Contrastive vision-language pre-training models such as CLIP have achieved remarkable progress in vision-language understanding. However, a modality gap still exists in the shared embedding space, which refers to the gap between image and text feature clusters, ultimately limiting the performance of downstream tasks.Most existing studies attempt to alleviate this gap by directly pulling embeddings closer within the shared space. However, they often overlook the balance between alignment and distinctiveness, leading to degraded uniformity, which can easily result in representation collapse. Our approach focuses on addressing the modality gap from modality distinctiveness. We propose CCRA (Cross-modal Complementary Representation Alignment), a lightweight post-alignment framework that explicitly models the complementarity between modalities while maintaining semantic consistency, thereby effectively alleviating the modality gap.CCRA consists of two modules: (1) a Feature Complementary Network (FCN), which dynamically extracts and fuses complementary semantic cues and learnable query vectors; (2) a Distillation Enhancement Module (DEM), which transfers similarity distributions from a frozen CLIP teacher model to maintain training stability through a distillation constraint. CCRA achieves consistent improvements over five representative baselines across two cross-modal retrieval benchmarks (COCO2017-Val and Flickr8k/30k). On COCO2017-Val, it shows an improvement of 10.06% for I→T and 6.12% for T→I, reaching the best overall performance. Both quantitative and qualitative analyses further confirm that CCRA effectively narrows the modality gap and produces more uniform feature distributions on the hypersphere.

With the rapid growth of cloud storage user scale, there are dual challenges of resource waste and security hazards in massive data storage: on the one hand, redundant data exacerbates storage overhead; on the other hand, unauthorized access exacerbates the possibility of data leakage or tampering. To this end, this paper designs a shared data auditing scheme that supports fine-grained access control and cloud deduplication. First, combining Random Convergent Encryption (RCE), Proof-of-Ownership (PoW) technology, and introducing a certificate-less cryptosystem to securely deduplicate data in the cloud while eliminating certificate management and key escrow risks. Second, the data is encrypted using Ciphertext-Policy Attribute-Based Encryption (CP-ABE) technology, and only authorized users can decrypt the data based on attribute matching, which can effectively resist the risk of data leakage due to unauthorized access. At the same time, we designate an auditor to carry out data integrity auditing to prevent malicious audit behavior. Finally, Security and performance evaluations show that the scheme we’ve proposed is quite efficient and competitive.

Relation extraction (RE) aims to identify semantic relations between entities in unstructured text.Although recent work extends traditional RE to multimodal scenarios, most approaches still adopt classification-based paradigms with fused multimodal features, representing relations as discrete labels.This paradigm has two significant limitations: (1) it overlooks structural constraints like entity types and positional cues, and (2) it lacks semantic expressiveness for fine-grained relation understanding.We propose Retrieval Over Classification (ROC), a novel framework that reformulates multimodal RE as a retrieval task driven by relation semantics.ROC integrates entity type and positional information through a multimodal encoder, expands relation labels into natural language descriptions using a large language model, and aligns entity-relation pairs via semantic similarity-based contrastive learning.Experiments show that our method achieves state-of-the-art performance on the benchmark datasets MNRE and MORE and exhibits stronger robustness and interpretability.

Manufacturing specifications are documents entailing different techniques, processes, and components involved in manufacturing. There is a growing demand for named entity recognition (NER) resources and techniques for manufacturing-specific named entities, with the development of smart manufacturing. In this paper, we introduce a corpus of Chinese manufacturing specifications, named MS-NERC, including 4,424 sentences and 16,383 entities. We also propose an entity recognizer named Trainable State Transducer (TST), which is initialized with a finite state transducer describing the morphological patterns of entities. It can directly recognize entities based on prior morphological knowledge without training. Experimental results show that TST achieves an overall 82.05% F1 score for morphological-specific entities in zero-shot. TST can be improved through training, the result of which outperforms neural methods in few-shot and rich-resource. We believe that our corpus and model will be valuable resources for NER research not only in manufacturing but also in other low-resource domains.