual mathematical reasoning and reveal a negative correlation between solving steps and problem-specific performance. We confirm the IK issue of LMMs can be effectively improved via knowledge augmentation strategies. More notably, the primary challenge of GPT-4o has significantly transitioned from IK to IG, establishing it as the first LMM advancing towards the knowledge generalization stage. In contrast, other LMMs exhibit a marked inclination towards Rote Memorization - they correctly solve composite problems involving multiple knowledge concepts yet fail to answer sub-problems. We anticipate that WE-MATH will open new pathways for advancements in visual mathematical reasoning for LMMs. The WE-MATH data and evaluation code are available at https://github.com/We-Math/We-Math.

With the widespread use of surveillance cameras in smart cities [104] and the boom of online video applications powered by 4/5G communication technologies, traditional human inspection is no longer able to accurately monitor the video data generated around the clock, which is not only time-consuming and labor-intensive but also poses the risk of leaking important information (e.g., biometrics and sensitive speech). In contrast, VAD-empowered IoVT applications [54], such as Intelligent Surveillance Systems (IVSS) and automated content analysis platforms, can process massive video streams online and detect events of interest in real-time, sending only noteworthy anomaly parts for human review, significantly reducing data storage and communication costs, and helping to eliminate public concerns about data security and privacy protection. As a result, VAD has gained widespread attention in academia and industry over the last decade and has been used in emerging fields such as information forensics [154], industrial manufacturing [71] in smart cities as well as online content analysis in mobile video applications [153]. VAD extends the data scope of conventional Anomaly Detection (AD) from time series, images, and graphs to video, which not only needs to cope with the endogenous data complexity, but also needs to take into account the computational and communication costs in resource-limited devices [55]. Specifically, the inherent high-dimensional structure of video data, high information density and redundancy, heterogeneity of temporal and spatial patterns, and feature entanglement between foreground targets and background scenes make VAD more challenging than traditional AD tasks at the levels of representation learning and anomaly discrimination [89]. Existing studies [4, 60, 69, 76] have shown that high-performance VAD models need to target the modeling of appearance and motion information, i.e., the difference between regular events and anomalous examples in both spatial and temporal dimensions. In contrast to time series AD that mainly measures periodic temporal patterns of variables, and image AD which only focusing on spatial contextual deviations, VAD needs to extract both discriminative spatial and temporal features from a large amount of redundant information (e.g., repetitive temporal contexts and label-independent data distributions), as well as to learn the differences between normal and anomalous events in terms of their local appearances and global motions [100]. However, video anomalies are ambiguous and subjective [48].

One of the most discussed problems in the financial world is stock option pricing. The Black-Scholes Equation is a Parabolic Partial Differential Equation which provides an option pricing model. The present work proposes an approach based on Neural Networks to solve the Black-Scholes Equations. Real-world data from the stock options market were used as the initial boundary to solve the Black-Scholes Equation. In particular, times series of call options prices of Brazilian companies Petrobras and Vale were employed. The results indicate that the network can learn to solve the Black-Sholes Equation for a specific real-world stock options time series. The experimental results showed that the Neural network option pricing based on the Black-Sholes Equation solution can reach an option pricing forecasting more accurate than the traditional Black-Sholes analytical solutions. The experimental results making it possible to use this methodology to make short-term call option price forecasts in options markets.

The rapid growth of the Industry 4.0 paradigm is increasing the pressure to develop effective automated monitoring systems. Artificial Intelligence (AI) is a convenient tool to improve the efficiency of industrial processes while reducing errors and waste. In fact, it allows the use of real-time data to increase the effectiveness of monitoring systems, minimize errors, make the production process more sustainable, and save costs. In this paper, a novel automatic monitoring system is proposed in the context of production process of plastic consumables used in analysis laboratories, with the aim to increase the effectiveness of the control process currently performed by a human operator. In particular, we considered the problem of classifying the presence or absence of a transparent anticoagulant substance inside test tubes. Specifically, a hand-designed deep network model is used and compared with some state-of-the-art models for its ability to categorize different images of vials that can be either filled with the anticoagulant or empty. Collected results indicate that the proposed approach is competitive with state-of-the-art models in terms of accuracy. Furthermore, we increased the complexity of the task by training the models on the ability to discriminate not only the presence or absence of the anticoagulant inside the vial, but also the size of the test tube. The analysis performed in the latter scenario confirms the competitiveness of our approach. Moreover, our model is remarkably superior in terms of its generalization ability and requires significantly fewer resources. These results suggest the possibility of successfully implementing such a model in the production process of a plastic consumables company.

Torch relay is an important tradition of the Olympics and heralds the start of the Games. Robots applied in the torch relay activity can not only demonstrate the technological capability of humans to the world but also provide a sight of human lives with robots in the future. This article presents an aerial manipulator designed for the robot-to-robot torch relay task of the Beijing 2022 Winter Olympics. This aerial manipulator system is composed of a quadrotor, a 3 DoF (Degree of Freedom) manipulator, and a monocular camera. This article primarily describes the system design and system control scheme of the aerial manipulator. The experimental results demonstrate that it can complete robot-to-robot torch relay task under the guidance of vision in the ice and snow field.