Join PLUS

🚩 We are recruiting undergrad students in SIST as Research Assistant for our projects. Click for more information.

🚩 Our group is also recruiting top-caliber graduate students with strong expertise in computer vision and machine learning for 2023. Please send email to Prof. Xuming He for more information after registering your application on the school website.

News

📌 [03/2024] Two papers accepted by CVPR 2024!

📌 [03/2024] One papers accepted by ICLR 2024!

📌 [03/2024] One papers accepted by Neurips 2024!

📌 [12/2023] One paper accepted by TPAMI 2023!

📌 [06/2022] One paper accepted by TMLR 2023!

📌 [06/2022] Two papers accepted by ICCV 2023!

📌 [06/2022] One paper accepted by IJCAI 2023!

📌 [06/2022] One paper accepted by CVPR 2023!

📌 [06/2022] Two papers accepted by ICLR 2023!

📌 [06/2022] One paper accepted by AAAI 2023!

📌 [06/2022] One paper accepted by FG 2023 as Best Student Paper!

Recent Publications

Quickly discover relevant content by filtering publications.

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models

We introduce a new open-vocabulary SGG framework based on sequence generation. Our framework leverages vision-language pre-trained models (VLM) by incorporating an image-to-graph generation paradigm.

Learning by Correction: Efficient Tuning Task for Zero-Shot Generative Vision-Language Reasoning

We introduce Image-Conditioned Caption Correction (ICCC), a novel pre-training task designed to enhance VLMs’ zero-shot performance without the need for labeled task-aware data.

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

MacCap introduces a novel zero-shot image captioning framework with text-only training by noise injection training and visual subregion …

Contact

  • 201210 Shanghai Pudong Zhangjiang Campus:393 Middle Huaxia Road
  • SIST Building No.1 and take the stairs to Office 311 on Floor 3