Spatia. [CVPR2026] Long-horizon, spatially consistent video generation enabled by persistent 3D scene point clouds and dynamic-static disentanglement.
221HPR. [CVPR 2024] Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective
20HC-RefLoCo. [NeurIPS 2024] A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
9