no code implementations • 1 Apr 2024 • Hao Chen, Yuqi Hou, Chenyuan Qu, Irene Testini, Xiaohan Hong, Jianbo Jiao
While many existing datasets focus on scene understanding from a certain perspective (e. g. egocentric or third-person views), our dataset offers a panoptic perspective (i. e. multiple viewpoints with multiple data modalities).
no code implementations • 14 Nov 2022 • Shizheng Zhou, Juntao Jiang, Xiaohan Hong, Yajun Fang, Yan Hong, Pengcheng Fu
The total number of images in the dataset is 937 and all the objects in these images were annotated.