This paper introduces an adaptive image super-resolution model that incorporates degradation-aware generative networks, enhancing aerial surveillance image clarity in real-time for large-scale monitoring applications.

Henry Douglas Farnsworth, Zhang Linwei, Bhavika Sushmita Reddy, Olivier Marcel Chevalier, Ayumi Hoshino, Francesca Noemi Delgado

This study proposes a fall detection system using temporal action encoding and pose consistency validation, enhancing monitoring accuracy for elderly individuals in smart home and assisted living environments.

Gavin Charles Hammond, Liu Yuanhao, Neha Shantanu Kulkarni, Remy Gabriel Marchand, Keiko Misaki Yamada, Alina Teresa Navarro

This research introduces a hybrid model combining semantic parsing, visual grounding, and natural language processing for precise interpretation of navigation instructions in dynamic indoor and outdoor environments.

Owen Maxwell Livingston, Zhang Yueqin, Shraddha Nisha Bansal, Antoine Claude Fournier, Naomi Sakura Watanabe, Adriana Beatriz Silva

This paper presents a multi-sensor tracking solution that fuses vision, LiDAR, and radar inputs using advanced data association and feature refinement networks for robust object tracking in smart mobility systems.

Douglas Raymond Wilcox, Huang Wenliang, Karishma Devi Rao, Enzo Laurent Deschamps, Yuna Emi Takagi, Bianca Carolina Costa

This study introduces a self-supervised learning approach for detecting visual anomalies in autonomous vehicles, leveraging spatiotemporal representation learning to identify environmental deviations and object-level inconsistencies.

Isaiah Leonard Maxwell, Zhang Qiaolian, Manisha Satyen Shah, Philippe Gérard Lefevre, Aiko Nanami Fujimoto, Julia Margot Romano