3 papers
cs.CV2026
Efficient Semantic Understanding from Digital Foveation
Caterina Caccavella, Vittorio Fra, Andreas Ziegler +2
Dense semantic segmentation allocates computational resources uniformly across the entire image, regardless of scene complexity or task relevance. Inspired by biological vision, we…
cs.CV2026
Neuromorphic visual attention for Sign-language recognition on SpiNNaker
Sarka Liskova, Olha Vedmedenko, Mazdak Fatahi +3
Sign-language recognition has achieved substantial gains in classification accuracy in recent years; however, the latency and power requirements of most existing methods limit thei…
cs.CV2025
Wandering around: A bioinspired approach to visual attention through object motion sensitivity
Giulia D'Angelo, Victoria Clerico, Chiara Bartolozzi +3
Active vision enables dynamic visual perception, offering an alternative to static feedforward architectures in computer vision, which rely on large datasets and high computational…