4.6 Article

Characterization inference based on joint-optimization of multi-layer semantics and deep fusion matching network

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Research on image classification method based on improved multi-scale relational network

Wenfeng Zheng et al.

Summary: This paper investigates how to quickly learn from a small number of sample images. By using the model-independent meta-learning algorithm and the multi-scale meta-relational network, the generalization ability of the measurement is enhanced, leading to improved classification accuracy.

PEERJ COMPUTER SCIENCE (2021)

Article Computer Science, Artificial Intelligence

Knowledge base graph emb e dding module design for Visual question answering model

Wenfeng Zheng et al.

Summary: This paper constructs a knowledge base graph embedding module to extend the versatility of knowledge-based VQA models. By extracting core entities from images and text and performing sub-graph embedding, the accuracy of knowledge-based VQA models is improved.

PATTERN RECOGNITION (2021)

Article Computer Science, Artificial Intelligence

Joint embedding VQA model based on dynamic word vector

Zhiyang Ma et al.

Summary: This article introduces a joint embedding model based on dynamic word vector-N-KBSN model, which can better express semantic and grammatical differences compared to existing Visual Question Answering models based on static word vectors. Experimental results show that the accuracy of this model significantly improves.

PEERJ COMPUTER SCIENCE (2021)

Article Computer Science, Information Systems

Improving Visual Reasoning Through Semantic Representation

Wenfeng Zheng et al.

Summary: In visual reasoning, deep learning has greatly improved the accuracy of results. By introducing semantic representation, a higher-level representation, more accurate results can be obtained. This study lays the foundation for introducing different levels of knowledge representation into deep learning in the future.

IEEE ACCESS (2021)

Article Computer Science, Artificial Intelligence

ESIM: Edge Similarity for Screen Content Image Quality Assessment

Zhangkai Ni et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)