Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63791
Volume:
10 |
5 |
May 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Master of Computer Applications
Bapuji Institute of Engineering and Technology,Davanagere
Master of Computer Applications
Bapuji Institute of Engineering and Technology,Davanagere
Video prediction involves generating future frames of a video sequence based on previously observed frames. It is one of the fundamental problem in computer vision which has numerous applications in autonomous driving, robotics, surveillance, and medical imaging. Recent advancements in deep learning, particularly spatiotemporal neural networks and generative models, have significantly improved the quality of future frame synthesis. This paper presents a deep learning based framework for video prediction using convolutional recurrent networks and generative adversarial models. The Proposed System captures temporal dynamics and spatial features in order to generate realistic future frames. Experimental evaluation on benchmark video datasets demonstrates improved prediction accuracy and visual quality compared to conventional approaches. This framework provides a scalable solution for real time video forecasting tasks.
KEYWORDS
This paper presented a deep learning based framework for video prediction using spatiotemporal neural networks and generative modeling techniques. The integration of transformer modules and adversarial training enhances prediction quality and temporal consistency. Future work includes exploring diffusion based video generation models, incorporating multimodal inputs such as optical flow, applying self-supervised pretraining for improved representation learning, and optimizing models for edge computing environments.
This paper presented a deep learning based framework for video prediction using spatiotemporal neural networks and generative modeling techniques. The integration of transformer modules and adversarial training enhances prediction quality and temporal consistency. Future work includes exploring diffusion based video generation models, incorporating multimodal inputs such as optical flow, applying self-supervised pretraining for improved representation learning, and optimizing models for edge computing environments.
Publication Date
5/22/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...