Hi, could you please provide the object feature extraction code for REVERIE/SOON dataset?
It is mentioned in the paper that "For objects, we use the same ViT on the REVERIE dataset as it provides bounding boxes, while we use the BUTD object detector on the SOON dataset." Did you crop each object from the panorama and extract its feature using ViT?
Hi, could you please provide the object feature extraction code for REVERIE/SOON dataset?
It is mentioned in the paper that "For objects, we use the same ViT on the REVERIE dataset as it provides bounding boxes, while we use the BUTD object detector on the SOON dataset." Did you crop each object from the panorama and extract its feature using ViT?