Browse ORBilu by Open Access
- What it is and what it isn't
- Green Road / Gold Road?
- Ready to Publish. Now What?
- How can I support the OA movement?
- Where can I learn more?
ORBilu is a project developed by
|
Results 1-20 of 27.
((uid:50043202))
1
2
   Together Yet Apart: Multimodal Representation Learning for Personalised Visual Art RecommendationYilma, Bereket Abera  ; Leiva, Luis A. in Yilma, Bereket Abera; Leiva, Luis A. (Eds.) Proceedings of the ACM Conference on User Modeling, Adaptation and Personalization (UMAP 2023) (2023, June 26) With the advent of digital media, the availability of art content has greatly expanded, making it increasingly challenging for individuals to discover and curate works that align with their personal ... [more ▼] With the advent of digital media, the availability of art content has greatly expanded, making it increasingly challenging for individuals to discover and curate works that align with their personal preferences and taste. The task of providing accurate and personalised Visual Art (VA) recommendations is thus a complex one, requiring a deep understanding of the intricate interplay of multiple modalities such as images, textual descriptions, or other metadata. In this paper, we study the nuances of modalities involved in the VA domain (image and text) and how they can be effectively harnessed to provide a truly personalised art experience to users. Particularly, we develop four fusion-based multimodal VA recommendation pipelines and conduct a large-scale user-centric evaluation. Our results indicate that early fusion (i.e, joint multimodal learning of visual and textual features) is preferred over a late fusion of ranked paintings from unimodal models (state-of-the-art baselines) but only if the latent representation space of the multimodal painting embeddings is entangled. Our findings open a new perspective for a better representation learning in the VA RecSys domain. [less ▲] Detailed reference viewed: 178 (29 UL)Let’s Talk it through, anew: Promises and Pitfalls of Customisable Conversational Reflection SupportDubiel, Mateusz ; Leiva, Luis A. Scientific Conference (2023, April 28) As modern lifestyles are becoming increasingly stressful and ever more hectic with multiple stimuli constantly competing for our attention, Affective Disorders (ADs) such as anxiety and depression are on ... [more ▼] As modern lifestyles are becoming increasingly stressful and ever more hectic with multiple stimuli constantly competing for our attention, Affective Disorders (ADs) such as anxiety and depression are on the rise. Consequently, due to the burgeoning demand for counseling and therapeutic services, many people who suffer from ADs are struggling to timely access the professional support that they require. To address this problem, voice-enabled Conversational Agents (CAs) have been recently proposed as tools for supporting self-reflection and providing assistance in managing a range of ADs through synthetic voices. However, despite their therapeutic potential, CAs offer a very limited choice when it comes to selection and personalisation of synthetic voices used. The goal of this paper is two-fold: (1) it discusses the potential benefits that a CA’s voice customisation can bring to enhance user engagement and promote long term self-reflection, and (2) it offers reflection on the corresponding challenges associated to this approach. [less ▲] Detailed reference viewed: 74 (2 UL)The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of PaintingsYilma, Bereket Abera ; Leiva, Luis A. in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ’23) (2023, April) Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and ... [more ▼] Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and cognitive reflections they may trigger in users. In this paper, we focus on efficiently capturing the elements (i.e., latent semantic relationships) of visual art for personalized recommendation. We propose and study recommender systems based on textual and visual feature learning techniques, as well as their combinations. We then perform a small-scale and a large-scale user-centric evaluation of the quality of the recommendations. Our results indicate that textual features compare favourably with visual ones, whereas a fusion of both captures the most suitable hidden semantic relationships for artwork recommendation. Ultimately, this paper contributes to our understanding of how to deliver content that suitably matches the user's interests and how they are perceived. [less ▲] Detailed reference viewed: 271 (73 UL)Is it Worth Attending Classes in-person? A Post-COVID Study in ICT University CoursesCapozucca, Alfredo ; Leiva, Luis A. Presentation (2023, January 23) Detailed reference viewed: 31 (3 UL)UEyes: Understanding Visual Saliency across User Interface Types; Leiva, Luis A. ; Houssel, Paul Robert Balthazar et alin Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI) (2023) Detailed reference viewed: 76 (7 UL)Gustav: Cross-device Cross-computer Synchronization of Sensory SignalsLatifzadeh, Kayhan ; Leiva, Luis A. in Adjunct Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (2022) Detailed reference viewed: 55 (20 UL)A Contextual Framework for Adaptive User Interfaces: Modelling the Interaction EnvironmentDubiel, Mateusz ; Yilma, Bereket Abera ; Latifzadeh, Kayhan et alScientific Conference (2022) Detailed reference viewed: 103 (22 UL)Conversational Agents Trust Calibration: A User-Centred Perspective to DesignDubiel, Mateusz ; ; Leiva, Luis A. in Conversational Agents Trust Calibration: A User-Centred Perspective to Design (2022) Previous work identified trust as one of the key requirements for adoption and continued use of conversational agents (CAs). Given recent advances in natural language processing and deep learning, it is ... [more ▼] Previous work identified trust as one of the key requirements for adoption and continued use of conversational agents (CAs). Given recent advances in natural language processing and deep learning, it is currently possible to execute simple goal-oriented tasks by using voice. As CAs start to provide a gateway for purchasing products and booking services online, the question of trust and its impact on users’ reliance and agency becomes ever-more pertinent. This paper collates trust-related literature and proposes four design suggestions that are illustrated through example conversations. Our goal is to encourage discussion on ethical design practices to develop CAs that are capable of employing trust-calibration techniques that should, when relevant, reduce the user’s trust in the agent. We hope that our reflections, based on the synthesis of insights from the fields of human-agent interaction, explainable ai, and information retrieval, can serve as a reminder of the dangers of excessive trust in automation and contribute to more user-centred CA design. [less ▲] Detailed reference viewed: 103 (16 UL)Describing UI Screenshots in Natural LanguageLeiva, Luis A. ; ; in ACM Transactions on Intelligent Systems and Technology (2022) Detailed reference viewed: 45 (1 UL)Learning GUI Completions with User-defined Constraints; Leiva, Luis A. ; in ACM Transactions on Interactive Intelligent Systems (2022), 12(1), Detailed reference viewed: 90 (13 UL)Artificial Intelligence and Machine Learning - 33rd Benelux Conference on Artificial Intelligence, BNAIC/Benelearn 2021, Esch-sur-Alzette, Luxembourg, November 10-12, 2021, Revised Selected Papers.Leiva, Luis A. ; Pruski, Cedric ; Markovich, Réka et alBook published by Springer (2022) Detailed reference viewed: 73 (1 UL)Modeling How Different User Groups Perceive Webpage AestheticsLeiva, Luis A. ; ; in Universal Access in the Information Society (2022) Detailed reference viewed: 44 (2 UL)Debiased Label Aggregation for Subjective Crowdsourcing Tasks; ; et al in Extended Abstracts of the SIGCHI Conference on Human Factors in Computing Systems (CHI EA) (2022) Detailed reference viewed: 45 (2 UL)Robust and Deployable Gesture Recognition for Smartwatches; ; et al in Proceedings of the ACM Conference on Intelligent User Interfaces (IUI) (2022) Detailed reference viewed: 41 (2 UL)Solids on Soli: Millimetre-Wave Radar Sensing through Materials; ; et al in Proceedings of the ACM on Human-Computer Interaction (2022) Detailed reference viewed: 89 (8 UL)Attentive Sequence-to-Sequence Modeling of Stroke Gestures Articulation Performance; Leiva, Luis A. in IEEE Transactions on Human-Machine Systems (2021), 51(6), Detailed reference viewed: 67 (2 UL)My Mouse, My Rules: Privacy Issues of Behavioral User Profiling via Mouse TrackingLeiva, Luis A. ; ; in Proceedings of ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR) (2021) Detailed reference viewed: 154 (13 UL)Interactive Exploration of Large-scale UI Datasets with Design MapsLeiva, Luis A. ; ; in Interacting with Computers (2021) Detailed reference viewed: 78 (8 UL)When Choice Happens: A Systematic Examination of Mouse Movement Length for Decision Making in Web Search; ; Leiva, Luis A. in Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) (2021) Detailed reference viewed: 217 (16 UL)Proceedings of BNAIC/BeneLearn 2021Leiva, Luis A. ; Pruski, Cedric ; Markovich, Réka et alBook published by BnL (2021) Detailed reference viewed: 232 (33 UL)
1
2
|
||
