no code implementations • 11 Dec 2023 • Guglielmo Camporese, Alessandro Bergamo, Xunyu Lin, Joseph Tighe, Davide Modolo
For example, on early recognition observing only the first 10% of each video, our method improves the SOTA by +2. 23 Top-1 accuracy on Something-Something-v2, +3. 55 on UCF-101, +3. 68 on SSsub21, and +5. 03 on EPIC-Kitchens-55, where prior work used either multi-modal inputs (e. g. optical-flow) or batched inference.
no code implementations • 15 May 2023 • Sourav Das, Guglielmo Camporese, Shaokang Cheng, Lamberto Ballan
Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics.
1 code implementation • 26 Oct 2022 • Nada Osman, Guglielmo Camporese, Lamberto Ballan
Human intention prediction is a growing area of research where an activity in a video has to be anticipated by a vision-based system.
2 code implementations • 1 Jun 2022 • Guglielmo Camporese, Elena Izzo, Lamberto Ballan
Vision Transformers (ViTs) enabled the use of the transformer architecture on vision tasks showing impressive performances when trained on big datasets.
no code implementations • 2 Sep 2021 • Nada Osman, Guglielmo Camporese, Pasquale Coscia, Lamberto Ballan
Action anticipation in egocentric videos is a difficult task due to the inherently multi-modal nature of human actions.
1 code implementation • ICCV 2021 • Yunrui Guo, Guglielmo Camporese, Wenjing Yang, Alessandro Sperduti, Lamberto Ballan
In this way, we are able to control the compactness of the features of the same class around the center of the gaussians, thus controlling the ability of the classifier in detecting samples from unknown classes.
no code implementations • 11 Dec 2020 • Valentin Mendelev, Tina Raissi, Guglielmo Camporese, Manuel Giollo
Automatic Speech Recognition (ASR) based on Recurrent Neural Network Transducers (RNN-T) is gaining interest in the speech community.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Apr 2020 • Guglielmo Camporese, Pasquale Coscia, Antonino Furnari, Giovanni Maria Farinella, Lamberto Ballan
Since multiple actions may equally occur in the future, we treat action anticipation as a multi-label problem with missing labels extending the concept of label smoothing.