-
PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic S...
We introduce the PaintNet dataset to accelerate research on supervised learning for multi-path prediction conditioned on free-shape 3D objects. PaintNet includes more than 800... -
DELTA: Dense Electromyography for Long-Term Adaptive control
The DELTA dataset, namely ”Dense Electromyography for Long-Term Adaptive control”, holds significance in the realm of prosthetic applications, featuring High Density surface... -
A Backpack Full of Skills: Egocentric Video Understanding with Diverse Task P...
Human comprehension of a video stream is naturally broad: in a few instants, we are able to understand what is happening, the relevance and relationship of objects, and... -
PEM: Prototype-based Efficient MaskFormer for Image Segmentation
Prototype-based Efficient MaskFormer (PEM) is an efficient transformer-based architecture that can operate in multiple segmentation tasks. PEM proposes a novel prototype-based... -
Bringing Online Egocentric Action Recognition into the wild
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities. Egocentric vision seems to be a viable... -
Experimental results from the Empirical Investigation of the Completeness of ...
This is the raw data from the empirical investigation of the paper “Completeness of Datasets Documentation on ML/AI repositories: an Empirical Investigation”. This work aim of...