Xurui Gao — accepted AI-conference papers

2026

OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios

Hong Gao, Jingyu Wu, Xiangkai Xu, Kangni Xie, Yunchen Zhang, Bin Zhong +2

CVPR 2026

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. While Multimodal Large Language Models have shown promise, a significant gap remains between current models and real-world demands involving diverse objects and complex queries. W

Cited by 0 Source ↗Scholar ↗

2026

SARL-STG: A Spatially Aware Reinforcement Learning Framework for Refining MLLMs in Spatio-Temporal Video Grounding

Hong Gao, Xiangkai Xu, Bin Zhong, Junjie Yin, Fangyu Kang, Yutong Xu +3

CVPR 2026

Spatio-Temporal Video Grounding (STVG) requires models to localize objects both spatially and temporally. Despite recent progress, existing methods struggle with complex and fine-grained spatial semantics in language descriptions, leading to error propagation from temporal to spatial grounding stage

Cited by 0 Source ↗Scholar ↗