Semantic Scholar Academic Search

{
  "q": "transformer attention mechanisms",
  "recency": "month",
  "per_page": 10
}

{
  "data": [
    {
      "id": "1244c83428612e48f4d2dcb8a9d0032b21dcc616",
      "url": "https://www.semanticscholar.org/paper/1244c83428612e48f4d2dcb8a9d0032b21dcc616",
      "year": 2025,
      "title": "Comparing Eye-gaze and Transformer Attention Mechanisms in Reading Tasks",
      "types": [],
      "fields": [],
      "authors": [
        "Maria Mouratidi",
        "M. Poesio"
      ],
      "journal": "Proceedings of the First International Workshop on Gaze Data and Natural Language Processing",
      "pdf_url": null,
      "abstract": "As transformers become increasingly prevalent in NLP research, evaluating their cognitive alignment with human language processing has become essential for validating them as models of human language. This study compares eye-gaze patterns in human reading with transformer attention using different a",
      "citations": 0,
      "influential_citations": 0
    },
    {
      "id": "e22b121a31951480413460f0a2a0e9bf875997ce",
      "url": "https://www.semanticscholar.org/paper/e22b121a31951480413460f0a2a0e9bf875997ce",
      "year": 2025,
      "title": "TransCCNet: enhancing global contextual learning in multispectral remote sensing images through criss-cross and transformer attention mechanisms",
      "types": [
        "JournalArticle"
      ],
      "fields": [
        "Engineering"
      ],
      "authors": [
        "I. Ulku"
      ],
      "journal": "Journal of Applied Remote Sensing",
      "pdf_url": null,
      "abstract": "Abstract. Although semantic segmentation models excel in a wide range of vision tasks, they pose significant challenges for multispectral remote sensing images due to high inter-class similarity, intra-class variability, and occlusions. This work introduces a transformer-based criss-cross network (T",
      "citations": 0,
      "influential_citations": 0
    },
    {
      "id": "d2b8b0c52388401ead8bbe7b1eb4445e7f7d2c0f",
      "url": "https://www.semanticscholar.org/paper/d2b8b0c52388401ead8bbe7b1eb4445e7f7d2c0f",
      "year": 2026,
      "title": "Enhancing Transformer Attention Mechanisms for Knowledge Retention in Fine-Tuned Large Language Models",
      "types": [
        "JournalArticle"
      ],
      "fields": [],
      "authors": [
        "Navya Veginati"
      ],
      "journal": "International Journal of Scientific Research in Science and Technology",
      "pdf_url": null,
      "abstract": "Large language models based on transformers have shown outstanding performance in several natural language processing tasks. But, when such models are fine-tuned, catastrophic forgetting is likely to occur causing one to forget the knowledge that has been learned before. This paper suggests a better",
      "citations": 0,
      "influential_citations": 0
    },
    {
      "id": "95f709a4bc28a976fed21784c60cb0b0c1d37a34",
      "url": "https://www.semanticscholar.org/paper/95f709a4bc28a976fed21784c60cb0b0c1d37a34",
      "year": 2022,
      "title": "Applications of Transformer Attention Mechanisms in Information Security: Current Trends and Prospects",
      "types": [
        "Conference",
        "Review"
      ],
      "fields": [],
      "authors": [
        "M. Vubangsi",
        "Sarumi Usman Abidemi",
        "Olukayode Akanni",
        "A. Mubarak",
        "Fadi M. Al-Turjman"
      ],
      "journal": "2022 International Conference on Artificial Intelligence of Things and Crowdsensing (AIoTCs)",
      "pdf_url": null,
      "abstract": "In this work, we present a comprehensive survey on applications of the most recent transformer architecture based on attention in information security. Our review reveals three primary areas of application: Intrusion detection, Anomaly Detection and Malware Detection. We have presented an overview o",
      "citations": 2,
      "influential_citations": 0
    },
    {
      "id": "4566d113008951eba701affe2b6d47d1eb2eb687",
      "url": "https://www.semanticscholar.org/paper/4566d113008951eba701affe2b6d47d1eb2eb687",
      "year": 2024,
      "title": "Enhancing stock price prediction using GANs and transformer-based attention mechanisms",
      "types": [
        "JournalArticle"
      ],
      "fields": [],
      "authors": [
        "Siyi Li",
        "Sijie Xu"
      ],
      "journal": "Empirical Economics",
      "pdf_url": null,
      "abstract": null,
      "citations": 54,
      "influential_citations": 1
    },
    {
      "id": "3520e04fc0e2d34e8e1759ff0c40ac8ee80ba7c4",
      "url": "https://www.semanticscholar.org/paper/3520e04fc0e2d34e8e1759ff0c40ac8ee80ba7c4",
      "year": 2024,
      "title": "Integrating self-attention mechanisms in deep learning: A novel dual-head ensemble transformer with its application to bearing fault diagnosis",
      "types": [
        "JournalArticle"
      ],
      "fields": [
        "Computer Science"
      ],
      "authors": [
        "Qing Snyder",
        "Qingtang Jiang",
        "E. Tripp"
      ],
      "journal": "Signal Process.",
      "pdf_url": null,
      "abstract": null,
      "citations": 65,
      "influential_citations": 1
    },
    {
      "id": "6d9d1c7827257fe3b3fe0aabfb5f18d883c70b65",
      "url": "https://www.semanticscholar.org/paper/6d9d1c7827257fe3b3fe0aabfb5f18d883c70b65",
      "year": 2024,
      "title": "Crack Detection, Classification, and Segmentation on Road Pavement Material Using Multi-Scale Feature Aggregation and Transformer-Based Attention Mechanisms",
      "types": [
        "JournalArticle"
      ],
      "fields": [],
      "authors": [
        "Arselan Ashraf",
        "A. Sophian",
        "Ali Aryo Bawono"
      ],
      "journal": "Construction Materials",
      "pdf_url": "https://doi.org/10.3390/constrmater4040036",
      "abstract": "This paper introduces a novel approach to pavement material crack detection, classification, and segmentation using advanced deep learning techniques, including multi-scale feature aggregation and transformer-based attention mechanisms. The proposed methodology significantly enhances the model’s abi",
      "citations": 17,
      "influential_citations": 0
    },
    {
      "id": "49ee175d5901febdf0463829d78a810a7090ae46",
      "url": "https://www.semanticscholar.org/paper/49ee175d5901febdf0463829d78a810a7090ae46",
      "year": 2023,
      "title": "Transformer Architecture and Attention Mechanisms in Genome Data Analysis: A Comprehensive Review",
      "types": [
        "Review",
        "JournalArticle"
      ],
      "fields": [
        "Medicine"
      ],
      "authors": [
        "Sanghyuk Roy Choi",
        "Minhyeok Lee"
      ],
      "journal": "Biology",
      "pdf_url": "https://www.mdpi.com/2079-7737/12/7/1033/pdf?version=1690007847",
      "abstract": "Simple Summary The rapidly advancing field of deep learning, specifically transformer-based architectures and attention mechanisms, has found substantial applicability in bioinformatics and genome data analysis. Given the analogous nature of genome sequences to language texts, these techniques initi",
      "citations": 194,
      "influential_citations": 8
    },
    {
      "id": "c8a544d0463e16cab475c8365f27b618d93bbf77",
      "url": "https://www.semanticscholar.org/paper/c8a544d0463e16cab475c8365f27b618d93bbf77",
      "year": 2025,
      "title": "Research on sentiment analysis model improved based on Transformer attention mechanism",
      "types": [
        "Book",
        "Conference",
        "Review"
      ],
      "fields": [],
      "authors": [
        "Qinzi Ji"
      ],
      "journal": "Proceedings of the 2025 International Conference on Simulation, Modeling and Big Data",
      "pdf_url": null,
      "abstract": "In response to the limitations of traditional sentiment analysis models, this paper proposes an improved sentiment analysis model based on Transformer attention mechanism. This model enhances contextual semantic modeling capability by optimizing self attention and multi head attention mechanisms; In",
      "citations": 0,
      "influential_citations": 0
    },
    {
      "id": "005b128b1c74db706800a1581f33ea02fc5550b7",
      "url": "https://www.semanticscholar.org/paper/005b128b1c74db706800a1581f33ea02fc5550b7",
      "year": 2025,
      "title": "Spiking Vision Transformer with Saccadic Attention",
      "types": [
        "JournalArticle"
      ],
      "fields": [
        "Computer Science"
      ],
      "authors": [
        "Shuai Wang",
        "Malu Zhang",
        "Dehao Zhang",
        "A. Belatreche",
        "Yichen Xiao",
        "Yu Liang",
        "Yimeng Shan",
        "Qian Sun",
        "Enqi Zhang",
        "Yang Yang"
      ],
      "journal": "ArXiv",
      "pdf_url": null,
      "abstract": "The combination of Spiking Neural Networks (SNNs) and Vision Transformers (ViTs) holds potential for achieving both energy efficiency and high performance, particularly suitable for edge vision applications. However, a significant performance gap still exists between SNN-based ViTs and their ANN cou",
      "citations": 32,
      "influential_citations": 1
    }
  ],
  "count": 10,
  "query": "transformer attention mechanisms",
  "source": "semantic_scholar",
  "success": true,
  "elapsed_ms": 3524
}

{
  "type": "json"
}