mlsanityData to 7 Oct 2026

Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval

arXiv 2203.08615 ↗First posted 16 Mar 2022cs.IR cs.AIcited by 33

Not on the map. Why?

Abstract (arXiv)

Cross-media retrieval of scientific and technological information is one of the important tasks in the cross-media study. Cross-media scientific and technological information retrieval obtain target information from massive multi-source and heterogeneous scientific and technological resources, which helps to design applications that meet users' needs, including scientific and technological information recommendation, personalized scientific and technological information retrieval, etc. The core of cross-media retrieval is to learn a common subspace, so that data from different media can be directly compared with each other after being mapped into this subspace. In subspace learning, existing methods often focus on modeling the discrimination of intra-media data and the invariance of inter-media data after mapping; however, they ignore the semantic consistency of inter-media data before and after mapping and media discrimination of intra-semantics data, which limit the result of cross-media retrieval. In light of this, we propose a scientific and technological information oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval method (SMCR) to find an effective common subspace. Specifically, SMCR minimizes the loss of inter-media semantic consistency in addition to modeling intra-media semantic discrimination, to preserve semantic similarity before and after mapping. Furthermore, SMCR constructs a basic feature mapping network and a refined feature mapping network to jointly minimize the media discriminative loss within semantics, so as to enhance the feature mapping network's ability to confuse the media discriminant network. Experimental results on two datasets demonstrate that the proposed SMCR outperforms state-of-the-art methods in cross-media retrieval.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 10 of its 44 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

10 of 44 references.

References · 10

  1. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  2. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  3. 2014Deep metric learning using Triplet networkcited by 421
  4. 2017Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networkscited by 88
  5. 2021Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognitioncited by 39
  6. 2019Transfer Learning with Dynamic Adversarial Adaptation Networkcited by 37
  7. 2018Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrievalcited by 29
  8. 2019Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networkscited by 27
  9. 2017An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challengescited by 21
  10. 2015Modality-dependent Cross-media Retrievalcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 24; 2023: 9.

33 papers.

Sort:

  1. 2022Chinese Word Sense Embedding with SememeWSD and Synonym Setcited by 2
  2. 2022Semantic Similarity Computing for Scientific Academic Conferences fused with domain featurescited by 1
  3. 2023Dynamic Fair Federated Learning Based on Reinforcement Learningcited by 1
  4. 2022An Intellectual Property Entity Recognition Method Based on Transformer and Technological Word Informationcited by 0
  5. 2022Prediction Algorithm for Heat Demand of Science and Technology Topics Based on Time Convolution Networkcited by 0
  6. 2022Research Scholar Interest Mining Method based on Load Centralitycited by 0
  7. 2022Academic Resource Text Level Multi-label Classification based on Attentioncited by 0
  8. 2022Web Page Content Extraction Based on Multi-feature Fusioncited by 0
  9. 2022Cross-Media Scientific Research Achievements Retrieval Based on Deep Language Modelcited by 0
  10. 2022Research topic trend prediction of scientific papers based on spatial enhancement and dynamic graph convolution networkcited by 0
  11. 2022An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific paperscited by 0
  12. 2022Scientific and Technological Text Knowledge Extraction Method of based on Word Mixing and GRUcited by 0
21 more
  1. 2022Accurate Portraits of Scientific Resources and Knowledge Service Componentscited by 0
  2. 2022Research on Cross-media Science and Technology Information Data Retrievalcited by 0
  3. 2022Knowledge Graph and Accurate Portrait Construction of Scientific and Technological Academic Conferencescited by 0
  4. 2022Retrieval of Scientific and Technological Resources for Experts and Scholarscited by 0
  5. 2022Research on Intellectual Property Resource Profile and Evolution Lawcited by 0
  6. 2022Research on Domain Information Mining and Theme Evolution of Scientific Paperscited by 0
  7. 2022GRAPHYP: A Scientific Knowledge Graph with Manifold Subnetworks of Communities. Detection of Scholarly Disputes in Adversarial Information Routescited by 0
  8. 2022Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexiconcited by 0
  9. 2022A sentiment analysis model for car review texts based on adversarial training and whole word mask BERTcited by 0
  10. 2022Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecastingcited by 0
  11. 2022A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Networkcited by 0
  12. 2022Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTacited by 0
  13. 2022Adaptive Dual Channel Convolution Hypergraph Representation Learning for Technological Intellectual Propertycited by 0
  14. 2023Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraintscited by 0
  15. 2023Reinforcement Federated Learning Method Based on Adaptive OPTICS Clusteringcited by 0
  16. 2023Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Networkcited by 0
  17. 2023Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusioncited by 0
  18. 2023Federated Topic Model and Model Pruning Based on Variational Autoencodercited by 0
  19. 2023Epidemic Decision-making System Based Federated Reinforcement Learningcited by 0
  20. 2023Relation Extraction Model Based on Semantic Enhancement Mechanismcited by 0
  21. 2023Topic model based on co-occurrence word networks for unbalanced short text datasetscited by 0