Jae Sung Park
10
Papers
96
Total Citations
Papers (10)
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
CVPR 2025
96
citations
Synthetic Visual Genome
CVPR 2025
0
citations
Adversarial Inference for Multi-Sentence Video Description
CVPR 2019
0
citations
Fusing Pre-Trained Language Models With Multimodal Prompts Through Reinforcement Learning
CVPR 2023
0
citations
VisualCOMET: Reasoning about the Dynamic Context of a Still Image
ECCV 2020
0
citations
Identity-Aware Multi-Sentence Video Description
ECCV 2020
0
citations
The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning
ECCV 2022
0
citations
MERLOT: Multimodal Neural Script Knowledge Models
NeurIPS 2021
0
citations
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
NeurIPS 2021
0
citations
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
NeurIPS 2023
0
citations