activity
20182021
most citedWorking Memory Connections for LSTM

282 citations · 320 across the 4 of their papers we have counts for

collaborators

10 papers

cs.LG2021282 cited

Working Memory Connections for LSTM

Federico Landi, Lorenzo Baraldi, Marcella Cornia +1

Recurrent Neural Networks with Long Short-Term Memory (LSTM) make use of gating mechanisms to mitigate exploding and vanishing gradients when learning long-term dependencies. For t…

cs.CV20218 cited

Learning to Select: A Fully Attentive Approach for Novel Object Captioning

Marco Cagrandi, Marcella Cornia, Matteo Stefanini +2

Image captioning models have lately shown impressive results when applied to standard datasets. Switching to real-life scenarios, however, constitutes a challenge due to the larger…

cs.CV2021

Out of the Box: Embodied Navigation in the Real World

Roberto Bigazzi, Federico Landi, Marcella Cornia +3

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of…

cs.CV20212 cited

Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis

Samuele Poppi, Marcella Cornia, Lorenzo Baraldi +1

As the request for deep learning solutions increases, the need for explainability is even more fundamental. In this setting, particular attention has been given to visualization te…

cs.CV2020

A Novel Attention-based Aggregation Function to Combine Vision and Language

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi +1

The joint understanding of vision and language has been recently gaining a lot of attention in both the Computer Vision and Natural Language Processing communities, with the emerge…

cs.CV2019

Meshed-Memory Transformer for Image Captioning

Marcella Cornia, Matteo Stefanini, Lorenzo Baraldi +1

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal co…