TL;DR: We propose StyleCrafter, a generic method that enhances pre-trained T2V models with style control, supporting Style-Guided Text-to-Image Generation and Style-Guided Text-to-Video Generation. 1.
While hiking deep in the Great Smoky Mountains National Park, explorers stumbled upon bizarre, ancient-looking rock formations—with no clear origin or explanation. Were they built by early settlers, ...
Scientists discovered a never-before-seen layer of rock beneath Bermuda that makes the archipelago seem to float in the middle of the ocean. How to watch the 2026 Rose Parade live on New Year's Day: ...
Abstract: Video embedding is the pivot in Temporal Action Detection (TAD). Once the video embedding can robustly capture the essence of actions and perceive activities in complex scenes, the TAD model ...
Abstract: Large-scale pre-trained vision-language models (e.g., CLIP) have shown incredible generalization performance in downstream tasks such as video-text retrieval (VTR). Traditional approaches ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback