Search

Text attribute person search aims to find specific pedestrians through given textual attributes, which is very meaningful in the scene of searching for designated pedestrians through witness descriptions. The key challenge is the significant modality gap between textual attributes and images. Previous methods focused on achieving explicit representation and alignment through unimodal pre-trained models. Nevertheless, the absence of inter-modality correspondence in these models may lead to distortions in the local information of intra-modality. Moreover, these methods only considered the alignment of inter-modality and ignored the differences between different attribute categories. To mitigate the above problems, we propose an Attribute-Aware Implicit Modality Alignment (AIMA) framework to learn the correspondence of local representations between textual attributes and images and combine global representation matching to narrow the modality gap. Firstly, we introduce the CLIP model as the backbone and design prompt templates to transform attribute combinations into structured sentences. This facilitates the model's ability to better understand and match image details. Next, we design a Masked Attribute Prediction (MAP) module that predicts the masked attributes after the interaction of image and masked textual attribute features through multi-modal interaction, thereby achieving implicit local relationship alignment. Finally, we propose an Attribute-IoU Guided Intra-Modal Contrastive (A-IoU IMC) loss, aligning the distribution of different textual attributes in the embedding space with their IoU distribution, achieving better semantic arrangement. Extensive experiments on the Market-1501 Attribute, PETA, and PA100K datasets show that the performance of our proposed method significantly surpasses the current state-of-the-art methods.

The study on minimal linear codes has received great attention due to their significant applications in secret sharing schemes and secure two-party computation. Until now, numerous minimal linear codes have been discovered. However, to the best of our knowledge, no infinite family of minimal ternary linear codes was found from vectorial functions. In this paper, we present a necessary and sufficient condition for a large class of ternary linear codes from vectorial functions such that those codes are minimal. Based on that, we construct several minimal ternary linear codes with three-weight from vectorial regular plateaued functions, and determine their weight distributions. Moreover, we also give a necessary and sufficient condition for a large family of ternary linear codes from vectorial functions such that the codes are minimal and violate the AB condition simultaneously. According to this characterization, we find several minimal ternary linear codes violating the AB condition. Notably, our results show that our method can be applied to solve a problem on minimal linear codes proposed by Li et al.

Although the U-Net architecture has been extensively used for segmentation of medical images, we address two of its shortcomings in this work. Firstly, the accuracy of vanilla U-Net degrades when the target regions for segmentation exhibit significant variations in shape and size. Even though the U-Net already possesses some capability to analyze features at various scales, we propose to explicitly add multi-scale feature maps in each convolutional module of the U-Net encoder to improve segmentation of histology images. Secondly, the accuracy of a U-Net model also suffers when the annotations for supervised learning are noisy or incomplete. This can happen due to the inherent difficulty for a human expert to identify and delineate all instances of specific pathology very precisely and accurately. We address this challenge by introducing auxiliary confidence maps that emphasize less on the boundaries of the given target regions. Further, we utilize the bootstrapping properties of the deep network to address the missing annotation problem intelligently. In our experiments on a private dataset of breast cancer lymph nodes, where the primary task was to segment germinal centres and sinus histiocytosis, we observed substantial improvement over a U-Net baseline based on the two proposed augmentations., Comment: 12 pages, 4 figures , 2 tables ,Added Attention UNet Results, Added Sinus and Germinal Center overlay images, Modified paper format, Fixed Title typos

Task-oriented image semantic communication is a new communication paradigm, which aims to transmit semantics for artificial intelligent (AI) tasks while ignoring the reconstruction quality of the images. However, in some applications, such as autonomous driving, both image reconstruction quality and the performance of the followed AI tasks must be simultaneously considered. To tackle this challenge, this paper proposes a task-oriented semantic communication scheme with semantic reconstruction (TOSC-SR). Its main goal is to simultaneously minimize pixel-level and task-relevant semantic-level distortion during communications under a certain rate, which formulates a new rate-distortion optimization problem. To successfully measure the loss at the semantic level, a new form of semantic distortion measured by the mutual information between the semantic-reconstructed images and the task labels is proposed. Then, we derive an analytical solution for the formulated problem, where the self-consistent equations of the problem are obtained to determine the optimal mapping of the source and the semantic-reconstructed images. To implement TOSC-SR, we further obtain an extended form of rate-distortion form based on the variational approximation of mutual information, which is applicable to multiple AI tasks. Experimental results show that the proposed approach outperforms the traditional JPEG, JPEG2000, BPG, VVC-based image communication systems and deep learning based benchmarks in terms of image reconstruction quality, AI task performance, and multi-task generalization ability., Comment: 17 pages, 8 figures

A radical paradigm shift of wireless networks from ``connected things'' to ``connected intelligence'' undergoes, which coincides with the Shanno and Weaver's envisions: Communications will transform from the technical level to the semantic level. This article proposes a semantic communication method with artificial intelligence tasks (SC-AIT). First, the architecture of SC-AIT is elaborated. Then, based on the proposed architecture, we implement SC-AIT for a image classifications task. A prototype of SC-AIT is also established for surface defect detection, is conducted. Experimental results show that SC-AIT has much lower bandwidth requirements, and can achieve more than $40\%$ classification accuracy gains compared with the communications at the technical level. Future trends and key challenges for semantic communications are also identified.