2024 Vol.7 Jun.N03

• Title: Saliency objection ranking based on boundary-aware
• Name: Yiping HU
• Company: School of Artificial Intelligence,Hebei University of Technology,Tianjin 300401,China
• Abstract:

   Salient Object Ranking aims to simulate human visual perception to locate and rank multiple salient objects in a complex scene, providing support for downstream tasks related to salient objects. Because the existing methods cannot accurately rank saliency objects and blurred edges of significant targets.To address these problems, this paper proposes a saliency ranking algorithm based on boundary awareness. By integrating a boundary attention unit in Transformer, fine boundary details are extracted to delineate the boundaries of salient objects for more accurate prediction of salient objects. Experiments show that the proposed algorithm achieves advanced performance compared with the mainstream algorithms in the aspect of salient target prediction.

  
  

• Keyword: saliency objection ranking; transformer; boundary perception
• DOI: 10.12250/jpciams2024090615
• Citation form: Yiping HU.Saliency objection ranking based on boundary-aware[J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.66-68

[1] Kajiura N, Kosugi S, Wang X. Self-play reinforcement learning for fast image retargeting[C]. ACM International Conference on Multimedia, New York, USA: ACM, 2020: 1755−1763.

[2] Yuzhen N, Shuai Z, Zhishan W. Image retargeting quality assessment based on registration confidence measure and noticeability-based pooling[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(3): 972-985.

[3] Kalash M, Amirul Islam M, Neil Bruce D. Relative saliency and ranking: models, metrics, data and benchmarks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 204-219.

[4] Thevenaz P, Thierry B, Unser M. Interpolation revisited medical images application[J]. IEEE Transactions on Medical Imaging, 2000, 19(7): 739-758.

[5] Suresha D, Prakash H. Single picture super resolution of natural images using n-neighbor adaptive bilinear interpolation and absolute asymmetry based wavelet hard thresholding[J]. International Conference on Applied and Theoretical Computing and Communication Technology, Bengaluru, Piscataway, 2016: 387-393.

[6] Feng L, Michael G. Video retargeting: automating pan and scan[C]. ACM International Conference on Multimedia, Santa Barbara, CA, USA:ACM, 2006: 23-27.

[7] Avidan S, Shamir A. A. seam carving for content-aware image resizing[J]. ACM Transactions on Graphics, 2007, 26(3): 10-18.

[8] Yan B, Yuan B, Yang B. Effective video retargeting with jittery assessment[J]. IEEE Transactions on Multimedia, 2013, 16(1): 272–277

[9] Shih-Syun L, I-Cheng Y, Chaohung L. Patch-based image warping for content-aware retargeting[J]. IEEE Transactions on Multimedia, 2012, 15(2): 359–368.

[10] Yanwen G, Feng L; Jian S. Image retargeting using mesh parametrization[J]. IEEE Transactions on Multimedia, 2009, 11(5): 856–867.

[11] Panozzo D, Weber O, Sorkine O. Robust image retargeting via axis-aligned deformation[C]. Computer Graphics Forum. Oxford, UK: Blackwell Publishing Ltd, 2012: 229–236.

[12] Yan B, Ke L, Xiaochu Y. Seam searching-based pixel fusion for image retargeting[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 25(1): 15–23.

[13] Ya Z, Zhibo C, Weiping L. Multi-operator media retargeting[J]. ACM Transactions on Graphics, 2009, 28(3): 1-11.

[14] Donghyeon C, Jinsun P, Tae-Hyun O. Weakly and self-supervised learning for content-aware deep image retargeting[C]. IEEE International Conference on Computer Vision. Piscataway, NJ: IEEE, 2017: 4558-4567.

[15] Danon D, Moab A, Daniel C. Image resizing by reconstruction from deep features[J] Computational Visual Media, 2021, 27(7): 453-466.

[16] Weimin T, Yan B, Chumin L. Cycle-IR: deep cyclic image retargeting[J]. IEEE Transactions on Multimedia, 2019, 22(7): 1730-1743.

[17] Indra Deep M, Shanmuganathan R. DCIL: deep contextual internal learning for image restoration and image retargeting[C]. IEEE Winter Conference on Applications of Computer Vision (WACV), Los Alamitos, USA: IEEE Computer Soc, 2020: 2366-2375.

[18] Zhou Y, Chen Z, Li W. Weakly Supervised Reinforced Multi-Operator Image Retargeting[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(1): 126-139.

[19] Avishek S, Jianbo J, Xianghua X. Inferring attention shift ranks of objects for image saliency[C]. IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2020: 12133−12143.

[20] Rubinstein M, Gutierrez D, Sorkine O. A comparative study of image retargeting[C]. ACM Transactions on Graphics, 2010, 29(6): 1−10.