A
A. V. Subramanyam
Researcher at Indraprastha Institute of Information Technology
Publications - 50
Citations - 691
A. V. Subramanyam is an academic researcher from Indraprastha Institute of Information Technology. The author has contributed to research in topics: Computer science & Digital watermarking. The author has an hindex of 10, co-authored 41 publications receiving 539 citations. Previous affiliations of A. V. Subramanyam include Nanyang Technological University.
Papers
More filters
Journal ArticleDOI
Robust Watermarking of Compressed and Encrypted JPEG2000 Images
TL;DR: A robust watermarking algorithm to watermark JPEG2000 compressed and encrypted images is proposed, using a stream cipher and the embedding capacity, robustness, perceptual quality and security of the proposed algorithm are investigated.
Proceedings ArticleDOI
Video forgery detection using HOG features and compression properties
A. V. Subramanyam,Sabu Emmanuel +1 more
TL;DR: A novel video forgery detection technique based on Histogram of Oriented Gradients feature matching and video compression properties to detect the spatial and temporal copy paste tampering in videos.
Journal ArticleDOI
Joint Watermarking Scheme for Multiparty Multilevel DRM Architecture
TL;DR: A joint digital watermarking scheme using Chinese remainder theorem for the multiparty multilevel DRM architecture that takes care of the security concerns of all parties involved.
Proceedings ArticleDOI
Face video based touchless blood pressure and heart rate estimation
TL;DR: This paper proposes a novel touchless approach that predicts BP and HR using the face video based PPG, which complies with the standards mentioned by Association for the Advancement of Medical Instrumentation.
Journal ArticleDOI
SDL: Spectrum-Disentangled Representation Learning for Visible-Infrared Person Re-Identification
TL;DR: A novel network with disentanglement loss which can distill identity features and dispel spectrum features and is trained in an end-to-end manner, which minimizes spectrum information and maximizes invariant identity relevant information at spectrum dispelling branch.