It’s happened to all of us: you find the perfect model for your needs — a bracket, a box, a cable clip, but it only comes in ...
In this work, we propose the Structurebased Pseudo Label generation (SPL) framework for the zero-shot video sentence localization task, which learns with only video data without any annotation. We ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback