Text-Based Person Retrieval (TBPR) aims to accurately retrieve target individuals from large-scale image databases using only textual descriptions. Existing methods typically assume a ground-truth correspondence between text and images (i.e., strongly correlated). However, in real-world scenarios, this assumption may not be able to hold for the cross-modal matching due to weak or even corrupted correlations between textual descriptions and visual content, referred to as noisy correspondence (NC). Such NC largely disrupts the correspondence learning between visual and semantic modalities. Though prior works have improved single-modal robustness against noisy labels, systematic modeling of both cross-modal and intra-modal geometric structures in TBPR remains limited attention. In this paper, we propose Geometric Structure Consistency Alignment (GSCA) to TBPR, which leverages cross-modal cosine similarity and intra-modal nearest-neighbor affinity to learn visual-semantic consistency under noisy correspondence. To mitigate the structural corruption caused by noisy pairs, we introduce the Structure Refinement and Mining (SRAM) module. By partitioning training data into clean, ambiguous, and noisy subsets, SRAM enables the model to strategically refine the cross-modal correspondence by mining reliable pairs, thus enhancing the reliability of positive or negative samples discrimination and preserving structural consistency across modalities. Extensive experiments demonstrate that our method achieves state-of-the-art performance across three public datasets. On CUHK-PEDES, it boosts Rank-1 by 1.42% in noise-free conditions, sustaining a robust 74.25% Rank-1 under a 50% noise ratio.

AI Generated Content (AIGC) has caught the attention of researchers around the world. Very good results have been achieved in the generation of Western art painting, but little research has been done on the generation of Chinese Landscape Painting (CLP). In addition, the quality of CLP generated by existing studies is still not high enough, they only imitate the color and often lack of details in their scenes. To overcome those weaknesses, we propose a progressive end-to-end Long Memory Adversarial Generation Network (LMGAN) to generate CLP. First, we create a new high-quality CLP dataset. Then we design a memory module and a mapping module to capture more low-dimensional features, as well as a layer extraction module to improve the layers of the generated results. Experiments show that LMGAN can generate richer and more detailed CLP compared to former methods.

Stego-images are often contaminated by interchannel noise or active noise attack when communicating on the Web. And it is challenging to restore embedded image from corrupted stego-image. This paper studies akNN-bit approximation algorithm to remove noises in embedded image. The proposed algorithm distinguishes reliable bits from extracted bits, and estimates pixel values by keeping reliable bits unchanged and correcting unreliable bits. Specifically, the 8th (highest) unreliable bit of a pixel can be approximated with its nearest neighbor pixels. And then, if an unreliable bit locates at any one of the$5^{th}\sim 7^{th}$bits of a pixel, it is adjusted with two nearest neighbors of the pixel, where the pixel is in-between these two nearest neighbors. Finally, for other unreliable bits, each one is approximated by the maximum and minimum possible values of nearest neighbors of its pixel. We conduct experiments for illustrating the efficiency, and demonstrate that the proposed algorithm can recover the embedded images with good visual quality from corrupted stego-images.