Result diversification in image retrieval based on semantic distance

Lu, Wei; Luo, Mengqi; Zhang, Zhenyu; Zhang, Guobiao; Ding, Hui; Chen, Haihua; Chen, Jiangping

doi:10.1016/j.ins.2019.06.020

Cited by 11 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, when describing a certain type of household appliance, we would say that it is gorgeous, luxurious, noble, etc., and we will not use strong, fierce, and other words that are usually used for electromechanical products. It has been proven that the performance based on the WordNet semantic distance algorithm is better than other algorithms in the field of image recognition [ 65 ]. Then, we built the cobweb structure according to the semantic network associated with the design [ 66 ].…”

Section: Methodsmentioning

confidence: 99%

Intelligent Design of Product Forms Based on Design Cognitive Dynamics and a Cobweb Structure

Yang

Zhang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Design is a complex, iterative, and innovative process. By traditional methods, it is difficult for designers to have an integral priori design experience to fully explore a wide range of design solutions. Therefore, refined intelligent design has become an important trend in design research. More powerful design thinking is needed in intelligent design process. Combining cognitive dynamics and a cobweb structure, an intelligent design method is proposed to formalize the innovative design process. The excavation of the dynamic mechanism of the product evolution process during product development is necessary to predict next-generation multi-image product forms from a larger design space. First, different design thinking stimulates the information source and is obtained by analyzing the designers’ thinking process when designing and mining the dynamic mechanism behind it. Based on the nonlinear cognitive cobweb process proposed by Francisco and a natural cobweb structure, the product image cognitive cobweb model (PICCM) is constructed. Then, natural cobweb predation behavior is simulated using a stimulus information source to impact the PICCM. This process uses genetic algorithms to obtain numerous offspring forms, and the PICCM’s mechanical properties are the energy loss parameters in the impact information. Furthermore, feasible solutions are selected from intelligent design sketches by the product artificial form evaluation system based on designers’ cognition, and a new product image cognitive cobweb system is reconstructed. Finally, a case study demonstrates the efficiency and feasibility of the proposed approach.

show abstract

Section: Methodsmentioning

confidence: 99%

Intelligent Design of Product Forms Based on Design Cognitive Dynamics and a Cobweb Structure

Yang

Zhang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…To re-rank the search results, the new ranking score is calculated. In the diversification of search results, MMR (Carbonell and Goldstein, 1998), xQuAD (Santos et al , 2010) and DivScore (Lu et al , 2019) are used to calculate the ranking score, and DivScore is selected. Due to the semantic labels of the Dunhuang murals being special and in Chinese, the normal similarity calculation methods are inapplicable.…”

Section: The Fine-tuned Cnn and Ontology Semantic Distance–based Mobi...mentioning

confidence: 99%

“…CR@X (Cluster-Recall at X, X = 5, 10, 20, 30 or 40) (Ionescu et al , 2014; Lu et al , 2019) is used to measure the performance of diversification in image retrieval. CR@X represents the number of different topics of the top X retrieved images in total relevant topics, and it assesses how many different clusters from the ground truth are represented among the top X results (Ionescu et al , 2014).…”

Section: The Fine-tuned Cnn and Ontology Semantic Distance–based Mobi...mentioning

confidence: 99%

Constructing a mobile visual search framework for Dunhuang murals based on fine-tuned CNN and ontology semantic distance

Zeng

Sun

et al. 2022

View full text Add to dashboard Cite

Purpose Dunhuang murals are rich in cultural and artistic value. The purpose of this paper is to construct a novel mobile visual search (MVS) framework for Dunhuang murals, enabling users to efficiently search for similar, relevant and diversified images. Design/methodology/approach The convolutional neural network (CNN) model is fine-tuned in the data set of Dunhuang murals. Image features are extracted through the fine-tuned CNN model, and the similarities between different candidate images and the query image are calculated by the dot product. Then, the candidate images are sorted by similarity, and semantic labels are extracted from the most similar image. Ontology semantic distance (OSD) is proposed to match relevant images using semantic labels. Furthermore, the improved DivScore is introduced to diversify search results. Findings The results illustrate that the fine-tuned ResNet152 is the best choice to search for similar images at the visual feature level, and OSD is the effective method to search for the relevant images at the semantic level. After re-ranking based on DivScore, the diversification of search results is improved. Originality/value This study collects and builds the Dunhuang mural data set and proposes an effective MVS framework for Dunhuang murals to protect and inherit Dunhuang cultural heritage. Similar, relevant and diversified Dunhuang murals are searched to meet different demands.

show abstract

“…A dynamic generative model for recommending influence logs based on diffusion of topic influences over communities in social networks has been proposed. Lu et al 32 have used the semantic distance for diversification of the recommendations in a scenario of image retrieval. The approach uses image context information such as the description of images, the tags, captions, for diversification of results.…”

Section: Related Workmentioning

confidence: 99%

QGMS: A query growth model for personalization and diversification of semantic search based on differential ontology semantics using artificial intelligence

Deepak

Santhanavijayan

2022

Computational Intelligence

View full text Add to dashboard Cite

The inclusion of collective intelligence through a semantic focused affective computing can incorporate intelligence to web search and ensure its compliance with the Web 3.0. In this article, a query growth model with inclusive and exclusive ontology semantics has been proposed for diversification of query recommendation in semantic search. The ontology semantics include query augmented ontology generation, agent‐driven attractor‐distractor generation to yield a merged ontology, and endowment of merged ontology by using hybridization of a series of knowledge bases. The strategy further includes the formulation of a semantic network and entity leveraging based on description logics (DLs) to improve the quality of query recommendation. A novel hierarchical entropy cognitive similarity covariance model has been proposed for yielding the most appropriate recommendable query words. The strategy also encompasses the user‐click information for capturing the current user intents to improve the quality queries recommended in semantic search, and thereby incorporate personalization. Experimentations are conducted for the CHiC dataset and the Spring 2006 Query Log dataset and an average accuracy of 96.27% and 92.01%, respectively, with a very low false discovery rate of 0.06 and 0.1 for the respective datasets.

show abstract

Result diversification in image retrieval based on semantic distance

Cited by 11 publications

References 21 publications

Intelligent Design of Product Forms Based on Design Cognitive Dynamics and a Cobweb Structure

Intelligent Design of Product Forms Based on Design Cognitive Dynamics and a Cobweb Structure

Constructing a mobile visual search framework for Dunhuang murals based on fine-tuned CNN and ontology semantic distance

QGMS: A query growth model for personalization and diversification of semantic search based on differential ontology semantics using artificial intelligence

Contact Info

Product

Resources

About