JoeLeelyf/OVO-Bench

<h1 align="center"> <font color=#0088cc>O</font><font color=#060270>V</font><font color=#0088cc>O</font>-Bench: How Far is Your Video-LLMs from Real-World <font color=#0088cc>O</font>nline <font color=#060270>V</font>ide<b style="color: #0088cc;">O</b> Understanding? </h1> <p align="center"> 🔥🔥OVO-Bench is accepted by CVPR 2025!🔥🔥 </p> <p align="center"> <a href="https://arxiv.org/abs/2501.05510" style="margin-right: 10px;"> <img src="https://img.shields.io/badge/arXiv-2501.05510-b31b1b.svg?logo=arXiv"> </a> </p> > **Important Note:** Current codebase is modified compared to our initial arXiv paper. We strongly recommend that any use of OVO-Bench should be based on current edition. ## Introduction ### 🌟 Three distinct problem-solving modes - **Backward Tracing**: trace back to past events to answer the question. - **Real-Time Visual Perception**: understand and respond to events as they unfold at the current timestamp. - **Forward Active Responding**: delay the response until sufficient future information becomes available to answer the question accurately.