Barbara Caputo

research

∙ 09/08/2023

Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation

Segmenting unknown or anomalous object instances is a critical task in a...

0 Shyam Nandan Rai, et al. ∙

research

∙ 08/21/2023

EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition

Visual Place Recognition is a task that aims to predict the place of an ...

0 Gabriele Berton, et al. ∙

research

∙ 07/25/2023

Unmasking Anomalies in Road-Scene Segmentation

Anomaly segmentation is a critical task for driving applications, and it...

0 Shyam Nandan Rai, et al. ∙

research

∙ 07/24/2023

EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction

This report presents the technical details of our approach for the EPIC-...

0 Amirshayan Nasirimajd, et al. ∙

research

∙ 07/17/2023

Divide Classify: Fine-Grained Classification for City-Wide Visual Place Recognition

Visual Place recognition is commonly addressed as an image retrieval pro...

0 Gabriele Trivigno, et al. ∙

research

∙ 06/14/2023

What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations

We propose and address a new generalisation problem: can a model trained...

0 Chiara Plizzari, et al. ∙

research

∙ 04/12/2023

Are Local Features All You Need for Cross-Domain Visual Place Recognition?

Visual Place Recognition is a task that aims to predict the coordinates ...

0 Giovanni Barbarani, et al. ∙

research

∙ 11/06/2022

Bringing Online Egocentric Action Recognition into the wild

To enable a safe and effective human-robot cooperation, it is crucial to...

0 Gabriele Goletto, et al. ∙

research

∙ 10/12/2022

Hierarchical Instance Mixing across Domains in Aerial Segmentation

We investigate the task of unsupervised domain adaptation in aerial sema...

0 Edoardo Arnaudo, et al. ∙

research

∙ 09/09/2022

PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

In this report, we describe the technical details of our submission to t...

0 Mirco Planamente, et al. ∙

research

∙ 08/24/2022

Detecting the unknown in Object Detection

Object detection methods have witnessed impressive improvements in the l...

0 Dario Fontanel, et al. ∙

research

∙ 07/08/2022

Learning Sequential Descriptors for Sequence-based Visual Place Recognition

In robotics, Visual Place Recognition is a continuous process that recei...

0 Riccardo Mereu, et al. ∙

research

∙ 06/17/2022

FreeREA: Training-Free Evolution-based Architecture Search

In the last decade, most research in Machine Learning contributed to the...

0 Niccolò Cavagnero, et al. ∙

research

∙ 04/19/2022

Modeling Missing Annotations for Incremental Learning in Object Detection

Despite the recent advances in the field of object detection, common arc...

0 Fabio Cermelli, et al. ∙

research

∙ 04/17/2022

Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images

In this paper, we investigate the problem of Semantic Segmentation for a...

0 Antonio Tavera, et al. ∙

research

∙ 04/07/2022

Deep Visual Geo-localization Benchmark

In this paper, we propose a new open-source benchmarking framework for V...

0 Gabriele Berton, et al. ∙

research

∙ 04/05/2022

Rethinking Visual Geo-localization for Large-Scale Applications

Visual Geo-localization (VG) is the task of estimating the position wher...

0 Gabriele Berton, et al. ∙

research

∙ 01/31/2022

Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation

Deep neural networks have enabled major progresses in semantic segmentat...

14 Fabio Cermelli, et al. ∙

research

∙ 01/24/2022

Learning Semantics for Visual Place Recognition through Multi-Scale Attention

In this paper we address the task of visual place recognition (VPR), whe...

0 Valerio Paolicelli, et al. ∙

research

∙ 12/07/2021

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images

Incremental learning represents a crucial task in aerial image processin...

0 Edoardo Arnaudo, et al. ∙

research

∙ 12/07/2021

E^2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition

Event cameras are novel bio-inspired sensors, which asynchronously captu...

6 Chiara Plizzari, et al. ∙

research

∙ 10/22/2021

Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation

Semantic segmentation models have reached remarkable performance across ...

0 Antonio Tavera, et al. ∙

research

∙ 10/22/2021

Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation

In this paper we consider the task of semantic segmentation in autonomou...

0 Antonio Tavera, et al. ∙

research

∙ 10/19/2021

Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition

First person action recognition is becoming an increasingly researched a...

0 Mirco Planamente, et al. ∙

research

∙ 09/20/2021

Viewpoint Invariant Dense Matching for Visual Geolocalization

In this paper we propose a novel method for image matching based on dens...

2 Gabriele Berton, et al. ∙

research

∙ 07/09/2021

On the Challenges of Open World Recognitionunder Shifting Visual Domains

Robotic visual systems operating in the wild must act in unconstrained s...

0 Dario Fontanel, et al. ∙

research

∙ 07/05/2021

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

Vision systems trained in closed-world scenarios will inevitably fail wh...

0 Silvia Bucci, et al. ∙

research

∙ 07/01/2021

PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition

In this report, we describe the technical details of our submission to t...

0 Chiara Plizzari, et al. ∙

research

∙ 06/04/2021

Towards Fairness Certification in Artificial Intelligence

Thanks to the great progress of machine learning in the last years, seve...

0 Tatiana Tommasi, et al. ∙

research

∙ 06/03/2021

Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment

First person action recognition is an increasingly researched topic beca...

0 Mirco Planamente, et al. ∙

research

∙ 06/01/2021

Detecting Anomalies in Semantic Segmentation with Prototypes

Traditional semantic segmentation methods can recognize at test time onl...

15 Dario Fontanel, et al. ∙

research

∙ 04/21/2021

A Closer Look at Self-training for Zero-Label Semantic Segmentation

Being able to segment unseen classes not observed during training is an ...

11 Giuseppe Pastore, et al. ∙

research

∙ 03/25/2021

Boosting Binary Masks for Multi-Domain Learning through Affine Transformations

In this work, we present a new, algorithm for multi-domain learning. Giv...

0 Massimiliano Mancini, et al. ∙

research

∙ 03/25/2021

Inferring Latent Domains for Unsupervised Deep Domain Adaptation

Unsupervised Domain Adaptation (UDA) refers to the problem of learning a...

0 Massimiliano Mancini, et al. ∙

research

∙ 02/12/2021

Adversarial Branch Architecture Search for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) is a key field in visual recognitio...

0 Luca Robbiano, et al. ∙

research

∙ 12/15/2020

A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer

This paper presents our work for the ninth edition of the Dialogue Syste...

10 Matteo A. Senese, et al. ∙

research

∙ 11/30/2020

A Few Guidelines for Incremental Few-Shot Segmentation

Reducing the amount of supervision required by neural networks is especi...

9 Fabio Cermelli, et al. ∙

research

∙ 10/14/2020

Adaptive-Attentive Geolocalization from few queries: a hybrid approach

We address the task of cross-domain visual place recognition, where the ...

0 Gabriele Moreno Berton, et al. ∙

research

∙ 08/04/2020

Shape Consistent 2D Keypoint Estimation under Domain Shift

Recent unsupervised domain adaptation methods based on deep architecture...

0 Levi O. Vasconcelos, et al. ∙

research

∙ 07/24/2020

Self-Supervised Learning Across Domains

Human adaptability relies crucially on learning and merging knowledge fr...

0 Silvia Bucci, et al. ∙

research

∙ 07/23/2020

Towards Recognizing Unseen Categories in Unseen Domains

Current deep visual recognition systems suffer from severe performance d...

9 Massimiliano Mancini, et al. ∙

research

∙ 05/23/2020

One-Shot Unsupervised Cross-Domain Detection

Despite impressive progress in object detection over the last years, it ...

3 Antonio D'Innocente, et al. ∙

research

∙ 04/21/2020

Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition

Unsupervised Domain Adaptation (DA) exploits the supervision of a label-...

21 Mohammad Reza Loghmani, et al. ∙

research

∙ 04/20/2020

Boosting Deep Open World Recognition by Clustering

While convolutional neural networks have brought significant advances in...

0 Dario Fontanel, et al. ∙

research

∙ 04/17/2020

IDDA: a large-scale multi-domain dataset for autonomous driving

Semantic segmentation is key in autonomous driving. Using deep visual le...

0 Emanuele Alberti, et al. ∙

research

∙ 02/10/2020

Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition

Wearable cameras are becoming more and more popular in several applicati...

0 Mirco Planamente, et al. ∙

research

∙ 02/03/2020

Modeling the Background for Incremental Learning in Semantic Segmentation

Despite their effectiveness in a wide range of tasks, deep architectures...

0 Fabio Cermelli, et al. ∙

research

∙ 10/09/2019

Learning to Generalize One Sample at a Time with Self-Supervision

Although deep networks have significantly increased the performance of v...

0 Antonio D'Innocente, et al. ∙

research

∙ 06/04/2019

Knowledge is Never Enough: Towards Web Aided Deep Open World Recognition

While today's robots are able to perform sophisticated tasks, they can o...

0 Massimiliano Mancini, et al. ∙

research

∙ 04/01/2019

The RGB-D Triathlon: Towards Agile Visual Toolboxes for Robots

Deep networks have brought significant advances in robot perception, ena...

0 Fabio Cermelli, et al. ∙

Barbara Caputo

Featured Co-authors