papers

Publications (66)

cs.CV2022

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…

cs.CL2014

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…

cs.CV2022

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…

cs.CV2026

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…

cs.CV2023

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…

cs.CV2023

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…