Search Results for author: Zhenguang Liu

Found 36 papers, 22 papers with code

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection

1 code implementation4 Mar 2024 Zhongjie Ba, Qingyu Liu, Zhenguang Liu, Shuang Wu, Feng Lin, Li Lu, Kui Ren

In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature.

DeepFake Detection Face Swapping

Alleviating Structural Distribution Shift in Graph Anomaly Detection

1 code implementation25 Jan 2024 Yuan Gao, Xiang Wang, Xiangnan He, Zhenguang Liu, Huamin Feng, Yongdong Zhang

Graph anomaly detection (GAD) is a challenging binary classification problem due to its different structural distribution between anomalies and normal nodes -- abnormal nodes are a minority, therefore holding high heterophily and low homophily compared to normal nodes.

Binary Classification Graph Anomaly Detection

Red Teaming Visual Language Models

no code implementations23 Jan 2024 Mukai Li, Lei LI, Yuwei Yin, Masood Ahmed, Zhenguang Liu, Qi Liu

Additionally, we simply apply red teaming alignment to LLaVA-v1. 5 with Supervised Fine-tuning (SFT) using RTVLM, and this bolsters the models' performance with 10% in RTVLM test set, 13% in MM-Hal, and without noticeable decline in MM-Bench, overpassing other LLaVA-based models with regular alignment data.

Fairness

Let All be Whitened: Multi-teacher Distillation for Efficient Visual Retrieval

1 code implementation15 Dec 2023 Zhe Ma, Jianfeng Dong, Shouling Ji, Zhenguang Liu, Xuhong Zhang, Zonghui Wang, Sifeng He, Feng Qian, Xiaobo Zhang, Lei Yang

Instead of crafting a new method pursuing further improvement on accuracy, in this paper we propose a multi-teacher distillation framework Whiten-MTD, which is able to transfer knowledge from off-the-shelf pre-trained retrieval models to a lightweight student model for efficient visual retrieval.

Image Retrieval Retrieval +1

DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues

1 code implementation18 Sep 2023 Kun Pan, Yin Yifang, Yao Wei, Feng Lin, Zhongjie Ba, Zhenguang Liu, Zhibo Wang, Lorenzo Cavallaro, Kui Ren

However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution.

Continual Learning Contrastive Learning +5

Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization

1 code implementation13 Sep 2023 Zhenguang Liu, Xinyang Yu, Ruili Wang, Shuai Ye, Zhe Ma, Jianfeng Dong, Sifeng He, Feng Qian, Xiaobo Zhang, Roger Zimmermann, Lei Yang

We theoretically analyzed the mutual information between the label and the disentangled features, arriving at a loss that maximizes the extraction of task-relevant information from the original feature.

Disentanglement

Masked Diffusion Models Are Fast Distribution Learners

1 code implementation20 Jun 2023 Jiachen Lei, Qinglong Wang, Peng Cheng, Zhongjie Ba, Zhan Qin, Zhibo Wang, Zhenguang Liu, Kui Ren

In the pre-training stage, we propose to mask a high proportion (e. g., up to 90\%) of input images to approximately represent the primer distribution and introduce a masked denoising score matching objective to train a model to denoise visible areas.

Denoising Image Generation

Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization

no code implementations13 Jun 2023 Yuheng Yang, Haipeng Chen, Zhenguang Liu, Yingda Lyu, Beibei Zhang, Shuang Wu, Zhibo Wang, Kui Ren

However, the vanilla Euclidean space is not efficient for modeling important motion characteristics such as the joint-wise angular acceleration, which reveals the driving force behind the motion.

Action Recognition

CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-start Problem of Recommendation

no code implementations14 Mar 2023 Haonan Hu, Dazhong Rong, Jianhai Chen, Qinming He, Zhenguang Liu

Specifically, for a new item: B-EG calculates the similarity-based weighted sum of the ID embeddings of old items as its base embedding; S-EG generates its shift embedding not only with its attribute features but also with the average ID embedding of the users who interacted with it.

Attribute Meta-Learning

Who is Gambling? Finding Cryptocurrency Gamblers Using Multi-modal Retrieval Methods

1 code implementation27 Nov 2022 Zhengjie Huang, Zhenguang Liu, Jianhai Chen, Qinming He, Shuang Wu, Lei Zhu, Meng Wang

Meanwhile, decentralized applications have also attracted intense attention from the online gambling community, with more and more decentralized gambling platforms created through the help of smart contracts.

Retrieval

Invariant Feature Learning for Generalized Long-Tailed Classification

1 code implementation19 Jul 2022 Kaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang

In fact, even if the class is balanced, samples within each class may still be long-tailed due to the varying attributes.

Attribute Classification +1

Copy Motion From One to Another: Fake Motion Video Generation

no code implementations3 May 2022 Zhenguang Liu, Sifan Wu, Chejian Xu, Xiang Wang, Lei Zhu, Shuang Wu, Fuli Feng

3) To enhance texture details, we encode facial features with geometric guidance and employ local GANs to refine the face, feet, and hands.

Video Generation

2D Human Pose Estimation: A Survey

no code implementations15 Apr 2022 Haoming Chen, Runyang Feng, Sifan Wu, Hao Xu, Fengcheng Zhou, Zhenguang Liu

Briefly, existing approaches put their efforts in three directions, namely network architecture design, network training refinement, and post processing.

2D Human Pose Estimation Keypoint Detection

Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings

no code implementations7 Apr 2022 Yuhao Mao, Chong Fu, Saizhuo Wang, Shouling Ji, Xuhong Zhang, Zhenguang Liu, Jun Zhou, Alex X. Liu, Raheem Beyah, Ting Wang

To bridge this critical gap, we conduct the first large-scale systematic empirical study of transfer attacks against major cloud-based MLaaS platforms, taking the components of a real transfer attack into account.

Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation

1 code implementation CVPR 2022 Zhenguang Liu, Runyang Feng, Haoming Chen, Shuang Wu, Yixing Gao, Yunjun Gao, Xiang Wang

State-of-the-art methods strive to incorporate additional visual evidences from neighboring frames (supporting frames) to facilitate the pose estimation of the current frame (key frame).

Pose Estimation

3D Human Motion Prediction: A Survey

no code implementations3 Mar 2022 Kedi Lyu, Haipeng Chen, Zhenguang Liu, Beiqi Zhang, Ruili Wang

3D human motion prediction, predicting future poses from a given sequence, is an issue of great significance and challenge in computer vision and machine intelligence, which can help machines in understanding human behaviors.

Human motion prediction motion prediction

Motion Prediction via Joint Dependency Modeling in Phase Space

no code implementations7 Jan 2022 Pengxiang Su, Zhenguang Liu, Shuang Wu, Lei Zhu, Yifang Yin, Xuanjing Shen

In this paper, we introduce a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics.

Anatomy motion prediction

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

1 code implementation30 Dec 2021 Zhenguang Liu, Shuang Wu, Shuyuan Jin, Shouling Ji, Qi Liu, Shijian Lu, Li Cheng

One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results.

motion prediction

Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction

no code implementations29 Aug 2021 Fuchen Gao, Zhanquan Wang, Zhenguang Liu

Accurate prediction of metro passenger volume (number of passengers) is valuable to realize real-time metro system management, which is a pivotal yet challenging task in intelligent transportation.

Management

Exploring Lottery Ticket Hypothesis in Media Recommender Systems

1 code implementation2 Aug 2021 Yanfang Wang, Yongduo Sui, Xiang Wang, Zhenguang Liu, Xiangnan He

We get inspirations from the recently proposed lottery ticket hypothesis (LTH), which argues that the dense and over-parameterized model contains a much smaller and sparser sub-model that can reach comparable performance to the full model.

Recommendation Systems Representation Learning

Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection

1 code implementation24 Jul 2021 Zhenguang Liu, Peng Qian, Xiaoyang Wang, Yuan Zhuang, Lin Qiu, Xun Wang

Then, we propose a novel temporal message propagation network to extract the graph feature from the normalized graph, and combine the graph feature with designed expert patterns to yield a final detection system.

Vulnerability Detection

Aggregated Multi-GANs for Controlled 3D Human Motion Prediction

no code implementations17 Mar 2021 Zhenguang Liu, Kedi Lyu, Shuang Wu, Haipeng Chen, Yanbin Hao, Shouling Ji

Our method is compelling in that it enables manipulable motion prediction across activity types and allows customization of the human movement in a variety of fine-grained ways.

Human motion prediction motion prediction

Learning Intents behind Interactions with Knowledge Graph for Recommendation

2 code implementations14 Feb 2021 Xiang Wang, Tinglin Huang, Dingxian Wang, Yancheng Yuan, Zhenguang Liu, Xiangnan He, Tat-Seng Chua

In this study, we explore intents behind a user-item interaction by using auxiliary item knowledge, and propose a new model, Knowledge Graph-based Intent Network (KGIN).

Recommendation Systems Relation

Motion Prediction Using Trajectory Cues

1 code implementation ICCV 2021 Zhenguang Liu, Pengxiang Su, Shuang Wu, Xuanjing Shen, Haipeng Chen, Yanbin Hao, Meng Wang

Predicting human motion from a historical pose sequence is at the core of many applications in computer vision.

motion prediction

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

A Truthful FPTAS Mechanism for Emergency Demand Response in Colocation Data Centers

1 code implementation10 Jan 2019 Jian-hai Chen, Deshi Ye, Shouling Ji, Qinming He, Yang Xiang, Zhenguang Liu

Next, we prove that our mechanism is an FPTAS, i. e., it can be approximated within $1 + \epsilon$ for any given $\epsilon > 0$, while the running time of our mechanism is polynomial in $n$ and $1/\epsilon$, where $n$ is the number of tenants in the datacenter.

Computer Science and Game Theory

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