Article
Computer Science, Information Systems
Kun Zeng, Jiangchuan Hu, Yongyi Gong, Kanoksak Wattanachote, Runpeng Yu, Xiaonan Luo
Summary: Two seam coupling strategies, real mapping and virtual mapping, were proposed for vertical retargeting to address the problems of multiple assignments and missing assignments. Experimental results demonstrated that the method overcomes the limitations of vertical retargeting and effectively preserves geometric consistency.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Ankit Garg, Anuj Kumar Singh
Summary: This paper presents an improved technique for image retargeting, which uses the gradient energy map generation method to safeguard the prominent regions of the image. The efficiency of the technique is validated through objective and subjective image quality assessment.
Article
Engineering, Electrical & Electronic
Seung-Hun Nam, Wonhyuk Ahn, In-Jae Yu, Myung-Joon Kwon, Minseok Son, Heung-Kyu Lee
Summary: This paper proposes a CNN-based approach for classifying seam-carving forgery, with specialized network blocks designed to capture local artifacts caused by seam carving. Experimental results demonstrate that the method has good classification performance and robustness.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Software Engineering
Sean Flynn, David Hart, Bryan Morse, Seth Holladay, Parris Egbert
Summary: This paper introduces a novel method for intelligently resizing a wide range of volumetric data, including fluids, allowing for more versatile post-processing. Additionally, a faster seam computation method is presented to improve production workflow viability.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Information Systems
Hai Su, Zigui Ye, Yaping Liu, SongSen Yu
Summary: Seam carving algorithm is widely used for content-based image scaling. We propose a dynamic energy regulation method to improve the effect of seam carving by simulating the energy change in each carving. Our method adjusts the energy value of each pixel after each carving to simulate the extra energy introduced by carving.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Zehra Karapinar Senturk, Devrim Akgun
Summary: The paper introduces a new blind detection method based on seam carving for identifying retargeted images, which shows improved accuracies compared to traditional solutions through experiments.
ELEKTRONIKA IR ELEKTROTECHNIKA
(2021)
Article
Computer Science, Information Systems
Ankit Garg, Anand Nayyar, Anuj Kumar Singh
Summary: This paper proposes an improved seam carving technique to overcome the limitations of traditional techniques by restricting the intersection of optimal seam points on line structures. Through subjective and objective evaluations, the effectiveness and high similarity of the proposed technique have been demonstrated.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Eduardo Fragoso-Navarro, Kevin Rangel-Espinoza, Mariko Nakano-Miyatake, Manuel Cedillo-Hernandez, Hector Perez-Meana
Summary: Visible watermarking provides copyright protection to the naked eye by superimposing visible patterns on the host image. This paper proposes a watermark design based on modified Seam Carving technique to enhance robustness against various removal attacks, and its effectiveness is verified through experimental results.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Jila Ayubi, Mehdi Chehel Amirani, Morteza Valizadeh
Summary: This paper introduces a new method based on information entropy to extract the importance map and proposes a new method for selecting the most optimal seam based on the calculation of the Lyapunov exponents. Through simulation on the MSRA and RetargetMe datasets, it is demonstrated that the proposed algorithm performs better than the classical seam-carving and generalized seam-carving algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Zheng Wang, Jianguo Li, Yu-Gang Jiang
Summary: This paper introduces a new multimedia task of story-driven video editing, which retrieves related video segments and composes them into a video sequence based on the storyline. The proposed baseline solution includes three modules and a benchmark for evaluation, aiming to promote research on novel online short video editing applications.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Chemistry, Multidisciplinary
Ashraf Siddique, Seungkyu Lee
Summary: This paper introduces a video editing method that can achieve foreground object removal, background inpainting, and novel view video synthesis in challenging visual environments. By calculating a weighted confidence score and selecting high-quality observations to fill the desired region of interest in the video, the proposed method shows superior performance compared to multiple state-of-the-art methods.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Software Engineering
Miao Wang, Xiao-Nan Fang, Guo-Wei Yang, Ariel Shamir, Shi-Min Hu
Summary: The study introduces a novel method for identifying prominent structures in videos, enabling efficient calculation of prominent structures and alignment between videos. The prominent structural unit map encodes important information of video frames, supporting various video analysis and editing applications.
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
(2021)
Article
Engineering, Electrical & Electronic
Cui Jia, Song Lei, Lu Hongju, Tang Mingxi, Qi Meng
Summary: Image retargeting technologies aim to preserve important information and reduce edge distortion. The JND algorithm is proposed to detect and pass distortion information to reduce retargeting distortions, offering promising results compared to other approaches at 'Retarget Me' database.
JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY
(2021)
Article
Computer Science, Software Engineering
Lucio Moser, Chinyu Chien, Mark Williams, Jose Serra, Darren Hendler, Doug Roble
Summary: The algorithm proposed in this study achieves automatic transfer of facial expressions between videos and 3D characters, as well as between different 3D characters. By learning common latent representations and establishing mapping relationships between images, expressions can be remapped between different characters unaffected by physiological differences. This technique can be applied to markerless motion capture and automatic facial animation transfer.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Computer Science, Software Engineering
Yoni Kasten, Dolev Ofri, Oliver Wang, Tali Dekel
Summary: The method decomposes input videos into layered 2D atlases for unified appearance representation, supporting automatic mapping of edits back to original frames. It does not require prior 3D knowledge and can handle complex real-world videos, showcasing various editing applications including texture mapping and segmentation propagation.
ACM TRANSACTIONS ON GRAPHICS
(2021)