Correction in Version 1: Each file contains 36 x 17 dimension features extracted from fixed set 36 bounding boxes (Anderson et al., 2018) of Faster R-CNN (Ren et al., 2015) for each image in the MSCO
Correction in Version 1: Each file contains 36 x 17 dimension features extracted from fixed set 36 bounding boxes (Anderson et al., 2018) of Faster R-CNN (Ren et al., 2015) for each image in the MSCO
