Publications (66)
Self-supervised Human Mesh Recovery with Cross-Representation Alignment
Xuan Gong, Meng Zheng, Benjamin Planche +4
Fully supervised human mesh recovery methods are data-hungry and have poor generalizability due to the limited availability and diversity of 3D-annotated benchmark datasets. Recent…
A random forest system combination approach for error detection in digital dictionaries
Michael Bloodgood, Peng Ye, Paul Rodrigues +2
When digitizing a print bilingual dictionary, whether via optical character recognition or manual entry, it is inevitable that errors are introduced into the electronic version tha…
Progressive Multi-view Human Mesh Recovery with Self-Supervision
Xuan Gong, Liangchen Song, Meng Zheng +5
To date, little attention has been given to multi-view 3D human mesh estimation, despite real-life applicability (e.g., motion capture, sport analysis) and robustness to single-vie…
FairLLaVA: Fairness-Aware Parameter-Efficient Fine-Tuning for Large Vision-Language Assistants
Mahesh Bhosale, Abdul Wasi, Shantam Srivastava +5
While powerful in image-conditioned generation, multimodal large language models (MLLMs) can display uneven performance across demographic groups, highlighting fairness risks. In s…
Semantic Text-to-Face GAN -ST^2FG
Manan Oza, Sukalpa Chanda, David Doermann
Faces generated using generative adversarial networks (GANs) have reached unprecedented realism. These faces, also known as "Deep Fakes", appear as realistic photographs with very…
Language-guided Human Motion Synthesis with Atomic Actions
Yuanhao Zhai, Mingzhen Huang, Tianyu Luan +5
Language-guided human motion synthesis has been a challenging task due to the inherent complexity and diversity of human behaviors. Previous methods face limitations in generalizat…