Search Results for author: An-An Liu

Found 15 papers, 4 papers with code

A Training-Free Plug-and-Play Watermark Framework for Stable Diffusion

no code implementations8 Apr 2024 Guokai Zhang, Lanjun Wang, Yuting Su, An-An Liu

We also have validated that our method is generalized to multiple versions of SDs, even without retraining the watermark model.

Denoising

How to Understand Named Entities: Using Common Sense for News Captioning

no code implementations11 Mar 2024 Ning Xu, Yanhui Wang, Tingting Zhang, Hongshuo Tian, Mohan Kankanhalli, An-An Liu

Our approach consists of three modules: (a) Filter Module aims to clarify the common sense concerning a named entity from two aspects: what does it mean?

Common Sense Reasoning

Rule-driven News Captioning

no code implementations8 Mar 2024 Ning Xu, Tingting Zhang, Hongshuo Tian, An-An Liu

News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article.

AnyScene: Customized Image Synthesis with Composited Foreground

no code implementations CVPR 2024 Ruidong Chen, Lanjun Wang, Weizhi Nie, Yongdong Zhang, An-An Liu

Recent advancements in text-to-image technology have significantly advanced the field of image customization.

Image Generation

Causality is all you need

no code implementations21 Nov 2023 Ning Xu, YiFei Gao, Hongshuo Tian, Yongdong Zhang, An-An Liu

In this paper, we propose the Causal Graph Routing (CGR) framework, an integrated causal scheme relying entirely on the intervention mechanisms to reveal the cause-effect forces hidden in data.

Document Classification

Image-Based Virtual Try-On: A Survey

1 code implementation8 Nov 2023 Dan Song, Xuanpu Zhang, Juan Zhou, Weizhi Nie, Ruofeng Tong, Mohan Kankanhalli, An-An Liu

Image-based virtual try-on aims to synthesize a naturally dressed person image with a clothing image, which revolutionizes online shopping and inspires related topics within image generation, showing both research significance and commercial potential.

Image Generation Virtual Try-on

T2IW: Joint Text to Image & Watermark Generation

no code implementations7 Sep 2023 An-An Liu, Guokai Zhang, Yuting Su, Ning Xu, Yongdong Zhang, Lanjun Wang

Furthermore, we strengthen the watermark robustness of our approach by subjecting the compound image to various post-processing attacks, with minimal pixel distortion observed in the revealed watermark.

Image Generation

Causal Disentanglement Hidden Markov Model for Fault Diagnosis

no code implementations6 Aug 2023 Rihao Chang, Yongtao Ma, Weizhi Nie, Jie Nie, An-An Liu

In modern industries, fault diagnosis has been widely applied with the goal of realizing predictive maintenance.

Disentanglement Time Series +1

Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning

1 code implementation29 Nov 2022 Zheren Fu, Zhendong Mao, Bo Hu, An-An Liu, Yongdong Zhang

They have overlooked the wide characteristic changes of different classes and can not model abundant intra-class variations for generations.

Image Augmentation Image Retrieval +5

Temporal Action Localization with Multi-temporal Scales

no code implementations16 Aug 2022 Zan Gao, Xinglei Cui, Tao Zhuo, Zhiyong Cheng, An-An Liu, Meng Wang, Shenyong Chen

However, the temporal features of a low-level scale lack enough semantics for action classification while a high-level scale cannot provide rich details of the action boundaries.

Action Classification Avg +1

Intrinsic Bias Identification on Medical Image Datasets

no code implementations24 Mar 2022 Shijie Zhang, Lanjun Wang, Lian Ding, An-An Liu, Senhua Zhu, Dandan Tu

However, scientists and practitioners are difficult to identify implicit biases in the datasets, which causes lack of reliable unbias test datasets to valid models.

Attribute valid

Zero-Shot Multi-View Indoor Localization via Graph Location Networks

1 code implementation6 Aug 2020 Meng-Jiun Chiou, Zhenguang Liu, Yifang Yin, An-An Liu, Roger Zimmermann

In this paper, we propose a novel neural network based architecture Graph Location Networks (GLN) to perform infrastructure-free, multi-view image based indoor localization.

Indoor Localization

Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking

no code implementations21 Jul 2016 Wenhui Li, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, Mohan Kankanhalli

To enable the study of this problem, there exist a vast number of action datasets, which are recorded under controlled laboratory settings, real-world surveillance environments, or crawled from the Internet.

Action Recognition Benchmarking +1

Clique-Graph Matching by Preserving Global & Local Structure

no code implementations CVPR 2015 Wei-Zhi Nie, An-An Liu, Zan Gao, Yu-Ting Su

This paper originally proposes the clique-graph and further presents a clique-graph matching method by preserving global and local structures.

Graph Matching Graph Similarity

Cannot find the paper you are looking for? You can Submit a new open access paper.