TY - GEN A1 - Castillo, Susana A1 - Wallraven, Christian A1 - Cunningham, Douglas William T1 - The Semantic space for facial communication T2 - Computer Animation and Virtual Worlds Y1 - 2014 UR - http://onlinelibrary.wiley.com/doi/10.1002/cav.1593/abstract U6 - https://doi.org/10.1002/cav.1593 SN - 1546-427X VL - 25 IS - 3-4 SP - 223 EP - 231 ER - TY - GEN A1 - Fotsing, Cedrique A1 - Cunningham, Douglas William ED - Andres, Bjoern ED - Campen, Marcel ED - Sedlmair, Michael T1 - Context Aware Exemplar-based Image Inpainting using Irregular Patches T2 - Vision, Modeling, and Visualization N2 - We propose a new exemplar-based image inpainting method in this paper. Our method is based on the Criminisi pipeline. We focused on three main stages of the pipeline; calculation of priorities, construction of patches, and the search for the best match. To assign a high priority to patches constructed from the edge pixels, we use the ability of segmentation algorithms to divide an image into different texture blocks. The patches built from pixels located at the border between several texture blocks receive a high priority. Unlike most patch-based image inpainting methods which use regular patches (rectangle, square), the shape and size of our patches depend on the textural composition around the original pixel. The patches are built using a region growing principle in the different texture blocs around the original pixel. The search for the best match is done contextually. We search for the best match of the patch with the highest priority in a similar environment to its neighborhood around the target zone. The method is simple and easy to implement. The experiments show that our method obtains more plausible results than the basic method of Criminisi and its improved version Amoeba in most cases. KW - Capturing KW - Rendering Y1 - 2021 UR - https://diglib.eg.org/handle/10.2312/vmv20211373 SN - 978-3-03868-161-8 U6 - https://doi.org/10.2312/vmv.20211373 SP - 71 EP - 81 PB - The Eurographics Association ET - 1. Auflage ER - TY - GEN A1 - Schorradt, Martin T. A1 - Castillo, Susana A1 - Cunningham, Douglas William T1 - The Semantic Space for Emotional Speech and the Influence of Different Methods for Prosody Isolation on Its Perception T2 - SAP '18: Proceedings of the 15th ACM Symposium on Applied Perception Y1 - 2018 SN - 978-1-4503-5894-1 U6 - https://doi.org/10.1145/3225153.3225156 SP - 1 EP - 8 PB - Association for Computing Machinery CY - New York, NY, United States ER - TY - GEN A1 - Hahn, Philipp A1 - Castillo, Susana A1 - Cunningham, Douglas William T1 - Fitting the Style: The Semantic Space for Emotions on Stylized Faces T2 - CASA '19: Proceedings of the 32nd International Conference on Computer Animation and Social Agents Y1 - 2019 SN - 978-1-4503-7159-9 U6 - https://doi.org/10.1145/3328756.3328770 SP - 21 EP - 24 PB - Association for Computing Machinery CY - New York, NY, United States ER - TY - GEN A1 - Legde, Katharina A1 - Cunningham, Douglas William T1 - Evaluating the Effect of Clothing and Environment on the Perceived Personality of Virtual Avatars T2 - IVA '19: ACM International Conference on Intelligent Virtual Agents Y1 - 2019 SN - 978-1-4503-6672-4 U6 - https://doi.org/10.1145/3308532.3329425 SP - 206 EP - 208 PB - Association for Computing Machinery CY - New York, USA ER - TY - GEN A1 - Koulieris, George Alex A1 - Drettakis, George A1 - Cunningham, Douglas William A1 - Sidorakis, Nikolaos A1 - Mania, Katerina T1 - Context-awarematerial selective rendering for mobile graphics Y1 - 2014 SN - 978-1-4503-2958-3 U6 - https://doi.org/10.1145/2614217.2614246 N1 - Proceedings, SIGGRAPH '14 ACM SIGGRAPH 2014 Posters PB - ACM CY - New York, NY ER - TY - GEN A1 - Koulieris, George Alex A1 - Drettakis, George A1 - Cunningham, Douglas William A1 - Mania, Katerina T1 - C-lod: Context-aware material level-of-detail applied to mobile graphics T2 - Computer Graphics Forum Y1 - 2014 U6 - https://doi.org/10.1111/cgf.12411 SN - 1467-8659 N1 - Proceedings of the Eurographics Symposium on Rendering VL - 33 IS - 4 SP - 41 EP - 49 ER - TY - GEN A1 - Koulieris, George Alex A1 - Drettakis, George A1 - Cunningham, Douglas William T1 - An automated high level saliency predictor for smart gane balancing T2 - ACM Transactions on Applied Perception : (TAP) Y1 - 2014 SN - 1544-3965 VL - 11 IS - 4 SP - 17-1 EP - 17-21 ER - TY - GEN A1 - Castillo, Susana A1 - Wallraven, Christian A1 - Cunningham, Douglas William T1 - The semantic space for facial communication T2 - Computer Animation and Virtual Worlds Y1 - 2014 SN - 1546-427X VL - 25 IS - 3-4 SP - 223 EP - 231 ER - TY - GEN A1 - Schorradt, Martin T. A1 - Cunningham, Douglas William ED - Tumuluri, Raj ED - Sebe, Nicu ED - Pingali, Gopal ED - Jayagopi, Dinesh Babu ED - Dhall, Abhinav ED - Singh, Richa ED - Anthony, Lisa ED - Salah, Albert Ali T1 - Age Regression for Human Voices T2 - ICMI '22: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION Bengaluru India November 7 - 11, 2022 N2 - The human voice is one of our most important tools for communicating with other people. Besides pure semantic meaning it also conveys syntactical information such as emphasis as well as personal information such as emotional state, gender, and age. While the physical changes that occur to a person’s voice are well studied, there is surprisingly little work on the perception of those changes. To hold the range of subtleties present in a given utterance constant and thus focus on the changes caused by age, this paper takes adult recordings (three males, and three females) and artificially resynthesizes them (using values from measurements of real children’s voices) to create a childlike versions of the utterance at different target ages. In particular, we focus on a systematic, factorial combination pitch shifting and formant shifting. To get an insight about the influence of these factors on the estimated age, we performed a perceptual experiment. Since the resynthesis method we used can produce a wide range of voices, not all of which are physically consistent, we also asked the participants to rate how natural the voices sounded. Furthermore, since former studies suggest that people are not able to distinguish between males and females of young ages, participants were also asked to rate how male or female the voices sounded. Overall, we found that although the synthesis method produced physically plausible signals (compared average values for real children), the degree of signal manipulation was correlated with perceived unnaturalness. We also found that pitch shift had only a small affect on perceived age, that formant shift had a strong affect on perceived age, and that these effects depended on the original gender of the recording. As expected, people had difficulty guessing the gender of younger sounding voices. KW - Age Synthesis KW - Age Regression KW - Speech Synthesis KW - Speech Processing Y1 - 2022 SN - 978-1-4503-9390-4 U6 - https://doi.org/10.1145/3536221.3556599 SP - 570 EP - 578 PB - Association for Computing Machinery New York NY United States ER -