Shameema Sikder

federated learning (1) semantic segmentation (1) video captioning (1) self-supervised learning (1) temporal reasoning (1) privacy preservation (1) vision language model (1) vision foundation model (1) joint-embedding predictive architecture (1) black-box adaptation (1) video moment retrieval (1) surgical video analysis (1) spatiotemporal representation learning (1) surgical video understanding (1) first order optimization (1) zero order optimization (1)