Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay-where factors lose their predictive power over time-poses a significant challenge for alpha mining. Traditional methods such as genetic programming are prone to rapid alpha decay, primarily due to their susceptibility to overfitting. At the same time, approaches driven by Large Language Models (LLMs), despite their promise, often fail to impose regularization against factor homogenization-resulting in crowded signals and accelerated decay. To address this challenge, we propose AlphaAgent, an autonomous framework that effectively integrates LLM-driven agents with ad hoc regularization for mining decay-resistant alpha factors. AlphaAgent employs three key mechanisms: (i) originality enforcement through a similarity measure based on abstract syntax trees (ASTs) against existing alphas(ii) hypothesis-factor alignment via LLM-evaluated semantic consistency between market hypotheses and generated factors, and (iii) complexity control via AST-based structural constraints, preventing over-engineered constructions that are prone to overfitting. These mechanisms collectively guide the alpha generation process to balance originality, financial rationale, and adaptability to evolving market conditions, mitigating the risk of alpha decay. Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and U.S. S&P 500 markets over the past four years. Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.

In recent years, the Transformer architecture has shown its superiority in the video-based person re-identification task. Inspired by video representation learning, these methods mainly focus on designing modules to extract informative spatial and temporal features. However, they are still limited in extracting local attributes and global identity information, which are critical for the person re-identification task. In this paper, we propose a novel Multi-Stage Spatial-Temporal Aggregation Transformer (MSTAT) with two novel designed proxy embedding modules to address the above issue. Specifically, MSTAT consists of three stages to encode the attribute-associated, the identity-associated, and the attribute-identity-associated information from the video clips, respectively, achieving the holistic perception of the input person. We combine the outputs of all the stages for the final identification. In practice, to save the computational cost, the Spatial-Temporal Aggregation (STA) modules are first adopted in each stage to conduct the self-attention operations along the spatial and temporal dimensions separately. We further introduce the Attribute-Aware and Identity-Aware Proxy embedding modules (AAP and IAP) to extract the informative and discriminative feature representations at different stages. All of them are realized by employing newly designed self-attention operations with specific meanings. Moreover, temporal patch shuffling is also introduced to further improve the robustness of the model. Extensive experimental results demonstrate the effectiveness of the proposed modules in extracting the informative and discriminative information from the videos, and illustrate the MSTAT can achieve state-of-the-art accuracies on various standard benchmarks.

In this article, an improved short-term speed prediction method is proposed to predict short-term future speed and analyze future energy consumption of intelligent fuel cell vehicles. The short-term future speed is predicted by the proposed Inflated 3-D Inception long short-term memory (LSTM) network, which takes the spatiotemporal-vision information and vehicle motion states. Specifically, the spatiotemporal-vision-based deep neural network utilizes image sequences captured by a front-facing camera as environmental information and historical speed series as motion information to improve the prediction accuracy. Then, a case study of the proposed speed prediction method, with rule-based energy management strategy to calculate future energy consumption, is presented. The simulation results show that short-term speed prediction based on the Inflated 3-D Inception LSTM network can achieve high accuracy of speed prediction in various traffic densities, as well as low prediction errors of future energy consumption including the hydrogen consumption and state-of-charge attenuation.

Different color patterns of quick response (QR) codes, such as RGB, grayscale, and binary QR codes, are widely used in applications. In this paper, we propose a novel XOR-based visual secret sharing (VSS) scheme using grayscale QR codes as cover images and binary QR code as secret image. First, all the codewords of the secret QR code image are encoded into n temporary binary QR code images, which are substituted for the second significant bit planes of the grayscale QR code cover images to generate n shares. Each share is a grayscale QR code image, which can be decoded by a standard QR code decoder, so that it may not attract the attention of potential attackers when distributed in the public channel. The secret image can be recovered by XORing the codewords regions of QR codes which are extracted from the second significant bit planes of the grayscale shares. More importantly, the proposed scheme is robust to JPEG compression, addition of different noises, rotation, resizing, and cropping, which is useful in practice. The effectiveness and robustness of our scheme are shown by the experimental results. The application of QR code is suitable for wireless multimedia data security.

It is well known that depth can be recovered from a single image using defogging method. Inspiriting by the idea of defogging using dark channel prior, we propose a new approach to recover depth. The input is a foggy image. We defog the image using an improved dark channel prior method. We adopt the dilating and eroding method to refine the block effect. Experimental results show that our method can recover an accuracy depth from a single image.