← Search

Radhika Dua

2 accepted papers

2022

ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

CVPR 2022poster

Progress in 3D object understanding has relied on manually "canonicalized" shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, e.g., from internet model collections or depth sensors. ConDor…

Cited by 42PDFcodeScholar
2022

Reweighting Strategy Based on Synthetic Data Identification for Sentence Similarity

COLING 2022main

Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language models(PLMs) as a training corpus. However, PLMs often generate…