α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Soravit Changpinyo
Soravit Changpinyo
1
Affiliations
Affiliations
Google Research
12
papers
2,329
total citations
papers (12)
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
CVPR 2021
arXiv
1,385
citations
Connecting Vision and Language with Localized Narratives
ECCV 2020
arXiv
291
citations
On Scaling Up a Multilingual Vision and Language Model
CVPR 2024
arXiv
256
citations
What You See is What You Read? Improving Text-Image Alignment Evaluation
NEURIPS 2023
arXiv
120
citations
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
NEURIPS 2021
arXiv
51
citations
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
ICCV 2021
arXiv
49
citations
MetaCLUE: Towards Comprehensive Visual Metaphors Research
CVPR 2023
arXiv
45
citations
PreSTU: Pre-Training for Scene-Text Understanding
ICCV 2023
arXiv
39
citations
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
ECCV 2022
arXiv
35
citations
Connecting Vision and Language With Video Localized Narratives
CVPR 2023
arXiv
30
citations
Telling the What While Pointing to the Where: Multimodal Queries for Image Retrieval
ICCV 2021
arXiv
28
citations
Robust Visual Reasoning via Language Guided Neural Module Networks
NEURIPS 2021
0
citations