Multi-level cross-modal attention guided DIBR 3D image watermarking
For depth-image-based rendering (DIBR) 3D images, both center and synthesized virtual views are subject to illegal distribution during transmission. To address the issue of copyright protection of DIBR 3D images, we propose a multi-level cross-modal attention guided network (MCANet) for 3D image wat...
Saved in:
| Published in | Journal of visual communication and image representation Vol. 109; p. 104455 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Inc
01.06.2025
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | For depth-image-based rendering (DIBR) 3D images, both center and synthesized virtual views are subject to illegal distribution during transmission. To address the issue of copyright protection of DIBR 3D images, we propose a multi-level cross-modal attention guided network (MCANet) for 3D image watermarking. To optimize the watermark embedding process, the watermark adjustment module (WAM) is designed to extract cross-modal information at different scales, thereby calculating 3D image attention to adjust the watermark distribution. Furthermore, the nested dual output U-net (NDOU) is devised to enhance the compensatory capability of the skip connections, thus providing an effective global feature to the up-sampling process for high image quality. Compared to state-of-the-art (SOTA) 3D image watermarking methods, the proposed watermarking model shows superior performance in terms of robustness and imperceptibility. |
|---|---|
| AbstractList | For depth-image-based rendering (DIBR) 3D images, both center and synthesized virtual views are subject to illegal distribution during transmission. To address the issue of copyright protection of DIBR 3D images, we propose a multi-level cross-modal attention guided network (MCANet) for 3D image watermarking. To optimize the watermark embedding process, the watermark adjustment module (WAM) is designed to extract cross-modal information at different scales, thereby calculating 3D image attention to adjust the watermark distribution. Furthermore, the nested dual output U-net (NDOU) is devised to enhance the compensatory capability of the skip connections, thus providing an effective global feature to the up-sampling process for high image quality. Compared to state-of-the-art (SOTA) 3D image watermarking methods, the proposed watermarking model shows superior performance in terms of robustness and imperceptibility. |
| ArticleNumber | 104455 |
| Author | Huang, Jiangtao He, Zhouyan Chen, Qingmo Wang, Zhang Luo, Ting |
| Author_xml | – sequence: 1 givenname: Qingmo surname: Chen fullname: Chen, Qingmo organization: College of Science and Technology, Ningbo University, Ningbo 315212, China – sequence: 2 givenname: Zhang surname: Wang fullname: Wang, Zhang email: wangzhang@nbu.edu.cn organization: College of Science and Technology, Ningbo University, Ningbo 315212, China – sequence: 3 givenname: Zhouyan surname: He fullname: He, Zhouyan organization: College of Science and Technology, Ningbo University, Ningbo 315212, China – sequence: 4 givenname: Ting surname: Luo fullname: Luo, Ting organization: College of Science and Technology, Ningbo University, Ningbo 315212, China – sequence: 5 givenname: Jiangtao surname: Huang fullname: Huang, Jiangtao organization: College of Science and Technology, Ningbo University, Ningbo 315212, China |
| BookMark | eNp9j8tOwzAQRb0oEm3hC9j4B1L8TMmCBbQ8KhUhIVhbjmdcOaQJctwi_h63Zc1iNKMr3dE5EzLq-g4JueJsxhkvr5tZs3chzgQTOidKaT0i43zMCymYPCeTYWgYY7KSakwWL7s2haLFPbbUxX4Yim0PtqU2JexS6Du62QVAoMvV_RuVSxq2doP02yaMWxs_Q7e5IGfetgNe_u0p-Xh8eF88F-vXp9Xibl04fiNTUYP3c9CyrMC5UgmhrVaO-Rp4WUOtPJQKeCUYCi3zWFvlvHLAgSkvlZwSefp75IzozVfMNPHHcGYO7qYxR3dzcDcn99y6PbUwo-0DRjO4gJ1DCBFdMtCHf_u__BxnxA |
| Cites_doi | 10.1016/j.eswa.2019.113157 10.1109/TMM.2022.3149641 10.1016/j.image.2020.115935 10.1016/j.compbiomed.2022.106387 10.1016/j.jvcir.2023.103794 10.1088/1361-6560/ad40f6 10.1007/978-3-319-24574-4_28 10.1145/1015706.1015766 10.1016/j.neucom.2020.09.062 10.1007/s10489-022-04416-0 10.1109/TBC.2012.2206851 10.1609/aaai.v34i01.5463 10.1145/3656476 10.1145/2957751 10.1109/ACCESS.2020.2994966 10.1007/s11042-017-4678-x 10.1016/j.patcog.2023.109728 10.1109/TIP.2022.3205747 10.1016/j.inffus.2023.01.016 10.1007/s11042-015-3028-0 |
| ContentType | Journal Article |
| Copyright | 2025 |
| Copyright_xml | – notice: 2025 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.jvcir.2025.104455 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Journalism & Communications Engineering |
| ExternalDocumentID | 10_1016_j_jvcir_2025_104455 S1047320325000690 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29L 4.4 457 4G. 53G 5GY 5VS 7-5 71M 8P~ 9JN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYFN AAYWO ABBOA ABFNM ABJNI ABMAC ABWVN ABXDB ACDAQ ACGFS ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADFGL ADJOM ADMHC ADMUD ADNMO ADTZH AEBSH AECPX AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APXCP ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC BNPGV CAG COF CS3 DM4 DU5 EBS EFBJH EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG5 LX9 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SSH SST SSV SSZ T5K WH7 WUQ XPP YQT ZMT ZU3 ~G- AAYXX CITATION |
| ID | FETCH-LOGICAL-c183t-bdff7d5369dcc64225a54c0fbd16bdb4fd64d1920e253e25aa96bd9cd1d04f343 |
| IEDL.DBID | .~1 |
| ISSN | 1047-3203 |
| IngestDate | Tue Jul 01 04:45:29 EDT 2025 Sat Jun 21 16:54:16 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Cross-modal Attention Transformer Watermarking Depth-image-based rendering (DIBR) 3D image |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c183t-bdff7d5369dcc64225a54c0fbd16bdb4fd64d1920e253e25aa96bd9cd1d04f343 |
| ParticipantIDs | crossref_primary_10_1016_j_jvcir_2025_104455 elsevier_sciencedirect_doi_10_1016_j_jvcir_2025_104455 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | June 2025 2025-06-00 |
| PublicationDateYYYYMMDD | 2025-06-01 |
| PublicationDate_xml | – month: 06 year: 2025 text: June 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Journal of visual communication and image representation |
| PublicationYear | 2025 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Luo, Wu, He (b0080) 2024 He, Zhang, Ren (b0150) 2016 Hirschmuller, Scharstein (b0170) 2007 Kingma D P. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. Rana, Sur (b0020) 2016; 12 Ahmadi, Norouzi, Karimi (b0060) 2020; 146 Hashimoto, Ote (b0090) 2024; 69 Halici, Alatan (b0120) 2009 Cui, Wang, Niu (b0140) 2017; 76 Chen, Zhao (b0010) 2020; 87 Zhou, Yue, Fang (b0035) 2023; 94 Song, Song, Yang (b0155) 2022; 31 Fang, Jia, Zhou (b0115) 2022; 25 Nam, Kim, Mun (b0130) 2018; 77 Zitnick, Kang, Uyttendaele (b0165) 2004; 23 Zhu, Kaplan, Johnson Hidden (b0055) 2018 Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer International Publishing, pp. 234-241, 2015. Zhang, Chen, Liao (b0105) 2021; 44 He, He, Xu (b0015) 2023; 92 Sun, Zhang, Wang (b0045) 2021 Nam, Mun, Ahn (b0030) 2020; 8 Zhang H, Wang H, Cao Y, et al. Robust data hiding using inverse gradient attention. arXiv preprint arXiv:2011.10850, 2020. Song, Lichtenberg, Xiao (b0160) 2015 Sun, Ren, Yin (b0050) 2023 Chen, Li, Zhang (b0100) 2023; 142 Huang, Luo, Li (b0075) 2023; 72 Hu, Shen, Sun (b0145) 2018 Gao, Su, Wang (b0040) 2024; 20 Zhang, Niu, Shangguan (b0095) 2023; 152 Pang, Wang, Cao (b0110) 2023; 53 Yu (b0065) 2020; 34 Fehn (b0175) 2004; 5291 Lee, Lee, Lee (b0125) 2011 Tian, Zhang, Zou (b0005) 2021; 423 Kim, Lee, Oh (b0025) 2012; 58 Etoom, Al-Haj (b0135) 2017 Pang (10.1016/j.jvcir.2025.104455_b0110) 2023; 53 Hirschmuller (10.1016/j.jvcir.2025.104455_b0170) 2007 Tian (10.1016/j.jvcir.2025.104455_b0005) 2021; 423 10.1016/j.jvcir.2025.104455_b0070 Etoom (10.1016/j.jvcir.2025.104455_b0135) 2017 Zhou (10.1016/j.jvcir.2025.104455_b0035) 2023; 94 Sun (10.1016/j.jvcir.2025.104455_b0050) 2023 Hashimoto (10.1016/j.jvcir.2025.104455_b0090) 2024; 69 Halici (10.1016/j.jvcir.2025.104455_b0120) 2009 Song (10.1016/j.jvcir.2025.104455_b0155) 2022; 31 He (10.1016/j.jvcir.2025.104455_b0150) 2016 Fehn (10.1016/j.jvcir.2025.104455_b0175) 2004; 5291 Zhu (10.1016/j.jvcir.2025.104455_b0055) 2018 Ahmadi (10.1016/j.jvcir.2025.104455_b0060) 2020; 146 Hu (10.1016/j.jvcir.2025.104455_b0145) 2018 Chen (10.1016/j.jvcir.2025.104455_b0100) 2023; 142 Song (10.1016/j.jvcir.2025.104455_b0160) 2015 Rana (10.1016/j.jvcir.2025.104455_b0020) 2016; 12 Nam (10.1016/j.jvcir.2025.104455_b0030) 2020; 8 Huang (10.1016/j.jvcir.2025.104455_b0075) 2023; 72 Chen (10.1016/j.jvcir.2025.104455_b0010) 2020; 87 Kim (10.1016/j.jvcir.2025.104455_b0025) 2012; 58 Gao (10.1016/j.jvcir.2025.104455_b0040) 2024; 20 Luo (10.1016/j.jvcir.2025.104455_b0080) 2024 10.1016/j.jvcir.2025.104455_b0180 10.1016/j.jvcir.2025.104455_b0085 Lee (10.1016/j.jvcir.2025.104455_b0125) 2011 Zhang (10.1016/j.jvcir.2025.104455_b0095) 2023; 152 Nam (10.1016/j.jvcir.2025.104455_b0130) 2018; 77 He (10.1016/j.jvcir.2025.104455_b0015) 2023; 92 Sun (10.1016/j.jvcir.2025.104455_b0045) 2021 Zhang (10.1016/j.jvcir.2025.104455_b0105) 2021; 44 Fang (10.1016/j.jvcir.2025.104455_b0115) 2022; 25 Cui (10.1016/j.jvcir.2025.104455_b0140) 2017; 76 Zitnick (10.1016/j.jvcir.2025.104455_b0165) 2004; 23 Yu (10.1016/j.jvcir.2025.104455_b0065) 2020; 34 |
| References_xml | – volume: 53 start-page: 17391 year: 2023 end-page: 17410 ident: b0110 article-title: Pairwise open-sourced dataset protection based on adaptive blind watermarking publication-title: Appl. Intell. – volume: 31 start-page: 6124 year: 2022 end-page: 6138 ident: b0155 article-title: Improving RGB-D salient object detection via modality-aware decoder publication-title: IEEE Trans. Image Process. – volume: 5291 start-page: 93 year: 2004 end-page: 104 ident: b0175 article-title: Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV publication-title: Stereoscopic Displays and Virtual Reality Systems – start-page: 1407 year: 2021 end-page: 1417 ident: b0045 article-title: Deep RGB-D saliency detection with depth-sensitive attention and automatic multi-modal fusion publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 12 start-page: 1 year: 2016 end-page: 23 ident: b0020 article-title: Depth-based view-invariant blind 3D image watermarking publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) – year: 2023 ident: b0050 article-title: CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection publication-title: IEEE Trans. Multimedia – volume: 146 year: 2020 ident: b0060 article-title: ReDMark: Framework for residual diffusion watermarking based on deep networks publication-title: Expert Syst. Appl. – volume: 77 start-page: 7811 year: 2018 end-page: 7850 ident: b0130 article-title: A SIFT features based blind watermarking for DIBR 3D images publication-title: Multimed. Tools Appl. – volume: 25 start-page: 2648 year: 2022 end-page: 2660 ident: b0115 article-title: Encoded feature enhancement in watermarking network for distortion in real scenes publication-title: IEEE Trans. Multimedia – volume: 76 start-page: 649 year: 2017 end-page: 677 ident: b0140 article-title: A novel watermarking for DIBR 3D images with geometric rectification based on feature points publication-title: Multimed. Tools Appl. – volume: 34 start-page: 1120 year: 2020 end-page: 1128 ident: b0065 article-title: Attention based data hiding with generative adversarial networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence – volume: 423 start-page: 158 year: 2021 end-page: 178 ident: b0005 article-title: Quality assessment of DIBR-synthesized views: An overview publication-title: Neurocomputing – volume: 87 year: 2020 ident: b0010 article-title: A robust blind watermarking algorithm for depth-image-based rendering 3D images publication-title: Signal Process. Image Commun. – volume: 152 year: 2023 ident: b0095 article-title: A novel denoising method for CT images based on U-net and multi-attention publication-title: Comput. Biol. Med. – volume: 142 year: 2023 ident: b0100 article-title: Rethinking the unpretentious U-net for medical ultrasound image segmentation publication-title: Pattern Recogn. – volume: 58 start-page: 533 year: 2012 end-page: 543 ident: b0025 article-title: Robust DT-CWT watermarking for DIBR 3D images publication-title: IEEE Trans. Broadcast. – volume: 20 start-page: 1 year: 2024 end-page: 24 ident: b0040 article-title: Heterogeneous Fusion and Integrity Learning Network for RGB-D Salient Object Detection publication-title: ACM Trans. Multimed. Comput. Commun. Appl. – start-page: 770 year: 2016 end-page: 778 ident: b0150 article-title: Deep residual learning for image recognition publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 72 start-page: 1 year: 2023 end-page: 17 ident: b0075 article-title: ARWGAN: Attention-guided robust image watermarking model based on GAN publication-title: IEEE Trans. Instrum. Meas. – volume: 23 start-page: 600 year: 2004 end-page: 608 ident: b0165 article-title: High-quality video view interpolation using a layered representation publication-title: ACM Transactions on Graphics (TOG) – volume: 8 start-page: 93760 year: 2020 end-page: 93781 ident: b0030 article-title: NSCT-based robust and perceptual watermarking for DIBR 3D images publication-title: IEEE Access – volume: 92 year: 2023 ident: b0015 article-title: A bilateral attention based generative adversarial network for DIBR 3D image watermarking publication-title: J. Vis. Commun. Image Represent. – start-page: 657 year: 2018 end-page: 672 ident: b0055 article-title: Hiding data with deep networks publication-title: Proceedings of the European Conference on Computer Vision (ECCV) – start-page: 81 year: 2011 end-page: 84 ident: b0125 article-title: Perceptual watermarking for 3D stereoscopic video using depth information publication-title: 2011 Seventh International Conference on Intelligent Information Hiding and Multimedia Signal Processing. IEEE – year: 2024 ident: b0080 article-title: WFormer: A Transformer-Based Soft Fusion Model for Robust Image Watermarking publication-title: IEEE Trans. Emerging Top. Comput. Intell. – start-page: 7132 year: 2018 end-page: 7141 ident: b0145 article-title: Squeeze-and-excitation networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – volume: 69 year: 2024 ident: b0090 article-title: ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection publication-title: Phys. Med. Biol. – reference: Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer International Publishing, pp. 234-241, 2015. – start-page: 4217 year: 2009 end-page: 4220 ident: b0120 article-title: Watermarking for depth-image-based rendering publication-title: 2009 16th IEEE International Conference on Image Processing (ICIP). IEEE – start-page: 567 year: 2015 end-page: 576 ident: b0160 article-title: Sun rgb-d: A rgb-d scene understanding benchmark suite publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – start-page: 819 year: 2017 end-page: 826 ident: b0135 article-title: Frequency-domain watermarking of 3D DIBR images using the steerable pyramid and discrete cosine transforms publication-title: 2017 8th International Conference on Information Technology (ICIT) – volume: 94 start-page: 32 year: 2023 end-page: 42 ident: b0035 article-title: BCINet: Bilateral cross-modal interaction network for indoor scene understanding in RGB-D images publication-title: Inf. Fusion – reference: Zhang H, Wang H, Cao Y, et al. Robust data hiding using inverse gradient attention. arXiv preprint arXiv:2011.10850, 2020. – reference: Kingma D P. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014. – start-page: 1 year: 2007 end-page: 8 ident: b0170 article-title: Evaluation of cost functions for stereo matching publication-title: 2007 IEEE Conference on Computer Vision and Pattern Recognition – volume: 44 start-page: 4005 year: 2021 end-page: 4020 ident: b0105 article-title: Deep model intellectual property protection via deep watermarking publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0050 article-title: CATNet: A cascaded and aggregated transformer network for RGB-D salient object detection publication-title: IEEE Trans. Multimedia – volume: 146 year: 2020 ident: 10.1016/j.jvcir.2025.104455_b0060 article-title: ReDMark: Framework for residual diffusion watermarking based on deep networks publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2019.113157 – ident: 10.1016/j.jvcir.2025.104455_b0070 – volume: 25 start-page: 2648 year: 2022 ident: 10.1016/j.jvcir.2025.104455_b0115 article-title: Encoded feature enhancement in watermarking network for distortion in real scenes publication-title: IEEE Trans. Multimedia doi: 10.1109/TMM.2022.3149641 – start-page: 657 year: 2018 ident: 10.1016/j.jvcir.2025.104455_b0055 article-title: Hiding data with deep networks – start-page: 819 year: 2017 ident: 10.1016/j.jvcir.2025.104455_b0135 article-title: Frequency-domain watermarking of 3D DIBR images using the steerable pyramid and discrete cosine transforms – volume: 87 year: 2020 ident: 10.1016/j.jvcir.2025.104455_b0010 article-title: A robust blind watermarking algorithm for depth-image-based rendering 3D images publication-title: Signal Process. Image Commun. doi: 10.1016/j.image.2020.115935 – start-page: 7132 year: 2018 ident: 10.1016/j.jvcir.2025.104455_b0145 article-title: Squeeze-and-excitation networks – volume: 152 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0095 article-title: A novel denoising method for CT images based on U-net and multi-attention publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2022.106387 – start-page: 4217 year: 2009 ident: 10.1016/j.jvcir.2025.104455_b0120 article-title: Watermarking for depth-image-based rendering – volume: 92 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0015 article-title: A bilateral attention based generative adversarial network for DIBR 3D image watermarking publication-title: J. Vis. Commun. Image Represent. doi: 10.1016/j.jvcir.2023.103794 – volume: 72 start-page: 1 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0075 article-title: ARWGAN: Attention-guided robust image watermarking model based on GAN publication-title: IEEE Trans. Instrum. Meas. – volume: 69 issue: 10 year: 2024 ident: 10.1016/j.jvcir.2025.104455_b0090 article-title: ReconU-Net: a direct PET image reconstruction using U-Net architecture with back projection-induced skip connection publication-title: Phys. Med. Biol. doi: 10.1088/1361-6560/ad40f6 – ident: 10.1016/j.jvcir.2025.104455_b0085 doi: 10.1007/978-3-319-24574-4_28 – volume: 23 start-page: 600 issue: 3 year: 2004 ident: 10.1016/j.jvcir.2025.104455_b0165 article-title: High-quality video view interpolation using a layered representation publication-title: ACM Transactions on Graphics (TOG) doi: 10.1145/1015706.1015766 – start-page: 1 year: 2007 ident: 10.1016/j.jvcir.2025.104455_b0170 article-title: Evaluation of cost functions for stereo matching – volume: 423 start-page: 158 year: 2021 ident: 10.1016/j.jvcir.2025.104455_b0005 article-title: Quality assessment of DIBR-synthesized views: An overview publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.09.062 – year: 2024 ident: 10.1016/j.jvcir.2025.104455_b0080 article-title: WFormer: A Transformer-Based Soft Fusion Model for Robust Image Watermarking publication-title: IEEE Trans. Emerging Top. Comput. Intell. – ident: 10.1016/j.jvcir.2025.104455_b0180 – volume: 53 start-page: 17391 issue: 14 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0110 article-title: Pairwise open-sourced dataset protection based on adaptive blind watermarking publication-title: Appl. Intell. doi: 10.1007/s10489-022-04416-0 – start-page: 81 year: 2011 ident: 10.1016/j.jvcir.2025.104455_b0125 article-title: Perceptual watermarking for 3D stereoscopic video using depth information – volume: 5291 start-page: 93 year: 2004 ident: 10.1016/j.jvcir.2025.104455_b0175 article-title: Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV publication-title: Stereoscopic Displays and Virtual Reality Systems – start-page: 770 year: 2016 ident: 10.1016/j.jvcir.2025.104455_b0150 article-title: Deep residual learning for image recognition – start-page: 1407 year: 2021 ident: 10.1016/j.jvcir.2025.104455_b0045 article-title: Deep RGB-D saliency detection with depth-sensitive attention and automatic multi-modal fusion – start-page: 567 year: 2015 ident: 10.1016/j.jvcir.2025.104455_b0160 article-title: Sun rgb-d: A rgb-d scene understanding benchmark suite – volume: 58 start-page: 533 issue: 4 year: 2012 ident: 10.1016/j.jvcir.2025.104455_b0025 article-title: Robust DT-CWT watermarking for DIBR 3D images publication-title: IEEE Trans. Broadcast. doi: 10.1109/TBC.2012.2206851 – volume: 34 start-page: 1120 issue: 01 year: 2020 ident: 10.1016/j.jvcir.2025.104455_b0065 article-title: Attention based data hiding with generative adversarial networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence doi: 10.1609/aaai.v34i01.5463 – volume: 20 start-page: 1 issue: 7 year: 2024 ident: 10.1016/j.jvcir.2025.104455_b0040 article-title: Heterogeneous Fusion and Integrity Learning Network for RGB-D Salient Object Detection publication-title: ACM Trans. Multimed. Comput. Commun. Appl. doi: 10.1145/3656476 – volume: 12 start-page: 1 issue: 4 year: 2016 ident: 10.1016/j.jvcir.2025.104455_b0020 article-title: Depth-based view-invariant blind 3D image watermarking publication-title: ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) doi: 10.1145/2957751 – volume: 8 start-page: 93760 year: 2020 ident: 10.1016/j.jvcir.2025.104455_b0030 article-title: NSCT-based robust and perceptual watermarking for DIBR 3D images publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2994966 – volume: 77 start-page: 7811 year: 2018 ident: 10.1016/j.jvcir.2025.104455_b0130 article-title: A SIFT features based blind watermarking for DIBR 3D images publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-017-4678-x – volume: 142 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0100 article-title: Rethinking the unpretentious U-net for medical ultrasound image segmentation publication-title: Pattern Recogn. doi: 10.1016/j.patcog.2023.109728 – volume: 44 start-page: 4005 issue: 8 year: 2021 ident: 10.1016/j.jvcir.2025.104455_b0105 article-title: Deep model intellectual property protection via deep watermarking publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 31 start-page: 6124 year: 2022 ident: 10.1016/j.jvcir.2025.104455_b0155 article-title: Improving RGB-D salient object detection via modality-aware decoder publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2022.3205747 – volume: 94 start-page: 32 year: 2023 ident: 10.1016/j.jvcir.2025.104455_b0035 article-title: BCINet: Bilateral cross-modal interaction network for indoor scene understanding in RGB-D images publication-title: Inf. Fusion doi: 10.1016/j.inffus.2023.01.016 – volume: 76 start-page: 649 year: 2017 ident: 10.1016/j.jvcir.2025.104455_b0140 article-title: A novel watermarking for DIBR 3D images with geometric rectification based on feature points publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-015-3028-0 |
| SSID | ssj0003934 |
| Score | 2.4063132 |
| Snippet | For depth-image-based rendering (DIBR) 3D images, both center and synthesized virtual views are subject to illegal distribution during transmission. To address... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 104455 |
| SubjectTerms | Cross-modal Attention Depth-image-based rendering (DIBR) 3D image Transformer Watermarking |
| Title | Multi-level cross-modal attention guided DIBR 3D image watermarking |
| URI | https://dx.doi.org/10.1016/j.jvcir.2025.104455 |
| Volume | 109 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PS8MwFA4yL3oQnYo_Rw7iybiuTbL2ODtl_kSmg91Kk9dIh9vEbXrzbzcvbVFBPHgopSFpytf05aX53vcIOdIgMFuqYH5mBOOhjlgowGeZZ0cPKN7yFe7o3t7J3oBfDcVwicRVLAzSKkvbX9h0Z63LkmaJZvMlz5sPKDIQYAJw1PS3izyMYOdtHOWnH180jyAqdpZRkQBrV8pDjuM1etM5ioL6Avc6Ocb7_TY7fZtxLtbJWukq0k7xNBtkKZvUyeo3AcE62S8r5bMxPaY_gj1mmyR20bXsGXlB1HXIxlOwt0RNTcdypE-LHDKg3cuzPg26NB9b80LfU2ev3V_0LTK4OH-Me6xMmsC0_TrnTIExbRCBjEBru7jwRSq49oyCllQWfAOSg3XrvMwXgT3SNLLlkYYWeNwEPNgmtcl0ku0QGvHUEyEIzG_EtWwpCEEZYyCUaVsauUtOKrCSl0IbI6lIY6PEYZsgtkmB7S6RFaDJj1ecWOv9V8O9_zbcJyt4VTC7Dkht_rrIDq0PMVcNN0gaZLkT92_u8Xx53bv7BH82yCg |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3JTsMwEB1BOQAHBAUElMUHxAmraWKb5AiFqqXLgUXqLUo8MQqii6CF38eTBbUS4sAhFyeTRC_O8zIzbwDONUqqliq5mxjJha8D7kt0eeLY3oOxaLgxeXT7A9V-FvdDOVyBZpkLQ2GVBffnnJ6xddFSL9CsT9O0_kgiAx4VACdNf7vIW4U1UqeSFVi77nTbgx9C9oLcuUyiBGRQig9lYV6vnzolXVBXkrtTUMrfbwPUwqDT2oatYrbIrvMX2oGVZFyFzQUNwSrUiovSjxG7YEv5Hh-70MwSbPkbhQax7IF8NEF7S5LVzAId2cs8xQTZbefmgXm3LB1ZhmFfUUbZ2Ub6Hjy37p6abV7UTeDa_qAzHqMxVyg9FaDWdn3hykgK7ZgYGyq2-BtUAu3Mzklc6dkjigLbHmhsoCOMJ7x9qIwn4-QAWCAiR_ooqcSR0KoRo4-xMQZ9FV0pow7hsgQrnObyGGEZN_YaZtiGhG2YY3sIqgQ0XPrKoSXwvwyP_mt4Buvtp34v7HUG3Rps0Jk80OsYKrP3eXJipxSz-LToMt8lxclE |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multi-level+cross-modal+attention+guided+DIBR+3D+image+watermarking&rft.jtitle=Journal+of+visual+communication+and+image+representation&rft.au=Chen%2C+Qingmo&rft.au=Wang%2C+Zhang&rft.au=He%2C+Zhouyan&rft.au=Luo%2C+Ting&rft.date=2025-06-01&rft.issn=1047-3203&rft.volume=109&rft.spage=104455&rft_id=info:doi/10.1016%2Fj.jvcir.2025.104455&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_jvcir_2025_104455 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1047-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1047-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1047-3203&client=summon |