Varnith Chordia

video generation (2) fine-grained classification (1) multitask learning (1) sequence-to-sequence generation (1) positional encoding (1) video diffusion (1) temporal consistency (1) multi-level classification (1) punctuation restoration (1) video diffusion transformer (1) transformer model (1) spoken text (1) temporal control (1) multi-event generation (1) event sequencing (1) multi-event video generation (1) time-aware cross-attention (1) photometric transformation (1) written text (1) scene text replacement (1)