Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Video super resolution aims to generate high resolution video sequences from corresponding low resolution video sequences. Aiming at improving the insufficient utilization of temporal and spatial information of video sequences in current video super resolution methods, we proposed a new network based on deformable 3D convolutional group fusion. Input sequences were divided into groups according to different frame rates, which can effectively integrate time information in a hierarchical manner. The deformable 3D convolution was used for integration points within the good group of characteristics to keep the spatial and temporal correlation of video sequences. The introduction of time attention mechanism and group integration module provided supplementary information fusion for each group, to restore the missing details in the video sequence and generate high resolution video frames. Experimental results on Vid4 standard video data set show that The PSNR and SSIM of the generated high-resolution video frames are 27.39 and 0.8266, respectively. The network presented in this study has a good effect on the processing of motion video and has achieved better performance than current advanced methods.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11911439 | PMC |
| http://dx.doi.org/10.1038/s41598-025-93758-z | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Educational technology: educational video to support home care management for liver transplant patients.
Rev Bras Enferm
September 2025
Universidade Federal de Santa Catarina. Florianópolis, Santa Catarina, Brazil.
Objectives: to develop and validate educational video to support the management of home care for clients undergoing liver transplantation.
Methods: a study supported by Instructional Design, through the following stages: analysis: data obtained through three studies already developed by the researchers; design: the script learning objectives were outlined; sequences of scenes, professionals involved, location, language, illustrative figures and necessary materials. Moreover, content validity: production - video development; implementation and evaluation - the video was used by clients undergoing liver transplantation followed by their assessment of this product.
HOT: Hierarchical Hourglass Tokenizer for Efficient Video Pose Transformers.
IEEE Trans Pattern Anal Mach Intell
September 2025
Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make them impractical on resource-constrained devices. In this paper, we present a hierarchical plug-and-play pruning-and-recovering framework, called Hierarchical Hourglass Tokenizer (HOT), for efficient transformer-based 3D human pose estimation from videos.
View Article and Find Full Text PDFSegmenting the motion components of a video: A long-term unsupervised model.
IEEE Trans Pattern Anal Mach Intell
September 2025
Human beings have the ability to continuously analyze a video and immediately extract the motion components. We want to adopt this paradigm to provide a coherent and stable motion segmentation over the video sequence. In this perspective, we propose a novel long-term spatio-temporal model operating in a totally unsupervised way.
View Article and Find Full Text PDFFeasibility of a Gamified Mobile-Based Self-Management Intervention for Individuals With Nonspecific Chronic Lower Back Pain.
Nurs Res
September 2025
College of Nursing & Institute of Nursing Research, Korea University, Seoul, South Korea.
Background: Existing research fails to address the complex nature of nonspecific chronic lower back pain (cLBP ) despite its detrimental effect on economic, societal, and medical expenditures.
Objectives: We developed a nurse-led, mobile-delivered self-management intervention-Problem-Solving Pain to Enhance Living Well (PROPEL-M)-and evaluated its usability, feasibility, and initial efficacy for South Korean adults with nonspecific cLBP.
Methods: This study was composed of two phases: (a) lab and field usability testing for a gamified mobile device application; and (b) a pilot study employing a one-arm pre-test and post-test design among adults aged 18-60 years with nonspecific cLBP.
Consent-driven, semi-automated data collection during birth and newborn resuscitation: Insights from the NewbornTime study.
PLOS Digit Health
September 2025
Laerdal Medical AS, Stavanger, Norway.
Accurate observations at birth and during newborn resuscitation are fundamental for quality improvement initiatives and research. However, manual data collection methods often lack consistency and objectivity, are not scalable, and may raise privacy concerns. The NewbornTime project aims to develop an AI system that generates accurate timelines from birth and newborn resuscitation events by automated video recording and processing, providing a source of objective and consistent data.
View Article and Find Full Text PDF