Welcome to the AI Assets Catalog! Here you can browse, search and download all the assets currently indexed in the AI-on-Demand platform, including AI libraries, datasets, containers, and more. You are welcome to publish your own AI assets here! To do so, log in in to the platform, go to your dashboard and use the Submit new content button to access the submission forms.
Fast SR-UNet
Architecture and GAN-based training procedure for obtaining a fast neural network which enable better bitrate performances respect to the H.265 codec for the same quality, or better quality at the same bitrate.
LLMAKER - Consistent Game Content Creation via LLMs
A framework for evaluating LLM on iterative game content refinement
The Florence 4D Facial Expression Dataset
Dataset of 4D dynamic sequences of 3D faces with varying facial expressions
Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements
d-Simplex classifiers achieve stationary, compatible features, enabling seamless model updates in retrieval systems.
CL2R: Compatible Lifelong Learning Representations
A novel dataset of dynamic sequences of 3D face models, where a combination of synthetic and real identities exhibit an unprecedented variety of 4D facial expressions, with variations that include the classical neutral-apex transition, but generalize to e...
CoReS: Compatible Representations via Stationarity
Using stationary representations, CoReS trains models to obtain compatible representations, eliminating costly re-indexing in retrieval systems during upgrades.
Contrastive Supervised Distillation for Continual Representation Learning
Mitigating forgetting in continual representation learning using contrastive supervised distillation.
Regular Polytope Networks
Using fixed classifiers derived from regular polytopes to enhance neural network efficiency and accuracy by generating stationary, maximally-separated feature representations.
NEFER a Dataset for Neuromorphic Event-based Facial Expression Recognition
NEFER is composed of paired RGB and event videos representing human faces labeled with the respective emotions and also annotated with face bounding boxes and facial landmarks.