1,721,120 research outputs found
A Multi-scale colour and Keypoint Density-based Approach for Visual Saliency Detection.
Full text linkIn the first seconds of observation of an image, several visual attention processes are involved in the identification of the visual targets that pop-out from the scene to our eyes. Saliency is the quality that makes certain regions of an image stand out from the visual field and grab our attention. Saliency detection models, inspired by visual cortex mechanisms, employ both colour and luminance features. Furthermore, both locations of pixels and presence of objects influence the Visual Attention processes. In this paper, we propose a new saliency method based on the combination of the distribution of interest points in the image with multiscale analysis, a centre bias module and a machine learning approach. We use perceptually uniform colour spaces to study how colour impacts on the extraction of saliency. To investigate eye-movements and assess the performances of saliency methods over object-based images, we conduct experimental sessions on our dataset ETTO (Eye Tracking Through Objects). Experiments show our approach to be accurate in the detection of saliency concerning state-of-the-art methods and accessible eye-movement datasets. The performances over object-based images are excellent and consistent on generic pictures. Besides, our work reveals interesting findings on some relationships between saliency and perceptually uniform colour spaces
Conceptual representations of actions for autonomous robots
No full textAn autonomous robot involved in long and complex missions should be able to generate, update and process its own plans of action. In this perspective, it is not plausible that the meaning of the representations used by the robot is given from outside the system itself. Rather, the meaning of internal symbols must be firmly anchored to the world through the perceptual abilities and the overall activities of the robot. According to these premises, in this paper we present an approach to action representation that is based on a "conceptual" level of representation, acting as an intermediate level between symbols and data coming from sensors. Symbolic representations are interpreted by mapping them on the conceptual level through a mapping mechanism based on artificial neural networks. Examples of the proposed framework are reported, based on experiments performed on a RWI-B12 autonomous robot. © 2001 Elsevier Science B.V
A neural architecture for segmentation and modelling of range data
No full textA novel, two stage, neural architecture for the segmentation of range data and their modeling with undeformed superquadrics is presented. The system is composed by two distinct neural stages: a SOM is used to perform data segmentation, and, for each segment, a multi-layer feed-forward network performs model estimation. The topology preserving nature of the SOM algorithm makes this architecture suited to cluster data with respect to sudden curvature variations. The second stage is designed to model and compute the inside-outside function of an undeformed superquadric in whatever attitude, starting form the (x, y, z) data triples. The network has been trained using backpropagation, and the weights arrangement, after training, represents a robust estimate of the superquadric parameters. The modelling network is compared also with a second implementation, which estimates separately the parameters of the 2D superellipses generating the 3D model. The whole architectural design is general, it can be extended to other geometric primitives for part-based object recognition, and performs faster than classical model fitting techniques. Detailed explanation of the theoretical approach, along with some experiments with real data are reported
CHILab at HaSpeeDe3: Overview of the Taks A Textual
Full text linkThis technical report illustrates the system developed by the CHILab team for the competition HaSpeeDe3 as part of the EVALITA 2023 campaign. The key idea for HaSpeeDe3 task A - Political Hate Speech Detection - Textual, was to develop different systems arranged as suitable combinations of the Pre-Trained Language Model (PTLM) used for embedding extraction, neural architectures for further elaborations over the embeddings and a classifier. In particular, dense layers, LSTM, BiLSTM and Transformers were used. The best performing system across the ones investigated in this report was made by embeddings extracted via XLM-RoBERTa coupled with BiLSTM that reaches a macro-F1 score of 0.876
Conditioning Chat-GPT for Information Retrieval: The Unipa-GPT Case Study
Full text linkThis paper illustrates the architecture and training of Unipa-GPT, a Large Language Model based chatbot developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers' Night SHARPER event. In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported
CHILab at HODI: A minimalist approach
Full text linkThis technical report illustrates the system developed by the CHILab team for the competition HODI at EVALITA 2023. The key idea of the method we proposed for the HODI Subtask A - Homotransphobia detection, was to develop different systems arranged as suitable combinations of Pre-Trained Language Model (PTLM) for embedding extraction, neural architectures for further elaborations over the embeddings and a classifier. In particular dense layers, LSTM, BiLSTM and Transformers were used as neural architectures. The best performing system across the ones investigated in this report was made by embeddings extracted via AlBERTo coupled with a Transformer that reaches a macro-F1 score of 0.753
Recent advances of HCI in decision-making tasks for optimized clinical workflows and precision medicine
Full text linkThe ever-increasing amount of biomedical data is enabling new large-scale studies, even though ad hoc computational solutions are required. The most recent Machine Learning (ML) and Artificial Intelligence (AI) techniques have been achieving outstanding performance and an important impact in clinical research, aiming at precision medicine, as well as improving healthcare workflows. However, the inherent heterogeneity and uncertainty in the healthcare information sources pose new compelling challenges for clinicians in their decision-making tasks. Only the proper combination of AI and human intelligence capabilities, by explicitly taking into account effective and safe interaction paradigms, can permit the delivery of care that outperforms what either can do separately. Therefore, Human-Computer Interaction (HCI) plays a crucial role in the design of software oriented to decision-making in medicine. In this work, we systematically review and discuss several research fields strictly linked to HCI and clinical decision-making, by subdividing the articles into six themes, namely: Interfaces, Visualization, Electronic Health Records, Devices, Usability, and Clinical Decision Support Systems. However, these articles typically present overlaps among the themes, revealing that HCI inter-connects multiple topics. With the goal of focusing on HCI and design aspects, the articles under consideration were grouped into four clusters. The advances in AI can effectively support the physicians’ cognitive processes, which certainly play a central role in decision-making tasks because the human mental behavior cannot be completely emulated and captured; the human mind might solve a complex problem even without a statistically significant amount of data by relying upon domain knowledge. For this reason, technology must focus on interactive solutions for supporting the physicians effectively in their daily activities, by exploiting their unique knowledge and evidence-based reasoning, as well as improving the various aspects highlighted in this review
Convolutional architectures for virtual screening
Full text linkBackground: A Virtual Screening algorithm has to adapt to the different stages of this process. Early screening needs to ensure that all bioactive compounds are ranked in the first positions despite of the number of false positives, while a second screening round is aimed at increasing the prediction accuracy. Results: A novel CNN architecture is presented to this aim, which predicts bioactivity of candidate compounds on CDK1 using a combination of molecular fingerprints as their vector representation, and has been trained suitably to achieve good results as regards both enrichment factor and accuracy in different screening modes (98.55% accuracy in active-only selection, and 98.88% in high precision discrimination). Conclusion: The proposed architecture outperforms state-of-the-art ML approaches, and some interesting insights on molecular fingerprints are devised
- …
