conftrace_

keyframes

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

memory pack (1) multi-shot (1) storyboard (1) tokenizer (1) temporal motion (1) dual encoding (1) pixel space (1) video-language pre-training (1) two-stage training (1) generative pre-training (1)

Papers

STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative CVPR 2026 Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization ICML 2024