Follow
Soravit "Beer" Changpinyo
Soravit "Beer" Changpinyo
Other namesSoravit Changpinyo, Beer Changpinyo
Google DeepMind
Verified email at google.com - Homepage
Title
Cited by
Cited by
Year
Gemini: a family of highly capable multimodal models
G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ...
arXiv preprint arXiv:2312.11805, 2023
22132023
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts
S Changpinyo, P Sharma, N Ding, R Soricut
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021
9982021
Synthesized classifiers for zero-shot learning
S Changpinyo, WL Chao, B Gong, F Sha
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5327-5336, 2016
9382016
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ...
arXiv preprint arXiv:2403.05530, 2024
7022024
An empirical study and analysis of generalized zero-shot learning for object recognition in the wild
WL Chao, S Changpinyo, B Gong, F Sha
European Conference on Computer Vision (ECCV), 52-68, 2016
6842016
PaLI: A Jointly-Scaled Multilingual Language-Image Model
X Chen, X Wang, S Changpinyo, AJ Piergiovanni, P Padlewski, D Salz, ...
International Conference on Learning Representations (ICLR), 2023
6192023
Connecting vision and language with localized narratives
J Pont-Tuset, J Uijlings, S Changpinyo, R Soricut, V Ferrari
European Conference on Computer Vision (ECCV), 647-664, 2020
2442020
Predicting visual exemplars of unseen classes for zero-shot learning
S Changpinyo, WL Chao, F Sha
IEEE International Conference on Computer Vision (ICCV), 3496-3505, 2017
2152017
The power of sparsity in convolutional neural networks
S Changpinyo, M Sandler, A Zhmoginov
arXiv preprint arXiv:1702.06257, 2017
1682017
PaLI-X: On Scaling up a Multilingual Vision and Language Model
X Chen, J Djolonga, P Padlewski, B Mustafa, S Changpinyo, J Wu, ...
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
1512024
Multi-Task Learning for Sequence Tagging: An Empirical Study
S Changpinyo, H Hu, F Sha
27th International Conference on Computational Linguistics (COLING), 2965–2977, 2018
832018
All You May Need for VQA are Image Captions
S Changpinyo, D Kukliansky, I Szpektor, X Chen, N Ding, R Soricut
Conference of the North American Chapter of the Association for …, 2022
642022
Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?
Y Chen, H Hu, Y Luan, H Sun, S Changpinyo, A Ritter, MW Chang
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023
592023
What You See is What You Read? Improving Text-Image Alignment Evaluation
M Yarom, Y Bitton, S Changpinyo, R Aharoni, J Herzig, O Lang, E Ofek, ...
Advances in Neural Information Processing Systems (NeurIPS), 2023
542023
Classifier and exemplar synthesis for zero-shot learning
S Changpinyo, WL Chao, B Gong, F Sha
International Journal of Computer Vision (IJCV) 128 (1), 166-201, 2020
542020
On Model Calibration for Long-Tailed Object Detection and Instance Segmentation
TY Pan, C Zhang, Y Li, H Hu, D Xuan, S Changpinyo, B Gong, WL Chao
Advances in Neural Information Processing Systems (NeurIPS), 2021
522021
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
C Zhang, TY Pan, Y Li, H Hu, D Xuan, S Changpinyo, B Gong, WL Chao
IEEE/CVF International Conference on Computer Vision (ICCV), 2021
462021
Similarity component analysis
S Changpinyo, K Liu, F Sha
Advances in Neural Information Processing Systems (NIPS), 1511-1519, 2013
312013
MetaCLUE: Towards Comprehensive Visual Metaphors Research
AR Akula, B Driscoll, P Narayana, S Changpinyo, Z Jia, S Damle, G Pruthi, ...
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
302023
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
N Ding, X Chen, T Levinboim, S Changpinyo, R Soricut
European Conference on Computer Vision (ECCV), 2022
292022
The system can't perform the operation now. Try again later.
Articles 1–20