Login / Signup
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection.
Hangjie Yuan
Jianwen Jiang
Samuel Albanie
Tao Feng
Ziyuan Huang
Dong Ni
Mingqian Tang
Published in:
NeurIPS (2022)
Keyphrases
</>
input image
image features
image segmentation
high resolution
test images
image classification
image retrieval
low level
spatial information
object detectors
bounding box
relational databases
feature points
partial occlusion
computer vision
multi view
object detection
random fields
video sequences