Login / Signup
X-RefSeg3D: Enhancing Referring 3D Instance Segmentation via Structured Cross-Modal Graph Neural Networks.
Zhipeng Qian
Yiwei Ma
Jiayi Ji
Xiaoshuai Sun
Published in:
AAAI (2024)
Keyphrases
</>
cross modal
perceptual information
multi modal
structured data
image segmentation
visual recognition
multimedia retrieval
multiscale
image retrieval
visual similarity
nearest neighbor
multimedia databases