Object State Classification (OSC) is a critical task in computer vision, enabling systems to understand the functional state of objects. This work proposes a novel end-to-end architecture for OSC that leverages the inherent relationship between object classification and state recognition. Our approach first classifies the object and then uses object-specific attention mechanisms to focus on relevant features for state classification. This two-stage design allows the model to effectively capture object-state dependencies while maintaining modularity and flexibility. We conduct an extensive ablation study to analyze the impact of key parameters, such as attention mechanisms and loss weighting, and evaluate our method against three baselines across four benchmark datasets. Experimental results demonstrate that our approach outperforms competing methods by a significant margin, achieving state-of-the-art performance.

We investigate the problem of Object State Classification (OSC) in the context of zero-shot learning. Specifically, we propose the first method for Zero-shot Object-agnostic State Classification (OaSC) that, given an image, infers the state of a single object without relying on the knowledge or the estimation of the object class. In that direction, we capitalize on Knowledge Graphs (KGs) for structuring and organizing external knowledge, which, in combination with visual information, enable effective inference of the states of objects that have not been encountered in the training set. Having this unique property, a significant strength of our method is that it can handle an Open Set of object classes. We investigate the performance of OaSC in various datasets and settings, against several hypotheses and in comparison with state-of-the-art approaches for object attribute classification. OaSC outperforms these methods significantly across all benchmarks.1

Infusing autonomous artificial systems with knowledge about the physical world they inhabit is a critical and long-held aim for the Artificial Intelligence community. Training systems with relevant data is a typical approach; however, finding the data required is not always possible, especially when much of this knowledge is commonsense. In this paper, we present a comparison of topology-based and semantics-based methods for extracting information about object-action and object-state association relations from knowledge graphs, such as ConceptNet, WordNet, ATOMIC, YAGO, WebChild and DBpedia. Moreover, we propose a novel method for extracting information about object-action and object-state associations from knowledge graphs. Our method is composed of a set of techniques for locating, enriching, evaluating, cleaning and exposing knowledge from such resources, relying on semantic similarity methods. Some important aspects of our method are the flexibility in deciding how to deal with the noise that exists in the data, and the capability to determine the importance of a path through training, rather than through manual annotation.

A representational limitation of current argumentation frameworks is their inability to deal with sets of entities and their properties, for example to express that an argument is applicable for a specific set of entities that have a certain property and not applicable for all the others. In order to address this limitation, we recently introduced Abstract Argumentation Frameworks with Domain Assignments (AAFDs), which extend Abstract Argumentation Frameworks (AAFs) by assigning to each argument a domain of application, i.e., a set of entities for which the argument is believed to apply. We provided formal definitions of AAFDs and their semantics, showed with examples how this model can support various features of commonsense and non-monotonic reasoning, and studied its relation to AAFs. In this paper, aiming to provide a deeper insight into this new model, we present more results on the relation between AAFDs and AAFs and the properties of the AAFD semantics, and we introduce an alternative, more expressive way to define the domains of arguments using logical predicates. We also offer an implementation of AAFDs based on Answer Set Programming (ASP) and evaluate it using a range of experiments with synthetic datasets.

Abstract Abstract argumentation frameworks (AAFs), introduced by Dung (1995, Artif. Intell., 228, 321–357), enabled a new way of reasoning with arguments, which does not take into account the internal structure of arguments but only how they are related to each other. The only form of relation considered in AAFs is a binary attack relation on the set of arguments. From the definitions of acceptability semantics of AAFs, it is obvious that attacks actually have a dual role: on the one hand, they generate conflicts; on the other hand, they can defend other arguments from attacks. In this paper, we propose a framework, where the modeller can explicitly specify the role of each attack. For this purpose, we define a set of conflict-generating attacks ${\mathcal {R}_{C}}$ and a set of defending attacks ${\mathcal {R}_{d}}$, as well as a family of semantics that considers the role of each attack while determining which arguments are attacked, which are defended and which will be included in each extension. We study the formal properties of the proposed framework and semantics, show that our framework is a generalization of AAFs and assess its semantics against a set of principles. Finally, we present a web application that provides an interface for creating custom argumentation frameworks and uses ASP to compute their extensions.

The authors present a knowledge retrieval framework for the household domain enhanced with external knowledge sources that can argue over the information that it returns and learn new knowledge through an argumentation dialogue. The framework provides access to commonsense knowledge about household environments and performs semantic matching between entities from the web knowledge graph ConceptNet, using semantic knowledge from DBpedia and WordNet, with the ones existing in the knowledge graph. They offer a set of predefined SPARQL templates that directly address the ontology on which their knowledge retrieval framework is built and querying through SPARQL. The framework also features an argumentation component, where the user can argue against the answers of the knowledge retrieval component of the framework under two different scenarios: the missing knowledge scenario, where an entity should be in the answers, and the wrong knowledge scenario, where an entity should not be in the answers. This argumentation dialogue can end up in learning a new piece of knowledge when the user wins the dialogue.

Abstract Automatic deception detection is a crucial task that has many applications both in direct physical and in computer-mediated human communication. Our focus is on automatic deception detection in text across cultures. In this context, we view culture through the prism of the individualism/collectivism dimension, and we approximate culture by using country as a proxy. Having as a starting point recent conclusions drawn from the social psychology discipline, we explore if differences in the usage of specific linguistic features of deception across cultures can be confirmed and attributed to cultural norms in respect to the individualism/collectivism divide. In addition, we investigate if a universal feature set for cross-cultural text deception detection tasks exists. We evaluate the predictive power of different feature sets and approaches. We create culture/language-aware classifiers by experimenting with a wide range of n-gram features from several levels of linguistic analysis, namely phonology, morphology and syntax, other linguistic cues like word and phoneme counts, pronouns use, etc., and token embeddings. We conducted our experiments over eleven data sets from five languages (English, Dutch, Russian, Spanish, and Romanian), from six countries (United States of America, Belgium, India, Russia, Mexico, and Romania), and we applied two classification methods, namely logistic regression and fine-tuned BERT models. The results showed that the undertaken task is fairly complex and demanding. Furthermore, there are indications that some linguistic cues of deception have cultural origins and are consistent in the context of diverse domains and data set settings for the same language. This is more evident for the usage of pronouns and the expression of sentiment in deceptive language. The results of this work show that the automatic deception detection across cultures and languages cannot be handled in unified manners and that such approaches should be augmented with knowledge about cultural differences and the domains of interest.

Informal care is fundamental in the wellbeing and resilience of elderly and people with chronic conditions. However, solutions for the effective collaboration of healthcare professionals, patients and informal carers are not yet widely available. CareKeeper builds on a state-of-the-art personal health system, augmenting it with Artificial Intelligence and Big Data technologies, to boost informal care coordination. In this paper we report on the design of the platform with the aim of providing a light-weighted communication solution to support practical challenges about sharing the responsibility of caring, such as the frequency of visits, support to routinely activities and timely intervention in case of emergency and need.

Argumentative discourse rarely consists of opinions whose claims apply universally. As with logical statements, an argument applies to specific objects in the universe or relations among them, and may have exceptions. In this paper, we propose an argumentation formalism that allows associating arguments with a domain of application. Appropriate semantics are given, which formalise the notion of partial argument acceptance, i.e. the set of objects or relations that an argument can be applied to. We show that our proposal is in fact equivalent to the standard Argumentation Frameworks of Dung, but allows a more intuitive and compact expression of some core concepts of commonsense and non-monotonic reasoning, such as the scope of an argument, exceptions, relevance and others.

Consumers are largely unaware regarding the use being made to the data that they generate through smart devices, or their GDPR-compliance, since such information is typically hidden behind vague privacy policy documents, which are often lengthy, difficult to read (containing legal terms and definitions) and frequently changing. This paper describes the activities of the CAP-A project, whose aim is to apply crowdsourcing techniques to evaluate the privacy friendliness of apps, and to allow users to better understand the content of Privacy Policy documents and, consequently, the privacy implications of using any given mobile app. To achieve this, we developed a set of tools that aim at assisting users to express their own privacy concerns and expectations and assess the mobile apps’ privacy properties through collective intelligence.

The utilisation of personal data by mobile apps is often hidden behind vague Privacy Policy documents, which are typically lengthy, difficult to read (containing legal terms and definitions) and frequently changing. This paper discusses a suite of tools developed in the context of the CAP-A project, aiming to harness the collective power of users to improve their privacy awareness and to promote privacy-friendly behaviour by mobile apps. Through crowdsourcing techniques, users can evaluate the privacy friendliness of apps, annotate and understand Privacy Policy documents, and help other users become aware of privacy-related aspects of mobile apps and their implications, whereas developers and policy makers can identify trends and the general stance of the public in privacy-related matters. The tools are available for public use in: https://cap-a.eu/tools/.

Exploration and information identification constitute challenging research problems, with important applications in sensemaking over structured argumentative dialogues. In this paper, we present the implementation ArgQL, a high-level declarative query language, designed for querying dialogical data, structured in the principles of argumentation. We implement the language using an AIF-based representation and a translation of ArgQL into (complex) SPARQL queries. ArgQL provides a simple and intuitive way to query a structured dialogue using pure argumentative terminology.

Abstract Action languages have emerged as an important field of knowledge representation for reasoning about change and causality in dynamic domains. This paper presents Cerbere, a production system designed to perform online causal, temporal and epistemic reasoning based on the Event Calculus. The framework implements the declarative semantics of the underlying logic theories in a forward-chaining rule-based reasoning system, coupling the high expressiveness of its formalisms with the efficiency of rule-based systems. To illustrate its applicability, we present both the modeling of benchmark problems in the field, as well as its utilization in the challenging domain of smart spaces. A hybrid framework that combines logic-based with probabilistic reasoning has been developed, that aims to accommodate activity recognition and monitoring tasks in smart spaces.