Clustering traditionally aims to reveal a natural grouping structure within unlabeled data. However, this structure may not always align with users' preferences. In this paper, we propose a personalized clustering method that explicitly performs targeted representation learning by interacting with users via modicum task information (e.g., must-link or cannot-link pairs) to guide the clustering direction. We query users with the most informative pairs, i.e., those pairs most hard to cluster and those most easy to miscluster, to facilitate the representation learning in terms of the clustering preference. Moreover, by exploiting attention mechanism, the targeted representation is learned and augmented. By leveraging the targeted representation and constrained contrastive loss as well, personalized clustering is obtained. Theoretically, we verify that the risk of personalized clustering is tightly bounded, guaranteeing that active queries to users do mitigate the clustering risk. Experimentally, extensive results show that our method performs well across different clustering tasks and datasets, even when only a limited number of queries are available.

In recent research on image encryption, many schemes associate the key generation mechanism with the plaintext to resist chosen plaintext attacks. However, when the sender encrypts many images, a large amount of additional data related to the plaintext need to be transmitted, which leads to problems such as high transmission costs, high requirements for key storage space, and complex key management. Therefore, in this paper, we propose a self-sufficient plaintext-related JPEG image encryption scheme based on a unified key (SPJEU). This scheme establishes the connection between the plaintext and the key by selecting the direct current (DC) coefficients in the JPEG image through a unified key. Homomorphic encryption is applied to the selected DC coefficients, allowing plaintext information to be decrypted directly from the ciphertext domain using a specific calculation method. The remaining DC coefficients are encrypted through group diffusion, and the alternating current (AC) coefficients are grouped and permuted based on the run length. Extensive experiments show that our scheme can resist chosen plaintext attacks, avoid transmitting plaintext-related additional data in the communication channel, and simplify key management. This scheme also ensures the security and format compatibility of the ciphertext image, and the file increment after encryption is very small.

The existing excellent person re-identification (Re-ID) model is still affected by the samples with the incorrect labels. It is difficult to accurately annotate person images in the real scene, resulting in label noise. To avoid fitting to the noisy labels, a common solution in Re-ID is to replace the original label with the label predicted by the deep model. Unfortunately, similar samples of different identities with the same label are due to label noise, which is challenging for the model to distinguish them. Neighborhood information can optimize noisy labels through neighborhood labels and similarity between samples. This paper proposes a label refinement module based on neighborhood information (LRNI) for person Re-ID with label noise. Specifically, we first use the pre-trained model to extract features and calculate the similarity between samples. Rather than treating samples as isolated, the similarity used as label propagation weight and neighborhood labels are combined to optimize noisy labels. To further reduce the influence of label noise, we design a hard sample re-weighting (HSR) strategy to balance the learning of noisy and boundary samples. Experimental results under different noise settings demonstrate our method's effectiveness in the person Re-ID task.

Effective and timely monitoring of croplands is critical for managing food supply. While remote sensing data from earth-observing satellites can be used to monitor croplands over large regions, this task is challenging for small-scale croplands as they cannot be captured precisely using coarse-resolution data. On the other hand, the remote sensing data in higher resolution are collected less frequently and contain missing or disturbed data. Hence, traditional sequential models cannot be directly applied on high-resolution data to extract temporal patterns, which are essential to identify crops. In this work, we propose a generative model to combine multi-scale remote sensing data to detect croplands at high resolution. During the learning process, we leverage the temporal patterns learned from coarse-resolution data to generate missing high-resolution data. Additionally, the proposed model can track classification confidence in real time and potentially lead to an early detection. The evaluation in an intensively cultivated region demonstrates the effectiveness of the proposed method in cropland detection.