Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Bace, Mihai"'
We present HAIFAI - a novel collaborative human-AI system to tackle the challenging task of reconstructing a visual representation of a face that exists only in a person's mind. Users iteratively rank images presented by the AI system based on their
Externí odkaz:
http://arxiv.org/abs/2412.06323
We present DiffGaze, a novel method for generating realistic and diverse continuous human gaze sequences on 360{\deg} images based on a conditional score-based denoising diffusion model. Generating human gaze on 360{\deg} images is important for vari
Externí odkaz:
http://arxiv.org/abs/2403.17477
We present User-predictable Face Editing (UP-FacE) -- a novel method for predictable face shape editing. In stark contrast to existing methods for face editing using trial and error, edits with UP-FacE are predictable by the human user. That is, user
Externí odkaz:
http://arxiv.org/abs/2403.13972
Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often difficult to obt
Externí odkaz:
http://arxiv.org/abs/2403.13653
Autor:
Penzkofer, Anna, Schaefer, Simon, Strohm, Florian, Bâce, Mihai, Leutenegger, Stefan, Bulling, Andreas
While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierarchical RL methods have increased sample efficiency by incorporating in
Externí odkaz:
http://arxiv.org/abs/2306.11483
Analysing and modelling interactive behaviour is an important topic in human-computer interaction (HCI) and a key requirement for the development of intelligent interactive systems. Interactive behaviour has a sequential (actions happen one after ano
Externí odkaz:
http://arxiv.org/abs/2303.16039
We propose Neuro-Symbolic Visual Dialog (NSVD) -the first method to combine deep learning and symbolic program execution for multi-round visually-grounded reasoning. NSVD significantly outperforms existing purely-connectionist methods on two key chal
Externí odkaz:
http://arxiv.org/abs/2208.10353
Publikováno v:
IEEE Transactions on Visualization and Computer Graphics, 2022, 28(12): 4995-5005
Despite its importance for assessing the effectiveness of communicating information visually, fine-grained recallability of information visualisations has not been studied quantitatively so far. In this work, we propose a question-answering paradigm
Externí odkaz:
http://arxiv.org/abs/2112.15217
We propose Unified Model of Saliency and Scanpaths (UMSS) -- a model that learns to predict visual saliency and scanpaths (i.e. sequences of eye fixations) on information visualisations. Although scanpaths provide rich information about the importanc
Externí odkaz:
http://arxiv.org/abs/2112.02340
Human-like attention as a supervisory signal to guide neural attention has shown significant promise but is currently limited to uni-modal integration - even for inherently multimodal tasks such as visual question answering (VQA). We present the Mult
Externí odkaz:
http://arxiv.org/abs/2109.13139