When Visual Grounding Meets Gigapixel-level Large-scale Scenes: Benchmark and Approach
Visual grounding refers to the process of associating natural language expressions with
corresponding regions within an image. Existing benchmarks for visual grounding primarily …
corresponding regions within an image. Existing benchmarks for visual grounding primarily …
GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes
Pedestrian trajectory prediction is a well-established task with significant recent
advancements. However existing datasets are unable to fulfill the demand for studying …
advancements. However existing datasets are unable to fulfill the demand for studying …