Scholar

Wenhao Wang

Google Scholar ID: k3mq3XMAAAAJ

Google DeepMind, University of Technology Sydney

AI SafetyVideo GenerationCopyright ProtectionVisual Copy DetectionDiffusion Models

Citations & Impact

All-time

Citations

463

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

VideoUFO: The first dataset curated in alignment with real-world users’ focused topics for text-to-video generation, comprising over 1.09 million video clips spanning 1,291 topics.
TIP-I2V: The first dataset comprising over 1.70 million unique user-provided text and image prompts for image-to-video generation.
VidProM: The first dataset featuring 1.67 million unique text-to-video prompts and 6.69 million videos generated from 4 different state-of-the-art diffusion models, ranked Top 6/121,084 in the Hugging Face Dataset Trending List on Mar. 19th 2024.
Proposed a novel task, origin identification for text-guided image-to-image diffusion models.
Introduced ICDiff, the first Image Copy Detection (ICD) specialized for diffusion-generated replicas.
Published a survey on replication in visual diffusion models.

Research Experience

Before UTS, was a Research Assistant at Baidu Research, co-supervised by Yifan Sun and Yi Yang; previously, a Remote Research Intern at Inception Institute of Artificial Intelligence (IIAI) from 2020 to 2021, supervised by Fang Zhao and Shengcai Liao.

Education

Ph.D. student at the University of Technology Sydney, supervised by Yi Yang. Gained a bachelor's degree from Beihang University in 2021 with Shenyuan Medal (Top 10 Undergraduate).

Background