News

eLife17h
A neuromorphic model of active vision shows how spatiotemporal encoding in lobula neurons can aid pattern recognition in bees
Active vision dynamically refines spatiotemporal neural representations, optimising visual processing through scanning behaviour and non-associative learning, providing insights into efficient sensory ...
IEEE19h
On improving recurrent neural network for image classification
The paper proposes a new method for improving the performance of Recurrent Neural Networks. The proposed method uses two parallel recurrent layers which execute independent of each other. The final ...
IEEE20d
Robust Model Predictive Control-Based Recurrent Neural Networks for Autonomous Vehicles in Avoidance Collisions - IEEE Xplore
Ensuring safe driving under real-time uncertainties remains a critical challenge in autonomous vehicle control. To address this issue for a collision avoidance task, this study proposes a robust model ...
GitHub28d
cv-stuttgart/MS-RAFT-3D: [ICIP 2025] Code for "MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-Based Scene Flow" - GitHub
We use CUDA version 11.3. and PyTorch version 1.12.1. The following packages are required: DATASETS_SCENEFLOW_ROOT ├── fth ├── frames_cleanpass ├── frames_finalpass ├── disparity ├── disparity_change ...