Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding 事件

Knowledge-Preserved Model Tuning in Null-Space for Robust Spatio-Temporal Video Grounding arXiv:2606.03539v1 Announce Type: new Abstract: Spatio-Temporal Video Grounding aims to localize object tubes based on textual queries. While recent methods have achieved remarkable success, they mainly focus on high-quality(HQ) inputs, neglecting the widespread presence of low-quality(LQ) videos in real-world scenarios. Although tuning methods like LoRA can adapt to degraded inputs, they inevitably disrup