Francesca Palermo

Francesca Palermo, Bukeikhan Omarali, Changae Oh et al.

This paper presents a novel algorithm for crack localisation and detection based on visual and tactile analysis via fibre-optics. A finger-shaped sensor based on fibre-optics is employed for the data acquisition to collect data for the analysis and the experiments. To detect the possible locations of cracks a camera is used to scan an environment while running an object detection algorithm. Once the crack is detected, a fully-connected graph is created from a skeletonised version of the crack. A minimum spanning tree is then employed for calculating the shortest path to explore the crack which is then used to develop the motion planner for the robotic manipulator. The motion planner divides the crack into multiple nodes which are then explored individually. Then, the manipulator starts the exploration and performs the tactile data classification to confirm if there is indeed a crack in that location or just a false positive from the vision algorithm. If a crack is detected, also the length, width, orientation and number of branches are calculated. This is repeated until all the nodes of the crack are explored. In order to validate the complete algorithm, various experiments are performed: comparison of exploration of cracks through full scan and motion planning algorithm, implementation of frequency-based features for crack classification and geometry analysis using a combination of vision and tactile data. From the results of the experiments, it is shown that the proposed algorithm is able to detect cracks and improve the results obtained from vision to correctly classify cracks and their geometry with minimal cost thanks to the motion planning algorithm.

Yushan Huang, Yuchen Zhao, Alexander Capstick et al.

Current methods for pattern analysis in time series mainly rely on statistical features or probabilistic learning and inference methods to identify patterns and trends in the data. Such methods do not generalize well when applied to multivariate, multi-source, state-varying, and noisy time-series data. To address these issues, we propose a highly generalizable method that uses information theory-based features to identify and learn from patterns in multivariate time-series data. To demonstrate the proposed approach, we analyze pattern changes in human activity data. For applications with stochastic state transitions, features are developed based on Shannon's entropy of Markov chains, entropy rates of Markov chains, entropy production of Markov chains, and von Neumann entropy of Markov chains. For applications where state modeling is not applicable, we utilize five entropy variants, including approximate entropy, increment entropy, dispersion entropy, phase entropy, and slope entropy. The results show the proposed information theory-based features improve the recall rate, F1 score, and accuracy on average by up to 23.01% compared with the baseline models and a simpler model structure, with an average reduction of 18.75 times in the number of model parameters.

Alexander Capstick, Francesca Palermo, Tianyu Cui et al.

When data is generated by multiple sources, conventional training methods update models assuming equal reliability for each source and do not consider their individual data quality. However, in many applications, sources have varied levels of reliability that can have negative effects on the performance of a neural network. A key issue is that often the quality of the data for individual sources is not known during training. Previous methods for training models in the presence of noisy data do not make use of the additional information that the source label can provide. Focusing on supervised learning, we aim to train neural networks on each data source for a number of steps proportional to the source's estimated reliability by using a dynamic re-weighting strategy motivated by likelihood tempering. This way, we allow training on all sources during the warm-up and reduce learning on less reliable sources during the final training stages, when it has been shown that models overfit to noise. We show through diverse experiments that this can significantly improve model performance when trained on mixtures of reliable and unreliable data sources, and maintain performance when models are trained on reliable sources only.

Vladimir Iashin, Francesca Palermo, Gökhan Solak et al.

Human-robot object handover is a key skill for the future of human-robot collaboration. CORSMAL 2020 Challenge focuses on the perception part of this problem: the robot needs to estimate the filling mass of a container held by a human. Although there are powerful methods in image processing and audio processing individually, answering such a problem requires processing data from multiple sensors together. The appearance of the container, the sound of the filling, and the depth data provide essential information. We propose a multi-modal method to predict three key indicators of the filling mass: filling type, filling level, and container capacity. These indicators are then combined to estimate the filling mass of a container. Our method obtained Top-1 overall performance among all submissions to CORSMAL 2020 Challenge on both public and private subsets while showing no evidence of overfitting. Our source code is publicly available: https://github.com/v-iashin/CORSMAL

Agnese Taluzzi, Davide Gesualdi, Riccardo Santambrogio et al.

This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchmark, and their combination within our framework results in an overall accuracy of 44.21% on the challenge, highlighting its effectiveness for complex egocentric VQA tasks.

Hamta Sedghani, Abednego Wamuhindo Kambale, Federica Filippini et al.

Extended reality technologies are transforming fields such as healthcare, entertainment, and education, with Smart Eye-Wears (SEWs) and Artificial Intelligence (AI) playing a crucial role. However, SEWs face inherent limitations in computational power, memory, and battery life, while offloading computations to external servers is constrained by network conditions and server workload variability. To address these challenges, we propose a Federated Reinforcement Learning (FRL) framework, enabling multiple agents to train collaboratively while preserving data privacy. We implemented synchronous and asynchronous federation strategies, where models are aggregated either at fixed intervals or dynamically based on agent progress. Experimental results show that federated agents exhibit significantly lower performance variability, ensuring greater stability and reliability. These findings underscore the potential of FRL for applications requiring robust real-time AI processing, such as real-time object detection in SEWs.

Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo et al.

The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails to adapt to their varying complexity. Dynamic, instance-based mixed-precision quantization promises a superior accuracy-efficiency trade-off by allocating higher precision only when needed. However, a critical bottleneck remains: existing methods require a costly dequantize-to-float and requantize-to-integer cycle to change precision, breaking the integer-only hardware paradigm and compromising performance gains. This paper introduces Dynamic Quantization Training (DQT), a novel framework that removes this bottleneck. At the core of DQT is a nested integer representation where lower-precision values are bit-wise embedded within higher-precision ones. This design, coupled with custom integer-only arithmetic, allows for on-the-fly bit-width switching through a near-zero-cost bit-shift operation. This makes DQT the first quantization framework to enable both dequantization-free static mixed-precision of the backbone network, and truly efficient dynamic, instance-based quantization through a lightweight controller that decides at runtime how to quantize each layer. We demonstrate DQT state-of-the-art performance on ResNet18 on CIFAR-10 and ResNet50 on ImageNet. On ImageNet, our 4-bit dynamic ResNet50 achieves 77.00% top-1 accuracy, an improvement over leading static (LSQ, 76.70%) and dynamic (DQNET, 76.94%) methods at a comparable BitOPs budget. Crucially, DQT achieves this with a bit-width transition cost of only 28.3M simple bit-shift operations, a drastic improvement over the 56.6M costly Multiply-Accumulate (MAC) floating-point operations required by previous dynamic approaches - unlocking a new frontier in efficient, adaptive AI.

Francesca Palermo, Honglin Li, Alexander Capstick et al.

Agitation is one of the neuropsychiatric symptoms with high prevalence in dementia which can negatively impact the Activities of Daily Living (ADL) and the independence of individuals. Detecting agitation episodes can assist in providing People Living with Dementia (PLWD) with early and timely interventions. Analysing agitation episodes will also help identify modifiable factors such as ambient temperature and sleep as possible components causing agitation in an individual. This preliminary study presents a supervised learning model to analyse the risk of agitation in PLWD using in-home monitoring data. The in-home monitoring data includes motion sensors, physiological measurements, and the use of kitchen appliances from 46 homes of PLWD between April 2019-June 2021. We apply a recurrent deep learning model to identify agitation episodes validated and recorded by a clinical monitoring team. We present the experiments to assess the efficacy of the proposed model. The proposed model achieves an average of 79.78% recall, 27.66% precision and 37.64% F1 scores when employing the optimal parameters, suggesting a good ability to recognise agitation events. We also discuss using machine learning models for analysing the behavioural patterns using continuous monitoring data and explore clinical applicability and the choices between sensitivity and specificity in-home monitoring applications.

Alessio Xompero, Santiago Donaher, Vladimir Iashin et al.

The contactless estimation of the weight of a container and the amount of its content manipulated by a person are key pre-requisites for safe human-to-robot handovers. However, opaqueness and transparencies of the container and the content, and variability of materials, shapes, and sizes, make this estimation difficult. In this paper, we present a range of methods and an open framework to benchmark acoustic and visual perception for the estimation of the capacity of a container, and the type, mass, and amount of its content. The framework includes a dataset, specific tasks and performance measures. We conduct an in-depth comparative analysis of methods that used this framework and audio-only or vision-only baselines designed from related works. Based on this analysis, we can conclude that audio-only and audio-visual classifiers are suitable for the estimation of the type and amount of the content using different types of convolutional neural networks, combined with either recurrent neural networks or a majority voting strategy, whereas computer vision methods are suitable to determine the capacity of the container using regression and geometric approaches. Classifying the content type and level using only audio achieves a weighted average F1-score up to 81% and 97%, respectively. Estimating the container capacity with vision-only approaches and estimating the filling mass with audio-visual multi-stage approaches reach up to 65% weighted average capacity and mass scores. These results show that there is still room for improvement on the design of new methods. These new methods can be ranked and compared on the individual leaderboards provided by our open framework.