Skip to yearly menu bar Skip to main content


VideoGrounding-DINO: Towards Open-Vocabulary Spatio-Temporal Video Grounding

Syed Talal Wasim · Muzammal Naseer · Salman Khan · Ming-Hsuan Yang · Fahad Shahbaz Khan

Arch 4A-E Poster #416
[ ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT


Video grounding aims to localize a spatio-temporal section in a video corresponding to an input text query. This paper addresses a critical limitation in current video grounding methodologies by introducing an Open-Vocabulary Spatio-Temporal Video Grounding task. Unlike prevalent closed-set approaches that struggle with open-vocabulary scenarios due to limited training data and predefined vocabularies, our model leverages pre-trained representations from foundational spatial grounding models. This empowers it to effectively bridge the semantic gap between natural language and diverse visual content, achieving strong performance in closed-set and open-vocabulary settings. Our contributions include a novel spatio-temporal video grounding model, surpassing state-of-the-art results in closed-set evaluations on multiple datasets and demonstrating superior performance in open-vocabulary scenarios. Notably, the proposed model outperforms state-of-the-art methods in closed-set settings on VidSTG (Declarative and Interrogative) and HC-STVG (V1 and V2) datasets. Furthermore, in open-vocabulary evaluations on HC-STVG V1 and YouCook-Interactions, our model surpasses the recent best-performing models by 4.88 m_vIoU and 1.83\% accuracy, demonstrating its efficacy in handling diverse linguistic and visual concepts for improved video understanding. Our codes will be publicly released.

Live content is unavailable. Log in and register to view live content