https://sihwapark.com Sihwa Park Sat, 26 Apr 2025 10:31:08 +0000 https://sihwapark.com en https://sihwapark.com/Home Sun, 11 Jun 2023 18:14:10 +0000 Sihwa Park https://sihwapark.com/Home https://sihwapark.com/News Mon, 12 Jun 2023 01:11:46 +0000 Sihwa Park https://sihwapark.com/News News Oct 1 , 2026: My journal article,&nbsp;An Exploratory Analytical Framework for Artificial Intelligence-Driven Interactive Art Installations, was published in Multimodal Technologies and Interaction (MTI). Jul 22 , 2026: I gave an artist talk at the SIGGRAPH 2026. Jul 20 , 2026: Diffusion TV was exhibited at the SIGGRAPH 2026 Art Gallery. Jul 13, 2026: I gave a presentation on Diffusion TV at the ACM C&amp;C 2026 XAIxArts Workshop. Jun 8, 2026: A Spotlight interview on&nbsp;Diffusion TV was published on&nbsp;the SIGGRAPH Blog. May 19, 2026: Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction&nbsp;was accepted for the ACM C&amp;C 2026 XAIxArts Workshop. Apr 23, 2026: Diffusion TV was accepted for the SIGGRAPH 2026 Art Gallery.Apr 13, 2026: I gave an invited artist talk at the School of Art and Design, San Diego State University (online). Dec 17, 2025: Diffusion TV was selected as an honoree for the AI Creative Futures Awards (AICA) 2025. Oct 6, 2025: Diffusion TV was exhibited at the Connected Minds Conference 2025 Arts Reception. Jun 13, 2025: Diffusion TV was exhibited at CVPR 2025 AI Art Gallery (On-site display and online) as one of the shortlisted artworks. May 23, 2025: Diffusion TV was exhibited at ISEA 2025. Apr 8, 2025: Diffusion TV was accepted for CVPR 2025 AI Art Gallery (On-site display and online). Dec 11, 2024: Diffusion TV was accepted for the ISEA 2025 Exhibition. Aug 30, 2024: I performed in Exit Points#52 at Arraymusic, Toronto. Apr 7, 2024: YouTube Mirror was accepted for CVPR 2024 AI Art Gallery (Online). Oct 24, 2023: I was appointed a Connected Minds Research Enhanced Hire position with a $100,000 CAD startup fund. Sep 1, 2023: YouTube Mirror was presented at AIMC 2023, Brighton, UK. Jun 12, 2023: YouTube Mirror was accepted for AIMC 2023 as both a paper and an installation. May 31, 2023: YouTube Mirror was exhibited at NIME 2023, Mexico City, Mexico. https://sihwapark.com/MAIAP Sat, 26 Apr 2025 10:31:08 +0000 Sihwa Park https://sihwapark.com/MAIAP (WIP) MAIAP: Multimodal AI-based Interface for Audiovisual Performance Date: July 2024-Categories: AI Art, Audiovisual Interface, Audiovisual Performance, Generative I have been working on designing a novel interface for utilizing image and sound AI models in audiovisual performance. As an early experiment, I created a prototype that generates images and sounds with pre-trained models in response to real-time webcam and mic input. The prototype was demonstrated in one of Exit Points' performances on August 30, 2024 at Arraymusic, which was organized by Michael Palumbo. The prototype uses SpecVQGAN for sound generation and StreamDiffusion with Stable Diffusion XL Turbo for image generation, both with modifications. Exit Points #52 Ensemble 2 Performance Footage My Sound Generated Exit Points #52 Switchemups Session (Visualization Only) Credit for the performance MAYSUN: Percussion, ElectronicsDanika Lorén: OperaEmmanuel Lacopo: Electric GuitarMichael Palumbo: Modular SynthSihwa Park: AI-generated Sound, VisualizationVideo and audio recordings for the first video were provided courtesy of Arraymusic and Michael Palumbo.All audio tracks of this performance are avaialbe at Bandcamp.&nbsp; This project is undertaken thanks in part to funding from the Connected Minds Program, supported by Canada First Research Excellence Fund, Grant #CFREF-2022-00010. Next ︎︎︎ https://sihwapark.com/Diffusion-TV Tue, 28 Jan 2025 05:30:31 +0000 Sihwa Park https://sihwapark.com/Diffusion-TV Diffusion TV Date: May 2025Categories: AI Art, Audiovisual Installation, Generative Diffusion TV is an experimental and interactive interface that invites audiences to explore the hidden processes of AI through a nostalgic CRT TV interface, allowing them to engage directly with diffusion models, the technology behind today’s most sophisticated AI-generated images and sounds. Inspired by Nam June Paik’s Egg Grows (1984–1989), which depicts the illusion of an egg growing through a series of progressively larger CRT TVs, Diffusion TV uses the old CRT TV to reveal the hidden process of AI denoising, transforming the complexity of AI diffusion models into a tangible, interactive experience. The work allows viewers to directly engage with the transformative process of turning chaotic data into recognizable images and sounds by adjusting the TV’s antenna and knobs, fostering a deeper connection between human interaction and technological transformation. By turning the knob, viewers can switch between three channels: Past, Present, and Future. The Past channel focuses on extinct animals to reflect on what has already disappeared, evoking a sense of loss and remembrance. The Present highlights the fragility of endangered species, offering a moment of reflection on the current environmental crisis. The Future channel displays speculative animals imagined with AI, encouraging contemplation about where humanity and technology are headed. Each channel presents audiovisual content generated by AI models such as Stable Diffusion XL and Stable Audio Open, dynamically adapting to the viewer’s adjustments. By adjusting the antenna, the audience gradually brings the animals into clearer focus, metaphorically remembering, preserving, or exploring their existence. Once the clearest image and sound of an animal are revealed, the process resets after a few seconds, returning to a noisy and unclear depiction of another animal, keeping the experience dynamic and ever-evolving. Like television programming, Diffusion TV continuously renews its content by regenerating the images and sounds of the animals at regular intervals.Diffusion TV explores how technology can shape our understanding of the natural world. Using the CRT TV, once an emblem of cutting-edge innovation but now a metaphor for obsolescence, the work mirrors the fragility of endangered species and asks what is preserved and what is lost in the pursuit of technological advancement. Through a more experiential, interactive understanding of AI’s inner workings, Diffusion TV encourages audiences to contemplate the interconnected relationships between humanity, technology, and nature. This project was undertaken thanks in part to funding from the Connected Minds Program, supported by Canada First Research Excellence Fund, Grant #CFREF-2022-00010.Diffusion TV at ISEA 2025, Hangaram Design Museum, Seoul, KoreaDiffusion TV was exhibited at ISEA 2025 as one of 39 juried artworks selected from 355 submissions (&lt; 11% acceptance rate). <img width="5712" height="3213" width_o="5712" height_o="3213" data-src="https://freight.cargo.site/t/original/i/dc47de372d4c3716b0242256de3b293847824bd59657c044b13e3f65860753ff/IMG_1771.jpeg" data-mid="234087225" border="0" src="https://freight.cargo.site/w/1000/i/dc47de372d4c3716b0242256de3b293847824bd59657c044b13e3f65860753ff/IMG_1771.jpeg" /><img width="3960" height="2228" width_o="3960" height_o="2228" data-src="https://freight.cargo.site/t/original/i/517c32d1ea69a969d48f4f8ae227c95bd912c4480de4157ab3f52301aa44904a/IMG_1787.jpeg" data-mid="234087223" border="0" src="https://freight.cargo.site/w/1000/i/517c32d1ea69a969d48f4f8ae227c95bd912c4480de4157ab3f52301aa44904a/IMG_1787.jpeg" /> <img width="4032" height="2268" width_o="4032" height_o="2268" data-src="https://freight.cargo.site/t/original/i/b60f2d755c7b54d2c80c183c45a93ae7d2c2ebe5d869cffbf2c24711b93423c0/IMG_1777.jpeg" data-mid="234087224" border="0" src="https://freight.cargo.site/w/1000/i/b60f2d755c7b54d2c80c183c45a93ae7d2c2ebe5d869cffbf2c24711b93423c0/IMG_1777.jpeg" /> Diffusion TV at CVPR AI Art Gallery 2025, Music City Center, Nashville, USADiffusion TV was featured in the CVPR AI Art Online Gallery 2025 as one of the shortlisted works, and was displayed on site as a loop video at the CVPR conference. <img width="3034" height="1681" width_o="3034" height_o="1681" data-src="https://freight.cargo.site/t/original/i/5c59fa1cbcfc39debf89d73cbcbe4824b490c28dc8e9da3e3a2d004d2eb5bf10/CVPR25-AI-Art_0.JPG" data-mid="234757770" border="0" src="https://freight.cargo.site/w/1000/i/5c59fa1cbcfc39debf89d73cbcbe4824b490c28dc8e9da3e3a2d004d2eb5bf10/CVPR25-AI-Art_0.JPG" /> <img width="3472" height="4624" width_o="3472" height_o="4624" data-src="https://freight.cargo.site/t/original/i/5b12de657c57daa192c560f709f9e68965d524c8555196d037e4d07bd5a76d56/CVPR25-AI-Art_2.jpg" data-mid="234757772" border="0" src="https://freight.cargo.site/w/1000/i/5b12de657c57daa192c560f709f9e68965d524c8555196d037e4d07bd5a76d56/CVPR25-AI-Art_2.jpg" /> <img width="3068" height="3884" width_o="3068" height_o="3884" data-src="https://freight.cargo.site/t/original/i/7e000a8f60a2d910616905f3fb3d36b520bbe2cbab51dd24ad27cfdf70e40385/CVPR25-AI-Art_Diffusion-TV-on-screen.jpeg" data-mid="234757769" border="0" src="https://freight.cargo.site/w/1000/i/7e000a8f60a2d910616905f3fb3d36b520bbe2cbab51dd24ad27cfdf70e40385/CVPR25-AI-Art_Diffusion-TV-on-screen.jpeg" /> Photo credit: Luba Elliott and Masaru Mizuochi Diffusion TV at the Connected Minds Conference 2025 Arts Reception <img width="1980" height="1176" width_o="1980" height_o="1176" data-src="https://freight.cargo.site/t/original/i/35ef58f92b12533aff3aeb9663faf202135578f21cd121abcf64dc2dff96958c/CM-Arts-Reception_01.jpg" data-mid="239312948" border="0" src="https://freight.cargo.site/w/1000/i/35ef58f92b12533aff3aeb9663faf202135578f21cd121abcf64dc2dff96958c/CM-Arts-Reception_01.jpg" /> <img width="1132" height="1980" width_o="1132" height_o="1980" data-src="https://freight.cargo.site/t/original/i/0e12fdb01b020ea7b2f43430714bbf1ba5ff86e6ee1839522517f20bb05c1beb/CM-Arts-Reception_02.jpg" data-mid="239312946" border="0" src="https://freight.cargo.site/w/1000/i/0e12fdb01b020ea7b2f43430714bbf1ba5ff86e6ee1839522517f20bb05c1beb/CM-Arts-Reception_02.jpg" /> Diffusion TV as an Honoree for the AI Creative Awards 2025Diffusion TV has been chosen as an honoree for the AI Creative Futures Awards (AICA) 2025. AICA is a Japan-based award that celebrates AI-driven creative works, offering new perspectives on the future of creativity. The award ceremony took place in Tokyo on December 17, 2025 and was live-streamed on YouTube. Learn more at https://aica-awards.com/ <img width="2081" height="1147" width_o="2081" height_o="1147" data-src="https://freight.cargo.site/t/original/i/55879f75dd9caaad7c6daf2377f2bd0c5732f8b31996cae734347779bda77a9c/IMG_2921.jpg" data-mid="241918147" border="0" src="https://freight.cargo.site/w/1000/i/55879f75dd9caaad7c6daf2377f2bd0c5732f8b31996cae734347779bda77a9c/IMG_2921.jpg" /> <img width="1910" height="1530" width_o="1910" height_o="1530" data-src="https://freight.cargo.site/t/original/i/daee7baacc076b817f950aff7069cd1ad15fd5642b54827f89e99dbf700146f4/Screenshot-2025-12-17-at-19.55.42.png" data-mid="241918154" border="0" src="https://freight.cargo.site/w/1000/i/daee7baacc076b817f950aff7069cd1ad15fd5642b54827f89e99dbf700146f4/Screenshot-2025-12-17-at-19.55.42.png" /> Diffusion TV at the SIGGRAPH 2026 Art Gallery,&nbsp;L.A. Convention Center, Los Angeles, CA, USA Diffusion TV was exhibited at the SIGGRAPH 2026 Art Gallery as one of 12 juried artworks selected from ~200 submissions (&lt; 6% acceptance rate). <img width="5760" height="3840" width_o="5760" height_o="3840" data-src="https://freight.cargo.site/t/original/i/ed4aebea5d134b407ce8ef12e31889fbbbd4e945671c50cdbcdaa755b80af700/IMG_1792.JPG" data-mid="250766035" border="0" src="https://freight.cargo.site/w/1000/i/ed4aebea5d134b407ce8ef12e31889fbbbd4e945671c50cdbcdaa755b80af700/IMG_1792.JPG" /><img width="5760" height="3840" width_o="5760" height_o="3840" data-src="https://freight.cargo.site/t/original/i/f1337ad77c7f7665195083e4e9a30b1b52ad14e4392bdbcfbf1bccd032d68338/IMG_1795.JPG" data-mid="250766036" border="0" src="https://freight.cargo.site/w/1000/i/f1337ad77c7f7665195083e4e9a30b1b52ad14e4392bdbcfbf1bccd032d68338/IMG_1795.JPG" /><img width="5760" height="3840" width_o="5760" height_o="3840" data-src="https://freight.cargo.site/t/original/i/4b944467f743425f36557ba148937f93e274d2917ad56fdeb65e52fc425df505/IMG_1798.JPG" data-mid="250766038" border="0" src="https://freight.cargo.site/w/1000/i/4b944467f743425f36557ba148937f93e274d2917ad56fdeb65e52fc425df505/IMG_1798.JPG" /><img width="5760" height="3840" width_o="5760" height_o="3840" data-src="https://freight.cargo.site/t/original/i/2a819cb05f7f7f0695a823dc5fc9139e0e06638955a65d9bef3f913f68248d10/IMG_1808.JPG" data-mid="250766039" border="0" src="https://freight.cargo.site/w/1000/i/2a819cb05f7f7f0695a823dc5fc9139e0e06638955a65d9bef3f913f68248d10/IMG_1808.JPG" /> Related Publications&nbsp; Sihwa Park, “Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction”, In Proceedings of Explainable AI for the Arts Workshop (XAIxArts), London, UK, 2026.&nbsp;arXiv:2609.05404 [video]Sihwa Park,&nbsp;“Diffusion TV”, In Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Art Gallery (SIGGRAPH Art Gallery '26). Association for Computing Machinery, New York, NY, USA, Article 4, 1–2. https://doi.org/10.1145/3799824.3812693 Interviews “What Emerges From Noise: The Speculative Worlds of ‘Diffusion TV’”,&nbsp;A Sportlight interview on the SIGGRAPH Blog Related Exhibitions&nbsp; Jul 2026, “Diffusion TV” at&nbsp;the SIGGRAPH 2026 Art Gallery, L.A. Convention Center, Los Angeles, CA, USA Oct 2025, “Diffusion TV” at the Connected Minds Conference 2025 Arts Reception (Invited),&nbsp;Sandra Faire and Ivan Fecan Theatre, York University Jun 2025, “Diffusion TV” at the IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) AI Art Gallery 2025 (On-site display and online, shortlisted) May 2025, “Diffusion TV” at the International Symposium on Electronic/Emerging Art (ISEA) 2025, Hangaram Design Museum, Seoul, Korea ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/YouTube-Mirror Sun, 29 May 2022 05:01:55 +0000 Sihwa Park https://sihwapark.com/YouTube-Mirror YouTube Mirror Date: May 2022Categories: AI Art, Data Art, Audiovisual Installation, Generative YouTube Mirror is an interactive, audiovisual AI installation that generates images and sounds in response to the images of the audience captured through a camera in real time, in the form of an interactive mirror. YouTube Mirror uses a cross-modal generative machine model that was trained in an unsupervised way to learn the association between images and sounds obtained from the YouTube videos I watched. YouTube Mirror employs a concept of interactive mirror in digital media arts, as a way to represent how machine vision perceives the world. Since the machine represents the world solely based on its learned audio-visual relationship, the audience can see themselves through the lens of the machine’s vision with the machine-generated images and sounds. YouTube Mirror is an artistic attempt to simulate my unconscious, implicit understanding of audio-visual relationships that can be found in and limited by the videos. YouTube Mirror also attempts to represent the possibility of the machine’s bias inherent in a small-size video dataset which is possibly affected by video recommendation algorithms on YouTube, in an abstract and artistic way. YouTube Mirror at NIME 2023, Mexico City, Mexico This version of the installation accompanied a video grid that loops 300 YouTube clips randomly selected among the whole 6,091 video data in order to show what data was used for training the model. YouTube Mirror at AIMC 2023, Brighton, United Kingdom <img width="4032" height="2268" width_o="4032" height_o="2268" data-src="https://freight.cargo.site/t/original/i/3e474ad7ba4e837b4b9bc899eb0755b6665eb82b5ac216ca5f65920fa5d825e0/IMG_3830.jpg" data-mid="190251494" border="0" src="https://freight.cargo.site/w/1000/i/3e474ad7ba4e837b4b9bc899eb0755b6665eb82b5ac216ca5f65920fa5d825e0/IMG_3830.jpg" /> <img width="4032" height="2268" width_o="4032" height_o="2268" data-src="https://freight.cargo.site/t/original/i/db0287ba8590509044949e01d44c82d9907f5fdbc9cb7f933a43c96bdeee276a/IMG_3831.jpg" data-mid="190251495" border="0" src="https://freight.cargo.site/w/1000/i/db0287ba8590509044949e01d44c82d9907f5fdbc9cb7f933a43c96bdeee276a/IMG_3831.jpg" /> <img width="4032" height="2268" width_o="4032" height_o="2268" data-src="https://freight.cargo.site/t/original/i/547fa13953cc41ed432fce77839aa4a6ce49878a63b9dc82a51bded4855a37cd/IMG_3838.jpg" data-mid="190251496" border="0" src="https://freight.cargo.site/w/1000/i/547fa13953cc41ed432fce77839aa4a6ce49878a63b9dc82a51bded4855a37cd/IMG_3838.jpg" /> Related Publication Sihwa Park, “YouTube Mirror: An Interactive Audiovisual Installation based on Cross-Modal Generative Modeling”, In Proceedings of the International Conference on AI and Musical Creativity (AIMC), Brighton, United Kingdom, 2023 Related Exhibitions Jun 2024, “YouTube Mirror” at the IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) AI Art Gallery 2024 (Online) Aug 2023, “YouTube Mirror” at the International Conference on AI and Musical Creativity (AIMC), Attenborough Centre for the Creative Arts, Brighton, United Kingdom May 2023, “YouTube Mirror” at the International Conference on New Interfaces for Musical Expression (NIME), Centro de Cultura Digital, Mexico City, Mexico May 2022, “YouTube Mirror” at the MAT 2023 End of Year Show: SYMADES, California NanoSystems Institute, UCSB, Santa Barbara, USA ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/Uncertain-Facing Tue, 23 Jun 2020 23:55:33 +0000 Sihwa Park https://sihwapark.com/Uncertain-Facing Uncertain Facing Date: Jun 2020Categories: AI Art, Data Art, Audiovisual Installation,&nbsp;Generative Uncertain Facing is a data-driven, interactive audiovisual installation that aims to represent the uncertainty of data points of which their positions in 3D space are estimated by machine learning techniques. It also tries to raise concerns about the possibility of the unintended use of machine learning with synthetic/fake data. As a data-driven audiovisual piece, Uncertain Facing consists of three major components: 1) face data including synthetic images of faces, generated by StyleGAN2, a generative adversarial network (GAN) for generating portraits of fake human faces, and their face embeddings obtained from FaceNet, a deep neural network trained for finding 128-dimensional feature vectors from face images, 2) t-SNE (t-distributed Stochastic Neighbor Embedding), a non-linear dimensionality reduction technique for the visualization of high-dimensional datasets, and 3) multimodal data representation based on metaball rendering, an implicit surface modeling technique in computer graphics, and granular sound synthesis Uncertain Facing visualizes the real-time clustering of fake faces in 3D space through t-SNE with face embeddings of the faces. This clustering reveals which faces are similar to each other by deducing a 3-dimensional map from 128 dimensions with an assumption based on a probability distribution over data points. However, unlike the original purpose of t-SNE that is meant to be used in an objective data exploration in machine learning, it represents data points as metaballs to reflect the uncertain and probabilistic nature of data locations the algorithm yields. Face images are mapped to surfaces of metaballs as textures, and if more than two data points are getting closer, their faces begin to merge, creating a fragmented, combined face as a means of an abstract, probabilistic representation of data as opposed to exactness that we expect from the use of scientific visualizations. Uncertain Facing also reflects an error value, which t-SNE measures at each iteration between a distribution in original high dimensions and a deduced low-dimensional distribution, as the jittery motion of data points. Along with the t-SNE and metaball-based visualization, Uncertain Facing sonifies the change of the overall data distribution in 3D space based on a granular sound synthesis technique. The data space is divided into eight subspaces and the locations of data points in the subspaces are tracked during the t-SNE operation. The density of data points in each subspace contributes to parameters of granular synthesis, for example, grain density. The error values also are used in determining the frequency range and duration of sound grains to represent the uncertainty of data in sound. As an interactive installation, Uncertain Facing allows the audience to explore the data in detail or their overall structure through a web-based UI on iPad. Moreover, the audience can take a picture of their face and send it to the data space to see its relationship with the data. Given the new face image, Uncertain Facing re-starts t-SNE after obtaining face embeddings of the audience’s face image in real time. While the real audience face is being mixed, merged with the fake faces in 3D space, Uncertain Facing also shows the top nine similar faces on the UI. Here, it tries to imply an aspect that machine learning could be misused in an unintended way as FaceNet does not distinguish between real and fake faces. <img width="3360" height="1887" width_o="3360" height_o="1887" data-src="https://freight.cargo.site/t/original/i/6ca4872b0d8980ade266ad3305d0e5ed44793288d374bda237d370b3a6244a01/00.-installation_1.png" data-mid="181494934" border="0" src="https://freight.cargo.site/w/1000/i/6ca4872b0d8980ade266ad3305d0e5ed44793288d374bda237d370b3a6244a01/00.-installation_1.png" /> <img width="3360" height="1890" width_o="3360" height_o="1890" data-src="https://freight.cargo.site/t/original/i/e590dd3d238d582dd28c1a06be777a0675394ba598f4eb321d4a94a4835321ab/00.-installation_3.png" data-mid="181494935" border="0" src="https://freight.cargo.site/w/1000/i/e590dd3d238d582dd28c1a06be777a0675394ba598f4eb321d4a94a4835321ab/00.-installation_3.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/a52997a690ce8830722d74ae878f3042bf245a8d0d8e5d67605f0be29347dae5/01.-metaball-rendering_1.png" data-mid="181494936" border="0" src="https://freight.cargo.site/w/1000/i/a52997a690ce8830722d74ae878f3042bf245a8d0d8e5d67605f0be29347dae5/01.-metaball-rendering_1.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/47b9d7ad8a32bfd00d8a6a7b57a5c0a2a20166b13284dc397628bc41f6c37b24/02.-metaballs-textured_1.png" data-mid="181494937" border="0" src="https://freight.cargo.site/w/1000/i/47b9d7ad8a32bfd00d8a6a7b57a5c0a2a20166b13284dc397628bc41f6c37b24/02.-metaballs-textured_1.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/044087b6af07f0f30f4a8a144de817d006f47580238304ec99d1125abc0da285/03.-combined-faces_1.png" data-mid="181494938" border="0" src="https://freight.cargo.site/w/1000/i/044087b6af07f0f30f4a8a144de817d006f47580238304ec99d1125abc0da285/03.-combined-faces_1.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/d97b6650b699d2a82772f9a81beccf44c58be70da565f505668a03b25f8f1f18/03.-combined-faces_2.png" data-mid="181494939" border="0" src="https://freight.cargo.site/w/1000/i/d97b6650b699d2a82772f9a81beccf44c58be70da565f505668a03b25f8f1f18/03.-combined-faces_2.png" /> Interactive Installation at Ars Electronica Festival 2020 <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/d94df5fff4c252477a0d5b881ea969924a3c535a439b85540d2046c5c2e374a0/01.installation1.jpeg" data-mid="181494944" border="0" src="https://freight.cargo.site/w/1000/i/d94df5fff4c252477a0d5b881ea969924a3c535a439b85540d2046c5c2e374a0/01.installation1.jpeg" /> <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/8e8b46f874b3b10ca29132a227b3a3fbfb14cbaead6c74bac0eb238b38b20b71/01.installation2.jpeg" data-mid="181494945" border="0" src="https://freight.cargo.site/w/1000/i/8e8b46f874b3b10ca29132a227b3a3fbfb14cbaead6c74bac0eb238b38b20b71/01.installation2.jpeg" /> <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/0fe768f4faee97997453db9750e00e8cd8f9fdf04f21ce644d25b48b17fb7f43/02.exhibition_space1.jpg" data-mid="181494941" border="0" src="https://freight.cargo.site/w/1000/i/0fe768f4faee97997453db9750e00e8cd8f9fdf04f21ce644d25b48b17fb7f43/02.exhibition_space1.jpg" /> <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/b52145457d2a4ea4a3616624b83cae429994587e25ddb3c65d6a02eeaf196361/03.exhibition_space2.jpg" data-mid="181494942" border="0" src="https://freight.cargo.site/w/1000/i/b52145457d2a4ea4a3616624b83cae429994587e25ddb3c65d6a02eeaf196361/03.exhibition_space2.jpg" /> <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/a0f2b6c2a73a1397a94da1c09a42d33322a148272d661d92f8a73903d4f6632b/04.wildstate.jpg" data-mid="181494943" border="0" src="https://freight.cargo.site/w/1000/i/a0f2b6c2a73a1397a94da1c09a42d33322a148272d661d92f8a73903d4f6632b/04.wildstate.jpg" /> Group exhibition “The Wild State”, Kunstuniversität Linz 2020, Photo: Su-Mara Kainz Related Exhibitions Nov 2021, “Uncertain Facing” at the Special Exhibition of AIIF 2021 Advanced Imaging &amp; Artificial Intelligence (Online, invited) Dec 2020, “Uncertain Facing” at the NeurIPS 2020 Workshop on Machine Learning for Creativity and Design (Online; displayed on its AI Art Gallery) Dec 2020, “Uncertain Facing” at the SIGGRAPH Asia 2020 Art Gallery (Virtual), Daegu, Korea Oct 2020, “Uncertain Facing” at the IEEE VIS Arts Program (VISAP) Exhibition (Online), Salt Lake City, Utah, USA [Presentation] Sep 2020, “Uncertain Facing” at The Wilde State: Networked exhibition, Ars Electronica Festival 2020, Linz, Austria Jun 2020, “Uncertain Facing” at the MAT 2020 End of Year Show: Bricolage (Online), UCSB, Santa Barbara, USA ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/GeoD Sat, 02 Jan 2021 22:43:57 +0000 Sihwa Park https://sihwapark.com/GeoD <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/20d02a239ae783e4ce937858b9e4209211ccd9121836b95fe0a7aa4d4d577076/topic89_main.png" data-mid="181494946" border="0" src="https://freight.cargo.site/w/1000/i/20d02a239ae783e4ce937858b9e4209211ccd9121836b95fe0a7aa4d4d577076/topic89_main.png" /> GeoD A Geographical Visualization of Topic Models with Wikification Date: Jul 2019 - Jul 2020Categories: Data Visualization, UI/UX Design GeoD visualizes geographical information (locations and entities with geocoded information) contained in topic models. It can be used to analyze locations discussed in the whole corpus underlying a whole model or in a specific topic. The geocoded information that GeoD maps is gathered from the corpus for a topic model first through a “wikification” process (using the Illinois Wikifier; see L. Ratinov et al., 2011) that confirms the recognition of named entities by checking for correspondence to locations, organizations, etc., for which there are articles in Wikipedia, and secondly through collecting latitude/longitude information for the data. (However, not all possible named entities can be recognized and geocoded as locations in this way.) Please refer to the related article, Cultural life: Theory and empirical testing (Dan C.Baciu, 2020), for detail. GeoD was created by WE1S Interpretation Lab, which is part of the WhatEvery1Says (WE1S) project where I worked as a Research Assistant with the role of Data Visualization Specialist. Working example Github repo Credits Created by the WE1S Interpretation Lab members: - Dan C. Baciu: data science concept, design concept, supervision - Sihwa Park: design and development lead, data visualization, interface design - Xindy Kang: initial visualization, interface design Visual Coding - White circles: publishers - Pink circles: published news content - Yellow lines connect publishers with the content that they published. - Lines are tinted white towards publishers and red towards content. - Green haze heatmap represents areas densely covered by news in this corpus. Data Among the WE1S data collections, the data for demonstration uses “Collection 1: U.S. News Media, c. 1989-2019”, which is the WE1S core collection of 82,324 unique articles mentioning “humanities”. Various Views of a Topic <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/2675f0f83ba2a25a8511cf7bc78a3c77ba4af40b724c9f97f8b9d17bdf241375/topic89_wide.png" data-mid="181494949" border="0" src="https://freight.cargo.site/w/1000/i/2675f0f83ba2a25a8511cf7bc78a3c77ba4af40b724c9f97f8b9d17bdf241375/topic89_wide.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/5bd1c502c8a16d6e71a0aac5338d6823076be6ebcf7ff06efd913266a2ee12c2/topic89_close.png" data-mid="181494947" border="0" src="https://freight.cargo.site/w/1000/i/5bd1c502c8a16d6e71a0aac5338d6823076be6ebcf7ff06efd913266a2ee12c2/topic89_close.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/33f2723882637f6a0b8d4c21fc037bbc05250ad771bbfb91a0510ce0a41781af/topic89_title.png" data-mid="181494948" border="0" src="https://freight.cargo.site/w/1000/i/33f2723882637f6a0b8d4c21fc037bbc05250ad771bbfb91a0510ce0a41781af/topic89_title.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/cdd290c2868d5bba7ab101e8bfcd0c1d6a9f8b6c7931977a83f1263b524d16da/topic89_pub.png" data-mid="181494950" border="0" src="https://freight.cargo.site/w/1000/i/cdd290c2868d5bba7ab101e8bfcd0c1d6a9f8b6c7931977a83f1263b524d16da/topic89_pub.png" /> Topic-wise Comparison <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/a1bb4d0b605a2f6f161403ee236913d284c6a1691fa64ff3d39ab7ce14da7950/topic4_close.png" data-mid="181494952" border="0" src="https://freight.cargo.site/w/1000/i/a1bb4d0b605a2f6f161403ee236913d284c6a1691fa64ff3d39ab7ce14da7950/topic4_close.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/13513013158696a3c0ffa23bb525a9dad98e58add40db24c6f408afa943e969f/topic89_title_pub.png" data-mid="181494951" border="0" src="https://freight.cargo.site/w/1000/i/13513013158696a3c0ffa23bb525a9dad98e58add40db24c6f408afa943e969f/topic89_title_pub.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/06b591f79c15dd8ef077c7024ce1a447e343785c99754d72e660e6fd6b439735/topic14.png" data-mid="181494953" border="0" src="https://freight.cargo.site/w/1000/i/06b591f79c15dd8ef077c7024ce1a447e343785c99754d72e660e6fd6b439735/topic14.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/e27e303cbc7382612ca851e50c3e984c07281d17ad6d6818f7553754ac2bf233/topic21.png" data-mid="181494954" border="0" src="https://freight.cargo.site/w/1000/i/e27e303cbc7382612ca851e50c3e984c07281d17ad6d6818f7553754ac2bf233/topic21.png" /> <img width="3360" height="2100" width_o="3360" height_o="2100" data-src="https://freight.cargo.site/t/original/i/e441a9d0255fb79192368deec7920587b707ea89f0fc9295208d8d359507fa17/topic53.png" data-mid="181494955" border="0" src="https://freight.cargo.site/w/1000/i/e441a9d0255fb79192368deec7920587b707ea89f0fc9295208d8d359507fa17/topic53.png" /> Related Project https://sihwapark.com/TopicBubbles ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/ARLooper Tue, 26 Mar 2019 12:04:59 +0000 Sihwa Park https://sihwapark.com/ARLooper ARLooper Date: Mar 2019Categories: Audiovisual Interface, AR, UI/UX Design ARLooper is an augmented reality mobile interface that allows multiple users to record sound and perform together in a shared AR space. ARLooper is an attempt to explore the potential of collaborative mobile AR instruments in supporting non-verbal communication for musical performances. With ARLooper, the user can record, manipulate, and play sounds being visualized as 3D waveforms in an AR space. ARLooper provides a shared AR environment wherein multiple users can observe each other’s activities in real time, supporting increasing the understanding of collaborative contexts. Related Performances https://sihwapark.com/Loading https://sihwapark.com/Ballet-Mécanique Related Publication Sihwa Park, “ARLooper: A Mobile AR Application for Collaborative Sound Recording and Performance”, In Lecture Notes in Computer Science (revised selected papers of CMMR 2019), Vol. 12631, 2021 Sihwa Park, “Collaborative Mobile Instruments in a Shared AR Space: a Case of ARLooper”, In Proceedings of the International Conference on New Interfaces for Musical Expression (NIME), Birmingham, United Kingdom, 2020 [Presentation] Sihwa Park, “ARLooper: Collaborative Audiovisual Experience with Mobile Devices in a Shared Augmented Reality Space”, In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems (CHI EA ’20). ACM, Honolulu, HI, USA, 2020 (The conference was cancelled due to the COVID-19) Sihwa Park, “ARLooper: a Mobile AR Application for Collaborative Sound Recording and Performance”, In Proceedings of International Symposium on Computer Music Multidisciplinary Research (CMMR), Marseille, France, 2019 Initial Version: https://vimeo.com/326552494 ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/Ballet-Mecanique Fri, 29 Oct 2021 09:06:33 +0000 Sihwa Park https://sihwapark.com/Ballet-Mecanique <img width="1920" height="1080" width_o="1920" height_o="1080" data-src="https://freight.cargo.site/t/original/i/4119011939563358d8e17ce049f94392e3e5bc214c76414e0621250cd0b73cbd/Ballet-Mecanique_041819.png" data-mid="181494962" border="0" src="https://freight.cargo.site/w/1000/i/4119011939563358d8e17ce049f94392e3e5bc214c76414e0621250cd0b73cbd/Ballet-Mecanique_041819.png" /> Ballet Mécanique Date: Apr 2019Categories: Audiovisual Performance, CREATE Ensemble Performance Description (written by Karl Yerkes)&nbsp; Ballet Mécanique is a Dadaist post-Cubist art film conceived, written, and co-directed by the artist Fernand Léger in collaboration with the filmmaker Dudley Murphy (with cinematographic input from Man Ray). It has a musical score by the American composer George Antheil. However, the film premiered in a silent version on September 24, 1924, at the Internationale Ausstellung neuer Theatertechnik (International Exposition for New Theater Technique) in Vienna presented by Frederick Kiesler. It is considered one of the masterpieces of early experimental filmmaking. The CREATE Ensemble members improvised with their own instruments based on the scene changes of this silent film while the film was showing. The scene changes were systematically chosen and labeled by a custom program written by the director, Karl Yerkes. This piece was an opening performance of the Center for Research in Electronic Art Technology (CREATE) concert, ‘The Music Easel’ on April 18, 2019 at Lotte Lehmann Concert Hall, University of California, Santa Barbara. (see details at https://music.ucsb.edu/news/event/1845) Performers: (from the left) Myungin Lee, Hannah Wolfe, Sihwa Park, Karl Yerkes (director), Alexis Crawshaw Performance at the MAT 2019 End of Year Show: MADE [at] UCSB, Elings Hall, University of California, Santa Barbara Performers : (from the left) Alexis Crawshaw, Diarmid Flatley, Myungin Lee, Tim Wood, Sihwa Park, Karl Yerkes (director) In these performances, I played my mobile instrument, ARLooper. ︎︎︎ Previous Next ︎︎︎ https://sihwapark.com/Brand-Logo-Sonification Sun, 10 Mar 2019 01:23:16 +0000 Sihwa Park https://sihwapark.com/Brand-Logo-Sonification Brand Logo Sonification Date: Mar 2019Categories: Audiovisual Installation, Data Art, Sonification Brand Logo Sonification is an audiovisual installation that exists on the border between old and analog technology and new digital practices. It mainly represents the global top 10 brand ranking data and logos from 2000 to 2018 through an oscilloscope, which is an electronic analog instrument, by the computational digital processes of data visualization and sonification. Based on OpenCV image processing and a vector synthesis technique, it extracts the contours of logos and converts them to audio that can be rendered on a vector display, such as an oscilloscope or laser. While the contours chiefly determine sound textures, the ranking data contributes to the whole composition: The ranking is used to decide the order and duration of brand appearances. And, brand values are proportionally mapped to the size of logos. If a brand’s value increases more than 10%, a brand logo starts with a noisy fluctuation, resulting in a noise sound, and becomes a clear shape at the middle of appearance duration. A degree of noise is proportional to a brand value change. If the ranking of a brand drops, its logo shape deforms smoothly by a flanging audio effect. Through this process combining analog and digital practices, this work also reveals that our society is getting more affected by digital and IT companies, such as Google, Apple, Amazon, or Facebook, than brands in traditional industries, as their ranking in the data becomes highly positioned over time. This work is presented with a laser display as a fixed-media and with an oscilloscope display as an interactive version. Materials: Processing with XYscope library, Oscilloscope emulator, a laser and an oscilloscope display Data is collected from Interbrand. This project was made as an individual project in the Vector Hack Workshop at UCSB, led by Derek Holzer. Brand Logo Sonification at The Santa Barbara Center for Art, Science and Technology(SBCAST), March 7, 2019 <img width="1280" height="853" width_o="1280" height_o="853" data-src="https://freight.cargo.site/t/original/i/ec29b8e533b7be6a1f605ac11929156ffcf8394666d042cbec9c1d2b0822395e/IMG_9392.JPG" data-mid="181494963" border="0" src="https://freight.cargo.site/w/1000/i/ec29b8e533b7be6a1f605ac11929156ffcf8394666d042cbec9c1d2b0822395e/IMG_9392.JPG" /> <img width="1280" height="719" width_o="1280" height_o="719" data-src="https://freight.cargo.site/t/original/i/26e5b0928470b8f411ce7dd4265480960e8ac1fbbaac4abea055a2f00b287490/IMG_9400.JPG" data-mid="181494964" border="0" src="https://freight.cargo.site/w/1000/i/26e5b0928470b8f411ce7dd4265480960e8ac1fbbaac4abea055a2f00b287490/IMG_9400.JPG" /> <img width="1280" height="719" width_o="1280" height_o="719" data-src="https://freight.cargo.site/t/original/i/410e41090ca6dbf55298a975df36f92eff51bd509ab1e926c1b7736bde5c8f10/IMG_9403.JPG" data-mid="181494965" border="0" src="https://freight.cargo.site/w/1000/i/410e41090ca6dbf55298a975df36f92eff51bd509ab1e926c1b7736bde5c8f10/IMG_9403.JPG" /> <img width="1280" height="853" width_o="1280" height_o="853" data-src="https://freight.cargo.site/t/original/i/9ef2a3cf53354b08cdd0ffbc314b3217e28bee359d7afa472bb9f8b4e6ed31b3/IMG_9407.JPG" data-mid="181494966" border="0" src="https://freight.cargo.site/w/1000/i/9ef2a3cf53354b08cdd0ffbc314b3217e28bee359d7afa472bb9f8b4e6ed31b3/IMG_9407.JPG" /> Improvisation Test The above video is an initial test by improvising without relying on the ranking data. IEEE VIS Arts Program 2019 Exhibition <img width="1453" height="1080" width_o="1453" height_o="1080" data-src="https://freight.cargo.site/t/original/i/0c365cc361e564559ab74bba28788073f102e62179ee0aaf92f6bdd9a68b3365/ieee_visap_2019.png" data-mid="181494968" border="0" src="https://freight.cargo.site/w/1000/i/0c365cc361e564559ab74bba28788073f102e62179ee0aaf92f6bdd9a68b3365/ieee_visap_2019.png" /> Related Exhibitions Oct 2019, “Brand Logo Sonification” Installation at the IEEE VIS Arts Program (VISAP), Vancouver, Canada Jun 2019, “Brand Logo Sonification” Installation at the MAT 2019 End of Year Show: MADE [at] UCSB, California NanoSystems Institute, UCSB, Santa Barbara, USA ︎︎︎ Previous Next ︎︎︎