Soravit Changpinyo

14

Papers

254

Total Citations

1

Affiliations

Affiliations

Google Research

Papers (14)

On Scaling Up a Multilingual Vision and Language Model

Synthesized Classifiers for Zero-Shot Learning

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Connecting Vision and Language With Video Localized Narratives

MetaCLUE: Towards Comprehensive Visual Metaphors Research

Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

Telling the What While Pointing to the Where: Multimodal Queries for Image Retrieval

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

PreSTU: Pre-Training for Scene-Text Understanding

Connecting Vision and Language with Localized Narratives

PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

Robust Visual Reasoning via Language Guided Neural Module Networks

What You See is What You Read? Improving Text-Image Alignment Evaluation