A5065899440- Video Analysis and Summarization
- Computer Graphics and Visualization Techniques
- Advanced Vision and Imaging
- Neuroscience and Music Perception
- Ethics and Social Impacts of AI
- Mental Health via Writing
- Innovative Human-Technology Interaction
- Music and Audio Processing
- Diverse Music Education Insights
- Topic Modeling
- Image Enhancement Techniques
- Human Motion and Animation
- Music Technology and Sound Studies
- Open Source Software Innovations
- Digital Games and Media
- Video Surveillance and Tracking Methods
- Image Processing and 3D Reconstruction
- Data Visualization and Analytics
- Music Therapy and Health
University of California, San Diego
2023
Robotics Research (United States)
2022
Indian Institute of Technology Hyderabad
2022
International Institute of Information Technology, Hyderabad
2021
We present Queer in AI as a case study for community-led participatory design AI. examine how and intersectional tenets started shaped this community's programs over the years. discuss different challenges that emerged process, look at ways organization has fallen short of operationalizing principles, then assess organization's impact. provides important lessons insights practitioners theorists methods broadly through its rejection hierarchy favor decentralization, success building aid by...
Research papers are a vital building block for scientific discussion. While these follow effective structures the relevant community, they unable to cater novice readers and express otherwise creative ideas in mediums. To this end, we propose ZINify, first approach automatically transform research into engaging zines using large language models (LLM) text-to-image generators. Following zine's long history of supporting independent, expression, technique that can work with authors build more...
We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our optimizes Gaussian Splatting representation to match complex prompts. initialize these splats by utilizing the state-of-the-art text-to-image generators, lifting their samples into 3D, and computing occlusion volume. then optimize this across multiple views as inpainting task with image-conditional diffusion models. To learn correct geometric structure, we incorporate depth...
Music affects and in some cases reflects one's emotional state.Key to this influence is lyrics their meaning conjunction with the acoustic properties of track.Recent work has focused on analysing these showing that individuals prone depression primarily consume low valence energy music.However, no studies yet have explored lyrical content preferences relation online music consumption such individuals.In current study, we examine simplicity, measured as Compressibility Absolute Information...
We present Queer in AI as a case study for community-led participatory design AI. examine how and intersectional tenets started shaped this community's programs over the years. discuss different challenges that emerged process, look at ways organization has fallen short of operationalizing principles, then assess organization's impact. provides important lessons insights practitioners theorists methods broadly through its rejection hierarchy favor decentralization, success building aid by...
Reading, much like music listening, is an immersive experience that transports readers while taking them on emotional journey. Listening to complementary has the potential amplify reading experience, especially when stylistically cohesive and emotionally relevant. In this paper, we propose first fully automatic method build a dense soundtrack for books, which can play high-quality instrumental entirety of duration. Our work employs unique text processing weaving pipeline determines context...
In this work, we propose IndoLayout, a novel real-time approach for generating high-quality occupancy maps from an RGB image indoor scenes. Such are often crucial path-planning and mapping in environments but built using only information contained the ego view. contrast, our also predicts values beyond immediately visible regions just monocular image, leveraging learnt priors Hence, proposed network can produce hallucinated, amodal scene layout that includes areas occluded such as navigable...
Music affects and in some cases reflects one's emotional state. Key to this influence is lyrics their meaning conjunction with the acoustic properties of track. Recent work has focused on analysing these showing that individuals prone depression primarily consume low valence energy music. However, no studies yet have explored lyrical content preferences relation online music consumption such individuals. In current study, we examine simplicity, measured as Compressibility Absolute...