 CM3T: Framework for Efficient Multimodal Learning for Inhomogeneous Interaction DatasetsIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2025 |
 Sensitive Image Classification by Vision TransformersIEEE International Conference on Systems, Man and Cybernetics (SMC), 2024 |
 An Outlook into the Future of Egocentric VisionInternational Journal of Computer Vision (IJCV), 2023 |
 Multimodal Distillation for Egocentric Action RecognitionIEEE International Conference on Computer Vision (ICCV), 2023 |
 Cross-view Action Recognition Understanding From Exocentric to
Egocentric PerspectiveNeurocomputing (Neurocomputing), 2023 |
 Epic-Sounds: A Large-scale Dataset of Actions That SoundIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
