Papers

1

Total Citations

45

H-Index

1

About

Akshay Dudhane is a computer vision researcher whose work centers on video object segmentation, particularly for challenging surveillance and autonomous driving scenarios. His most influential contribution is the development of a unified recurrent framework for moving object segmentation (MOS) that operates robustly across diverse and difficult environments, including varying lighting, weather, and camera motion. This approach eliminates the need for additional, separately trained modules—a common limitation in prior methods—by integrating temporal reasoning directly into a single end-to-end architecture. His 2021 paper on this topic has garnered 45 citations, reflecting its practical significance for real-world applications like robotics, outdoor surveillance, and self-driving cars. Dudhane’s research addresses a critical gap: enabling reliable foreground-background separation without task-specific fine-tuning, which is essential for deploying vision systems in uncontrolled settings. By advancing the efficiency and generalization of video segmentation models, his work helps bridge the gap between laboratory benchmarks and operational deployment in security and autonomous navigation.

Research Focus

Key Achievements

1
H-Index
1
Papers
45
Total Citations
45
Avg Citations/Paper
🏆 Most Cited Paper
An Unified Recurrent Video Object Segmentation Framework for Various Surveillance Environments
45 citations · 2021
📈 Most Prolific Year: 2021 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Mohamed bin Zayed University of Artificial Intelligence

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago