Scholar

Yuxiao Chen

Google Scholar ID: 6PW8cyQAAAAJ

PhD student in Computer Science, Rutgers University

Computer Vision Machine Learning

Citations & Impact

All-time

Citations

841

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

20 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Published 'Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens' at CVPR 2023.
Published 'HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention' at ICLR 2023.
Published 'More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching' at WACV 2023.
Published 'Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning' at ECCV 2022.
Two additional papers under review: one on LLM-based multi-pathway text-video alignment for instructional video action localization, and another on open-vocabulary action detection using VLM localizability and semantics.

Research Experience

Sept. 2018 – Present: Research Assistant at Rutgers University under Prof. Dimitris N. Metaxas, working on human/hand pose modeling, estimation, representation learning, and sign language video understanding.
May 2023 – Aug. 2023: Research Intern at NEC Laboratories America Inc., mentored by Dr. Kai Li, focusing on open-set video action localization and grounding.
May 2022 – Aug. 2022: Research Intern at AML Research, Bytedance, mentored by Dr. Jianbo Yuan, Dr. Yu Tian, and Dr. Xinyu Li, working on large-scale multimodal (image-text) model pre-training.
May 2020 – Aug. 2020: Applied Scientist Intern at Softline Discovery, Amazon, mentored by Dr. Jianbo Yuan, researching image-text matching/retrieval.
Sept. 2016 – May 2018: Research Assistant at University of Rochester under Prof. Jiebo Luo, conducting research on data mining in social media.
May 2017 – Aug. 2017: Research Intern at Youtu Lab, Tencent, mentored by Dr. Pai Peng, working on medical image analysis.

Co-authors

15 total