基于文献计量分析的视觉显著性评估研究综述

李和森; 黄奕文

doi:10.19554/j.cnki.1001-3563.2026.12.045

PDF(8080 KB)

包装工程（设计栏目） ›› 2026, Vol. 47 ›› Issue (12) : 509-521. DOI: 10.19554/j.cnki.1001-3563.2026.12.045

设计研讨

基于文献计量分析的视觉显著性评估研究综述

李和森^a, 黄奕文^a,b

作者信息 +

Review of Research on Visual Saliency Assessment Based on Bibliometric Analysis

LI Hesen^a, HUANG Yiwen^a,b

Author information +

文章历史 +

摘要

目的针对目前视觉显著性评估研究领域相关文献缺乏综合性梳理问题,系统分析了该领域研究现状,归纳了研究热点和趋势。方法以1992—2025年Web of Science数据库中与视觉显著性评估密切相关的高被引文献为样本,综合运用文献计量分析、因子分析、关键词共现分析、聚类分析等方法,探索了视觉显著性评估研究主题、研究脉络、知识结构框架。析出了显著性模型与视觉搜索、计算机视觉与深度学习、生物视觉机制与眼动控制、图像处理与质量评估、认知科学与注意机制等5个研究主题。经历了认知理论建构、统计建模、深度学习应用、多模态与Transformer融合等4个发展阶段。研究热点从早期的Eye Movement、Visual Attention等转向近年的Salient Project Detection与Multimodal Learning等前沿方向。建构了以“是什么-为什么-怎么办”为逻辑的视觉显著性评估研究知识框架。结论由研究主题和研究热点分析揭示了视觉显著性评估研究逐步从生物启发模型向数据驱动、多模态融合、轻量化模型建构等方向发展,发掘现有研究不足,并以此提出该领域未来的研究方向,为后续研究提供建议和借鉴。

Abstract

In view of the lack of comprehensive sorting of relevant literature in the current research field of visual saliency assessment, the work aims to systematically analyze the current status of research in this field and summarize the research hotspots and trends. Highly cited literature closely related to visual saliency assessment from 1992 to 2025 in the Web of Science database was selected as samples. Bibliometric analysis, factor analysis, keyword co-occurrence analysis, and cluster analysis were comprehensively employed to explore research topics, evolutionary paths, and knowledge structures. Five research topics were identified, including Saliency Models and Visual Search, Computer Vision and Deep Learning, Biological Visual Mechanisms and Eye Movement Control, Image Processing and Quality Assessment, Cognitive Science and Attention Mechanisms. Four developmental stages were observed, covering Cognitive Theory Construction, Statistical Modeling, Deep Learning Application, and Multimodal & Transformer Integration. Research hotspots evolved from early topics like Eye Movement and Visual Attention to recent cutting-edge directions such as Salient Project Detection and Multimodal Learning. A knowledge framework with the logic of "What-Why-How" was constructed for visual saliency assessment. The analysis of research topics and hotspots reveals that visual saliency assessment research is progressively shifting from biologically inspired models to data-driven, multimodal integration, and lightweight model construction. Existing research gaps are identified, and future directions are proposed to provide references for subsequent studies.

导出引用1

李和森, 黄奕文. 基于文献计量分析的视觉显著性评估研究综述[J]. 包装工程. 2026, 47(12): 509-521 https://doi.org/10.19554/j.cnki.1001-3563.2026.12.045

LI Hesen, HUANG Yiwen. Review of Research on Visual Saliency Assessment Based on Bibliometric Analysis[J]. Packaging Engineering. 2026, 47(12): 509-521 https://doi.org/10.19554/j.cnki.1001-3563.2026.12.045

中图分类号： TB472

参考文献

[1] XIE Y L, LU H C, YANG M H.Bayesian Saliency via Low and Mid Level Cues[J]. IEEE Transactions on Image Processing, 2013, 22(5): 1689-1698.
[2] ITTI L, KOCH C.A Saliency-Based Search Mechanism for Overt and Covert Shifts of Visual Attention[J]. Vision Research, 2000, 40(10-12): 1489-1506.
[3] ZHANG L, TONG M H, MARKS T K, et al.SUN: A Bayesian Framework for Saliency Using Natural Statistics[J]. Journal of Vision, 2008, 8(7): 32.
[4] TATLER B W.The Central Fixation Bias in Scene Viewing: Selecting an Optimal Viewing Position Independently of Motor Biases and Image Feature Distributions[J]. Journal of Vision, 2007, 7(14): 4.
[5] CHENG M M, ZHANG G X, MITRA N J, et al.Global Contrast Based Salient Region Detection[J]. IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37(3): 569-582.
[6] WANG Z, BOVIK A C, SHEIKH H R, SIMONCELLI E P.Image Quality Assessment: From Error Visibility to Structural Similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[7] BORJI A.Visual Saliency Based on Information Maximization between Global Context and Local Contrast[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(12): 2795-2806.
[8] ACHANTA R, SHAJI A, SMITH K, LUCCHI A, FUA P, SUSSTRUNK S.SLIC Superpixels Compared to State- of-the-Art Superpixel Methods[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282
[9] PERAZZI F, KRAHENBUHL P, PRITCH Y, HORNUNG A.Saliency Filters: Contrast Based Filtering for Salient Region Detection[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2012: 733-740.
[10] HE K M, ZHANG X Y, REN S Q, SUN J.Deep Residual Learning for Image Recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770-778.
[11] SIMONYAN K, ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[C]// 3rd International Conference on Learning Representations (ICLR 2015). San Diego, CA, USA: Computational and Biological Learning Society, 2015: 1-14.
[12] VASWANI A, SHAZEER N, PARMAR N, USZKOREIT J, JONES L, GOMEZ A N, KAISER L, POLOSUKHIN I.Attention Is All You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, CA, USA: Curran Associates, 2017: 6000-6010.
[13] YARBUS A L.Eye Movements During Perception of Complex Objects[M]. New York: Plenum Press, 1967: 171-196.
[14] ITTI L, KOCH C.Computational Modelling of Visual Attention[J]. Nature Reviews Neuroscience, 2001, 2(3): 194-203.
[15] BRUCE N D B. Features That Draw Visual Attention: An Information Theoretic Perspective[J]. Neurocomputing, 2005, 65-66: 125-133.
[16] WANG W, SHEN J, LING H.A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(7): 1531-1544.
[17] TREISMAN A M, GELADE G.A Feature-Integration Theory of Attention[J]. Cognitive Psychology, 1980, 12(1): 97-136.
[18] POSNER M I.Orienting of Attention[J]. Quarterly Journal of Experimental Psychology, 1980, 32(1): 3-25.
[19] ITTI L, BALDI P.A Principled Approach to Detecting Surprising Events in Video[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). San Diego: IEEE, 2005, 1: 631-637.
[20] BRUCE N D B, TSOTSOS J K. Saliency, Attention, and Visual Search: An Information Theoretic Approach[J]. Journal of Vision, 2009, 9(3): 5.
[21] ITTI L, BALDI P.Bayesian Surprise Attracts Human Attention[C]//Advances in Neural Information Processing Systems 19. Cambridge: MIT Press, 2005: 547-554.
[22] KÜMMERER M, WALLIS T S A, BETHGE M. DeepGaze II: Predicting Fixations from Deep Features over Time and Tasks[J]. Journal of Vision, 2017, 17(10): 1147.
[23] WANG W, SHEN J, SHAO L.Video Saliency Detection Using Spatiotemporal Cues[C]//Proceedings of the 2014 IEEE International Conference on Multimedia and Expo. Chengdu: IEEE, 2014: 1-6.
[24] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, WEISSENBORN D, ZHAI X, UNTERTHINER T, DEHGHANI M, MINDERER M, HEIGOLD G, GELLY S, USZKOREIT J, HOULSBY N.An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale[C]//Proceedings of the International Conference on Learning Representations (ICLR 2021). Virtual Event, Austria: OpenReview.net, 2021.
[25] GARFIELD E.From the Science of Science to Scientometrics: Visualizing the History of Science with HistCite Software[J]. Journal of Informetrics, 2009, 3(3): 173-179.
[26] SMALL H G, GRIFFITH B C.The Structure of Scientific Literatures I: Identifying and Graphing Specialties[J]. Science Studies, 1974, 4(1): 17-40.
[27] JIANG M, HUANG S, DUAN J, et al.SALICON: Saliency in Context[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 1072-1080.
[28] HORÉ A, ZIOU D.Image Quality Metrics: PSNR vs. SSIM[C]//Proceedings of the 2010 20th International Conference on Pattern Recognition. Istanbul: IEEE, 2010.
[29] LIU Y, CHEN X, WANG Z, et al.Deep Learning Methods for Medical Image Fusion: A Review[J]. Computers in Biology and Medicine, 2023, 160: 106959.
[30] CHEN L C, ZHU Y K, PAPANDREOU G, et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]// Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2018: 801-818.
[31] XIA Y, ZHANG D Q, KIM J, et al.Predicting Driver Attention in Critical Situations[C]// Proceedings of the Computer Vision-ACCV 2018. Cham: Springer, 2019.
[32] WANG L M, XIONG Y J, WANG Z, et al.Temporal Segment Networks: Towards Good Practices for Deep Action Recognition[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer, 2016.
[33] FRANKS I M, WEIGHTMAN A P, DORMAN G K, et al.The Use of Visual Search to Assess the Anticipation of Elite Soccer Goalkeepers: A Pilot Study[J]. Journal of Sports Sciences, 2020, 38(11/12): 1419-1425.
[34] TRANFIELD D, DENYER D, SMART P.Towards a Methodology for Developing Evidence-Informed Management Knowledge by Means of Systematic Review[J]. British Journal of Management, 2003, 14(3): 207-222.