Kanchana Ranasinghe

few-shot learning (2) self-supervised learning (2) long-form video (2) action recognition (2) video understanding (2) contrastive learning (2) visual question answering (2) zero-shot learning (2) semantic segmentation (2) visual grounding (1) multimodal learning (1) vision transformer (1) vision language model (1) object localization (1) shape recognition (1) feature space (1) video transformer (1) spatiotemporal modeling (1) self-attention mechanism (1) representation learning (1)