2 papers
cs.CV2025
Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completion
Anith Selvakumar, Manasa Bharadwaj
Monocular Indoor Semantic Scene Completion (SSC) aims to reconstruct a 3D semantic occupancy map from a single RGB image of an indoor scene, inferring spatial layout and object cat…
cs.SD2023
Getting More for Less: Using Weak Labels and AV-Mixup for Robust Audio-Visual Speaker Verification
Anith Selvakumar, Homa Fashandi
Distance Metric Learning (DML) has typically dominated the audio-visual speaker verification problem space, owing to strong performance in new and unseen classes. In our work, we e…