Search Results for author: Fabio Cuzzolin

Found 45 papers, 9 papers with code

Feature boosting with efficient attention for scene parsing

no code implementations29 Feb 2024 Vivek Singh, Shailza Sharma, Fabio Cuzzolin

This paper presents a novel feature-boosting network that gathers spatial context from multiple levels of feature extraction and computes the attention weights for each level of representation to generate the final class labels.

Scene Parsing

Generalising realisability in statistical learning theory under epistemic uncertainty

no code implementations22 Feb 2024 Fabio Cuzzolin

The purpose of this paper is to look into how central notions in statistical learning theory, such as realisability, generalise under the assumption that train and test distribution are issued from the same credal set, i. e., a convex set of probability distributions.

Learning Theory

Credal Learning Theory

no code implementations1 Feb 2024 Michele Caprio, Maryam Sultana, Eleni Elia, Fabio Cuzzolin

Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learnt from a (single) training set, assumed to issue from an unknown probability distribution.

Domain Adaptation Learning Theory

Reasoning with random sets: An agenda for the future

no code implementations19 Dec 2023 Fabio Cuzzolin

In this paper, we discuss a potential agenda for future work in the theory of random sets and belief functions, touching upon a number of focal issues: the development of a fully-fledged theory of statistical reasoning with random sets, including the generalisation of logistic regression and of the classical laws of probability; the further development of the geometric approach to uncertainty, to include general random sets, a wider range of uncertainty measures and alternative geometric representations; the application of this new theory to high-impact areas such as climate change, machine learning and statistical learning theory.

Learning Theory

Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction

no code implementations8 Aug 2023 Izzeddin Teeti, Rongali Sai Bhargav, Vivek Singh, Andrew Bradley, Biplab Banerjee, Fabio Cuzzolin

The emerging field of action prediction plays a vital role in various computer vision applications such as autonomous driving, activity analysis and human-computer interaction.

Activity Recognition Autonomous Driving +2

Random-Set Convolutional Neural Network (RS-CNN) for Epistemic Deep Learning

no code implementations11 Jul 2023 Shireen Kudukkil Manchingal, Muhammad Mubashar, Kaizheng Wang, Keivan Shariatmadar, Fabio Cuzzolin

Machine learning is increasingly deployed in safety-critical domains where robustness against adversarial attacks is crucial and erroneous predictions could lead to potentially catastrophic consequences.

Identification of Cognitive Workload during Surgical Tasks with Multimodal Deep Learning

no code implementations12 Sep 2022 Kaizhe Jin, Adrian Rubio-Solis, Ravi Naik, Tochukwu Onyeogulu, Amirul Islam, Salman Khan, Izzeddin Teeti, James Kinross, Daniel R Leff, Fabio Cuzzolin, George Mylonas

In this paper, a cascade of two machine learning approaches is suggested for the multimodal recognition of CWL in four different surgical task conditions.

Anatomy EEG +2

Epistemic Deep Learning

no code implementations15 Jun 2022 Shireen Kudukkil Manchingal, Fabio Cuzzolin

The belief function approach to uncertainty quantification as proposed in the Demspter-Shafer theory of evidence is established upon the general mathematical models for set-valued observations, called random sets.

Uncertainty Quantification

The intersection probability: betting with probability intervals

no code implementations5 Jan 2022 Fabio Cuzzolin

Probability intervals are an attractive tool for reasoning under uncertainty.

Decision Making

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

1 code implementation22 Dec 2021 Aduen Benjumea, Izzeddin Teeti, Fabio Cuzzolin, Andrew Bradley

As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors.

Autonomous Vehicles object-detection +1

International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines

no code implementations27 Oct 2021 Ajmal Shahbaz, Salman Khan, Mohammad Asiful Hossain, Vincenzo Lomonaco, Kevin Cannons, Zhan Xu, Fabio Cuzzolin

The aim of this paper is to formalize a new continual semi-supervised learning (CSSL) paradigm, proposed to the attention of the machine learning community via the IJCAI 2021 International Workshop on Continual Semi-Supervised Learning (CSSL-IJCAI), with the aim of raising field awareness about this problem and mobilizing its effort in this direction.

Activity Recognition Crowd Counting

Unsupervised anomaly detection for a Smart Autonomous Robotic Assistant Surgeon (SARAS)using a deep residual autoencoder

no code implementations22 Apr 2021 Dinesh Jackson Samuel, Fabio Cuzzolin

Anomaly detection in Minimally-Invasive Surgery (MIS) traditionally requires a human expert monitoring the procedure from a console.

Unsupervised Anomaly Detection

A geometric approach to conditioning belief functions

no code implementations21 Apr 2021 Fabio Cuzzolin

Conditioning is crucial in applied science when inference involving time series is involved.

Time Series Time Series Analysis

Spatiotemporal Deformable Scene Graphs for Complex Activity Detection

no code implementations16 Apr 2021 Salman Khan, Fabio Cuzzolin

We also contribute fresh temporal complex activity annotation for the recently released ROAD autonomous driving and SARAS-ESAD surgical action datasets and show the adaptability of our framework to different domains.

Action Detection Activity Detection +3

Uncertainty measures: The big picture

no code implementations14 Apr 2021 Fabio Cuzzolin

Probability theory is far from being the most general mathematical theory of uncertainty.

ROAD: The ROad event Awareness Dataset for Autonomous Driving

2 code implementations23 Feb 2021 Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Valentina Fontana, Reza Javanmard Alitappeh, Suman Saha, Kossar Jeddisaravi, Farzad Yousefi, Jacob Culley, Tom Nicholson, Jordan Omokeowa, Salman Khan, Stanislao Grazioso, Andrew Bradley, Giuseppe Di Gironimo, Fabio Cuzzolin

We also report the performance on the ROAD tasks of Slowfast and YOLOv5 detectors, as well as that of the winners of the ICCV2021 ROAD challenge, which highlight the challenges faced by situation awareness in autonomous driving.

Action Detection Activity Detection +4

Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration

no code implementations14 Dec 2020 Diana Mateus, Radu Horaud, David Knossow, Fabio Cuzzolin, Edmond Boyer

Matching articulated shapes represented by voxel-sets reduces to maximal sub-graph isomorphism when each set is described by a weighted graph.

Clustering Graph Matching

Challenges and Opportunities for Computer Vision in Real-life Soccer Analytics

no code implementations13 Apr 2020 Neha Bhargava, Fabio Cuzzolin

In this paper, we explore some of the applications of computer vision to sports analytics.

Sports Analytics

Two-Stream AMTnet for Action Detection

1 code implementation3 Apr 2020 Suman Saha, Gurkirt Singh, Fabio Cuzzolin

This is achieved by augmenting the previous Action Micro-Tube (AMTnet) action detection framework in three distinct ways: by adding a parallel motion stIn this paper, we propose a new deep neural network architecture for online action detection, termed ream to the original appearance one in AMTnet; (2) in opposition to state-of-the-art action detectors which train appearance and motion streams separately, and use a test time late fusion scheme to fuse RGB and flow cues, by jointly training both streams in an end-to-end fashion and merging RGB and optical flow features at training time; (3) by introducing an online action tube generation algorithm which works at video-level, and in real-time (when exploiting only appearance features).

Autonomous Driving Online Action Detection +2

Datamorphic Testing: A Methodology for Testing AI Applications

no code implementations10 Dec 2019 Hong Zhu, Dongmei Liu, Ian Bayley, Rachel Harrison, Fabio Cuzzolin

With the rapid growth of the applications of machine learning (ML) and other artificial intelligence (AI) techniques, adequate testing has become a necessity to ensure their quality.

BIG-bench Machine Learning Face Recognition

Spatio-Temporal Action Localization in a Weakly Supervised Setting

no code implementations6 May 2019 Kurt Degiorgio, Fabio Cuzzolin

Enabling computational systems with the ability to localize actions in video-based content has manifold applications.

Action Detection Multiple Instance Learning +2

End-to-End Video Captioning

no code implementations4 Apr 2019 Silvio Olivastri, Gurkirt Singh, Fabio Cuzzolin

The decoder is then optimised on such static features to generate the video's description.

Action Recognition Caption Generation +5

Recurrent Convolutions for Causal 3D CNNs

no code implementations17 Nov 2018 Gurkirt Singh, Fabio Cuzzolin

Recently, three dimensional (3D) convolutional neural networks (CNNs) have emerged as dominant methods to capture spatiotemporal representations in videos, by adding to pre-existing 2D CNNs a third, temporal dimension.

Action Detection

Predicting Action Tubes

no code implementations23 Aug 2018 Gurkirt Singh, Suman Saha, Fabio Cuzzolin

In this work, we present a method to predict an entire `action tube' (a set of temporally linked bounding boxes) in a trimmed video just by observing a smaller subset of it.

Action Classification Action Detection +1

Belief likelihood function for generalised logistic regression

no code implementations7 Aug 2018 Fabio Cuzzolin

The notion of belief likelihood function of repeated trials is introduced, whenever the uncertainty for individual trials is encoded by a belief measure (a finite random set).


TraMNet - Transition Matrix Network for Efficient Action Tube Proposals

1 code implementation1 Aug 2018 Gurkirt Singh, Suman Saha, Fabio Cuzzolin

At training time, transitions are specific to cell locations of the feature maps, so that a sparse (efficient) transition matrix is used to train the network.

Action Detection from a Robot-Car Perspective

no code implementations30 Jul 2018 Valentina Fontana, Gurkirt Singh, Stephen Akrigg, Manuele Di Maio, Suman Saha, Fabio Cuzzolin

We present the new Road Event and Activity Detection (READ) dataset, designed and created from an autonomous vehicle perspective to take action detection challenges to autonomous driving.

Action Detection Activity Detection +3

Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

no code implementations22 Jul 2017 Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

Current state-of-the-art human action recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame.

Action Recognition Instance Segmentation +2

AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture

no code implementations ICCV 2017 Suman Saha, Gurkirt Singh, Fabio Cuzzolin

As such, our 3D-RPN net is able to effectively encode the temporal aspect of actions by purely exploiting appearance, as opposed to methods which heavily rely on expensive flow maps.

Action Detection Region Proposal +1

Incremental Tube Construction for Human Action Detection

1 code implementation5 Apr 2017 Harkirat Singh Behl, Michael Sapienza, Gurkirt Singh, Suman Saha, Fabio Cuzzolin, Philip H. S. Torr

In this work, we introduce a real-time and online joint-labelling and association algorithm for action detection that can incrementally construct space-time action tubes on the most challenging action videos in which different action categories occur concurrently.

Action Detection

Online Real-time Multiple Spatiotemporal Action Localisation and Prediction

4 code implementations ICCV 2017 Gurkirt Singh, Suman Saha, Michael Sapienza, Philip Torr, Fabio Cuzzolin

To the best of our knowledge, ours is the first real-time (up to 40fps) system able to perform online S/T action localisation and early action prediction on the untrimmed videos of UCF101-24.

Early Action Prediction

Deep Learning for Detecting Multiple Space-Time Action Tubes in Videos

no code implementations4 Aug 2016 Suman Saha, Gurkirt Singh, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin

In stage 2, the appearance network detections are boosted by combining them with the motion detection scores, in proportion to their respective spatial overlap.

Action Detection Motion Detection +1

Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge

1 code implementation7 Jul 2016 Gurkirt Singh, Fabio Cuzzolin

We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification.

Activity Detection Binary Classification +4

Active Learning for Online Recognition of Human Activities from Streaming Videos

no code implementations11 Apr 2016 Rocco De Rosa, Ilaria Gori, Fabio Cuzzolin, Barbara Caputo, Nicolò Cesa-Bianchi

Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long.

Active Learning

Consistent transformations of belief functions

no code implementations30 Jul 2014 Fabio Cuzzolin

Consistent belief functions represent collections of coherent or non-contradictory pieces of evidence, but most of all they are the counterparts of consistent knowledge bases in belief calculus.

Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

no code implementations29 May 2014 Michael Sapienza, Fabio Cuzzolin, Philip H. S. Torr

The recent trend in action recognition is towards larger datasets, an increasing number of action classes and larger visual vocabularies.

Action Classification Action Recognition +2

Robust Temporally Coherent Laplacian Protrusion Segmentation of 3D Articulated Bodies

no code implementations26 May 2014 Fabio Cuzzolin, Diana Mateus, Radu Horaud

In an unsupervised context, i. e., no prior model of the moving object(s) is available, such a structure has to be learned from the data in a bottom-up fashion.

Cannot find the paper you are looking for? You can Submit a new open access paper.