no code implementations • 10 Feb 2025 • Siwei Meng, Yawei Luo, Ping Liu
By presenting an in-depth analysis of physics-grounded AIGC, this survey aims to bridge the gap between generative models and physical realism, providing insights that inspire future research in physically consistent content generation.
no code implementations • 8 Feb 2025 • Ping Liu, Jiawei Du
Dataset distillation, which condenses large-scale datasets into compact synthetic representations, has emerged as a critical solution for training modern deep learning models efficiently.
no code implementations • 16 Dec 2024 • Bingwen Hu, Heng Liu, Zhedong Zheng, Ping Liu
Our proposed multi-modal collaborative framework enables the production of realistic and high-quality SR images at significant up-scaling factors.
no code implementations • 28 Nov 2024 • Jiacheng Wang, Zhedong Zheng, Wei Xu, Ping Liu
Given a single image of a target object, image-to-3D generation aims to reconstruct its texture and geometric shape.
no code implementations • 25 Nov 2024 • Feifei Shao, Ping Liu, Zhao Wang, Yawei Luo, Hongwei Wang, Jun Xiao
We identify inter-task and intra-task sensitivity issues in current ICL methods for PCP, which we attribute to inflexible sampling strategies lacking context adaptation at the point and prompt levels.
no code implementations • 14 Nov 2024 • XiaoLe He, Ping Liu, Junling Wang
This paper investigates these limits by analyzing the boundaries of super- resolution algorithms for space targets and examines the relationships between key contributing factors.
no code implementations • 14 Oct 2024 • Zikai Zhang, Jiahao Xu, Ping Liu, Rui Hu
Specifically, Federated FMs (FedFMs) fine-tuning using low-rank adaptation (LoRA) modules instead of the full model over multiple clients can achieve both parameter efficiency and data privacy.
no code implementations • 25 Sep 2024 • Ning Sun, YuFei Wang, Yuwei Zhang, Jixiang Wan, Shenyue Wang, Ping Liu, Xudong Zhang
Human Activity Recognition (HAR) has gained great attention from researchers due to the popularity of mobile devices and the need to observe users' daily activity data for better human-computer interaction.
no code implementations • 19 Sep 2024 • Mingyu Wang, Ping Liu, Jihong Gu, Xiaofan Jia, Abdulkadir C. Yucel
A fast multipole method (FMM)-accelerated surface integral equation (SIE) simulator, called XRL, is proposed for broadband resistance/inductance (RL) extraction under the magneto-quasi-static assumption.
no code implementations • 13 Aug 2024 • Xin Zhang, Jiawei Du, Ping Liu, Joey Tianyi Zhou
This leads to inefficient utilization of the distillation budget and oversight of inter-class feature distributions, which ultimately limits the effectiveness and efficiency, as demonstrated in our analysis.
2 code implementations • 11 Jun 2024 • Ping Liu, Qiqi Tao, Joey Tianyi Zhou
We provide comprehensive taxonomies of detection techniques, discuss the evolution of generative methods from auto-encoders and GANs to diffusion models, and categorize these technologies by their unique attributes.
1 code implementation • 20 Mar 2024 • Yifan Wu, Jiawei Du, Ping Liu, Yuewei Lin, Wei Xu, Wenqing Cheng
Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance.
1 code implementation • 12 Mar 2024 • Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei
Consequently, these detectors have exhibited a lack of proficiency in learning the frequency domain and tend to overfit to the artifacts present in the training data, leading to suboptimal performance on unseen sources.
1 code implementation • 11 Mar 2024 • Chuangchuang Tan, Ping Liu, Renshuai Tao, Huan Liu, Yao Zhao, Baoyuan Wu, Yunchao Wei
Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources.
no code implementations • 21 Feb 2024 • Jianqiang Shen, Yuchin Juan, Shaobo Zhang, Ping Liu, Wen Pu, Sriram Vasudevan, Qingquan Song, Fedor Borisyuk, Kay Qianqi Shen, Haichao Wei, Yunxiang Ren, Yeou S. Chiou, Sicong Kuang, Yuan Yin, Ben Zheng, Muchen Wu, Shaghayegh Gharghabi, Xiaoqing Wang, Huichao Xue, Qi Guo, Daniel Hewlett, Luke Simon, Liangjie Hong, Wenjing Zhang
Web-scale search systems typically tackle the scalability challenge with a two-step paradigm: retrieval and ranking.
no code implementations • 20 Feb 2024 • Ping Liu, Haichao Wei, Xiaochen Hou, Jianqiang Shen, Shihai He, Kay Qianqi Shen, Zhujun Chen, Fedor Borisyuk, Daniel Hewlett, Liang Wu, Srikant Veeraraghavan, Alex Tsun, Chengming Jiang, Wenjing Zhang
This methodology decouples the training of the GNN model from that of existing Deep Neural Nets (DNN) models, eliminating the need for frequent GNN retraining while maintaining up-to-date graph signals in near realtime, allowing for the effective integration of GNN insights through transfer learning.
no code implementations • 17 Feb 2024 • Fedor Borisyuk, Shihai He, Yunbo Ouyang, Morteza Ramezani, Peng Du, Xiaochen Hou, Chengming Jiang, Nitin Pasumarthy, Priya Bannur, Birjodh Tiwana, Ping Liu, Siddharth Dangi, Daqi Sun, Zhoutao Pei, Xiao Shi, Sirou Zhu, Qianqi Shen, Kuang-Hsuan Lee, David Stein, Baolei Li, Haichao Wei, Amol Ghoting, Souvik Ghosh
In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework.
1 code implementation • 7 Feb 2024 • Tianle Zhang, Yuchen Zhang, Kun Wang, Kai Wang, Beining Yang, Kaipeng Zhang, Wenqi Shao, Ping Liu, Joey Tianyi Zhou, Yang You
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns.
1 code implementation • 4 Jan 2024 • Jiacheng Wang, Ping Liu, Wei Xu
Existing text-to-image editing methods tend to excel either in rigid or non-rigid editing but encounter challenges when combining both, resulting in misaligned outputs with the provided text prompts.
2 code implementations • CVPR 2024 • Chuangchuang Tan, Huan Liu, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, Yunchao Wei
Recently, the proliferation of highly realistic synthetic images, facilitated through a variety of GANs and Diffusions, has significantly heightened the susceptibility to misuse.
no code implementations • 27 Nov 2023 • Baolu Li, Ping Liu, Lan Fu, Jinlong Li, Jianwu Fang, Zhigang Xu, Hongkai Yu
Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for the Vehicle Re-ID models in the real world.
no code implementations • 13 Aug 2023 • Yuyang Yin, Dejia Xu, Chuangchuang Tan, Ping Liu, Yao Zhao, Yunchao Wei
Low light enhancement has gained increasing importance with the rapid development of visual creation and editing.
no code implementations • 3 Jul 2023 • Gabriel Tjio, Ping Liu, Yawei Luo, Chee Keong Kwoh, Joey Zhou Tianyi
Our workflow generates target-like images using the noisy predictions from the original target domain images.
no code implementations • 24 May 2023 • Feifei Shao, Yawei Luo, Lei Chen, Ping Liu, Wei Yang, Yi Yang, Jun Xiao
In this paper, we conduct a thorough causal analysis to investigate the origins of biased activation.
no code implementations • 25 Apr 2023 • Jiacheng Wang, Ping Liu, Jingen Liu, Wei Xu
To address these limitations, we propose a Text-guided Eyeglasses Manipulation method that allows for control of the eyeglasses shape and style based on a binary mask and text, respectively.
no code implementations • 24 Apr 2023 • Yaxin Shi, Xiaowei Zhou, Ping Liu, Ivor W. Tsang
Furthermore, we propose the use of transition consistency, defined on the transition variable, to enable regularization of consistency on unobserved translations, which is omitted in previous works.
no code implementations • 18 Apr 2023 • Gabriel Tjio, Ping Liu, Chee-Keong Kwoh, Joey Tianyi Zhou
To tackle this challenge, we introduce a dual-stage Feature Transform (dFT) layer within the Adversarial Semantic Hallucination+ (ASH+) framework.
no code implementations • 2 Feb 2023 • Ping Liu, Habib Ammari
We show that the resolution of multi-illumination imaging is approximately determined by the new imaging kernel from our operator theory and better resolution can be realized by sparsity-promoting techniques in practice but only for resolving very sparse sources.
no code implementations • ICCV 2023 • Yanhua Yu, Siyuan Shen, Zi Wang, Binbin Huang, Yuehan Wang, Xingyue Peng, Suan Xia, Ping Liu, Ruiqian Li, Shiying Li
Recovering information from non-line-of-sight (NLOS) imaging is a computationally-intensive inverse problem.
1 code implementation • ICCV 2023 • Chi Zhang, Zhang Xiaoman, Ekanut Sotthiwat, Yanyu Xu, Ping Liu, Liangli Zhen, Yong liu
Federated learning has gained recognitions as a secure approach for safeguarding local private data in collaborative learning.
no code implementations • 1 Dec 2022 • Ping Liu, Habib Ammari
In this paper, we analyze the capacity of super-resolution of one-dimensional positive sources.
no code implementations • 28 Nov 2022 • Ping Liu, Habib Ammari
The second crucial contribution of this paper is the theoretical proof of a two-point resolution limit in multi-dimensional spaces.
no code implementations • 24 Nov 2022 • Ping Liu, Yanchen He, Habib Ammari
A priori information on the positivity of source intensities is ubiquitous in imaging fields and is also important for a multitude of super-resolution and deconvolution algorithms.
1 code implementation • 29 Sep 2022 • Ping Liu, Xin Yu, Joey Tianyi Zhou
In this work, we first introduce a meta knowledge representation method that extracts meta knowledge from distributed clients.
no code implementations • 14 May 2022 • Ping Liu, Habib Ammari
The stability result exhibits the optimal performance of sparsity promoting in solving such problems; (iii) Our techniques pave the way for improving the estimate for resolution limits in higher-dimensional super-resolutions to nearly optimal; (iv) Inspired by these new techniques, we propose a new coordinate-combination-based model order detection algorithm for two-dimensional DOA estimation and theoretically demonstrate its optimal performance, and (v) we also propose a new coordinate-combination-based MUSIC algorithm for super-resolving sources in two-dimensional DOA estimation.
no code implementations • 8 Apr 2022 • Ping Liu, Habib Ammari
This result is derived by an observation that the inherent cut-off frequency for the velocity recovery can be viewed as the total observation time multiplies the cut-off frequency of the imaging system, which may lead to a better resolution limit as compared to the one for each diffraction-limited frame.
no code implementations • 1 Apr 2022 • Ping Liu, Hai Zhang
We consider the problem of resolving closely spaced point sources in one dimension from their Fourier data in a bounded domain.
no code implementations • 25 Feb 2022 • Feifei Shao, Yawei Luo, Ping Liu, Jie Chen, Yi Yang, Yulei Lu, Jun Xiao
To deploy SSDR-AL in a more practical scenario, we design a noise-aware iterative labeling strategy to confront the "noisy annotation" problem introduced by the previous "dominant labeling" strategy in superpoints.
no code implementations • 22 Feb 2022 • Ping Liu, Sanghyeon Yu, Ola Sabet, Lucas Pelkmans, Habib Ammari
In this paper, we study the spectral estimation problem of estimating the locations of a fixed number of point sources given multiple snapshots of Fourier measurements in a bounded domain.
no code implementations • 29 Dec 2021 • Zhengqing Pan, Ruiqian Li, Tian Gao, Zi Wang, Ping Liu, Siyuan Shen, Tao Wu, Jingyi Yu, Shiying Li
There has been an increasing interest in deploying non-line-of-sight (NLOS) imaging systems for recovering objects behind an obstacle.
no code implementations • 28 Nov 2021 • Yang Peng, Ping Liu, Yawei Luo, Pan Zhou, Zichuan Xu, Jingen Liu
Unsupervised domain adaptive person re-identification has received significant attention due to its high practical value.
Domain Adaptive Person Re-Identification
Person Re-Identification
no code implementations • 3 Aug 2021 • Bingwen Hu, Ping Liu, Zhedong Zheng, Mingwu Ren
Third, a Try-on Synthesis Module (TSM) combines the coarse result and the warped clothes to generate the final virtual try-on image, preserving details of the desired clothes and under the desired pose.
no code implementations • 2 Aug 2021 • Yang Zhang, Xin Yu, Xiaobo Lu, Ping Liu
Specifically, we design a novel cross-modal transformer module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively.
no code implementations • 20 Jun 2021 • Ping Liu, Yuewei Lin, Yang He, Yunchao Wei, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh, Jingen Liu
In this paper, we propose to utilize Automated Machine Learning to adaptively search a neural architecture for deepfake detection.
1 code implementation • 8 Jun 2021 • Gabriel Tjio, Ping Liu, Joey Tianyi Zhou, Rick Siow Mong Goh
In this work, we propose an adversarial semantic hallucination approach (ASH), which combines a class-conditioned hallucination module and a semantic segmentation module.
no code implementations • 22 Mar 2021 • Ping Liu, Hai Zhang
Our results indicate that there exists a phase transition phenomenon regarding to the super-resolution factor and the signal-to-noise ratio in each of the two recovery problems.
no code implementations • 9 Mar 2021 • Yaxin Shi, Xiaowei Zhou, Ping Liu, Ivor Tsang
To benefit the generalization ability of the translation model, we propose transition encoding to facilitate explicit regularization of these two {kinds} of consistencies on unseen transitions.
1 code implementation • 2 Jan 2021 • Siyuan Shen, Zi Wang, Ping Liu, Zhengqing Pan, Ruiqian Li, Tian Gao, Shiying Li, Jingyi Yu
We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging.
no code implementations • 26 Aug 2020 • Ping Liu, Yuewei Lin, Zibo Meng, Lu Lu, Weihong Deng, Joey Tianyi Zhou, Yi Yang
In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.
no code implementations • 18 May 2020 • Ping Liu, Yunchao Wei, Zibo Meng, Weihong Deng, Joey Tianyi Zhou, Yi Yang
However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training.
no code implementations • 7 May 2020 • Chenyou Fan, Ping Liu
This work studies training generative adversarial networks under the federated learning setting.
1 code implementation • NeurIPS 2020 • Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, Yi Yang
We aim at the problem named One-Shot Unsupervised Domain Adaptation.
domain classification
One-shot Unsupervised Domain Adaptation
+2
no code implementations • 26 Mar 2020 • Qilei Chen, Ping Liu, Jing Ni, Yu Cao, Benyuan Liu, Honggang Zhang
The first one is that our dataset is not fully labeled, i. e., only a subset of all lesion instances are marked.
no code implementations • 3 Mar 2020 • Ziling Wu, Ping Liu, Zheng Hu, Bocheng Li, Jun Wang
Our methods can significantly reduce the cost of development and maintenance of anomaly detection.
no code implementations • 9 Feb 2020 • Yang Zhang, Ivor W. Tsang, Jun Li, Ping Liu, Xiaobo Lu, Xin Yu
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
1 code implementation • ICCV 2019 • Zongxin Yang, Jian Dong, Ping Liu, Yi Yang, Shuicheng Yan
The second challenge is how to maintain high quality in generated results, especially for multi-step generations in which generated regions are spatially far away from the initial input.
1 code implementation • 16 Sep 2019 • Bingwen Hu, Zhedong Zheng, Ping Liu, Wankou Yang, Mingwu Ren
Given two facial images with and without eyeglasses, the proposed model learns to swap the eye area in two faces.
no code implementations • 6 Jun 2019 • Jie Cai, Zibo Meng, Ahmed Shehab Khan, Zhiyuan Li, James O'Reilly, Shizhong Han, Ping Liu, Min Chen, Yan Tong
In this paper, we proposed two strategies to fuse information extracted from different modalities, i. e., audio and visual.
no code implementations • SEMEVAL 2019 • Ping Liu, Wen Li, Liang Zou
Transfer learning and domain adaptive learning have been applied to various fields including computer vision (e. g., image recognition) and natural language processing (e. g., text classification).
no code implementations • 8 Apr 2019 • Yang He, Ping Liu, Linchao Zhu, Yi Yang
In addition, when evaluating the filter importance, only the magnitude information of the filters is considered.
no code implementations • ICCV 2019 • Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, Yi Yang
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks in which the latent representations are overcomplex.
no code implementations • 23 Jan 2019 • Guanghan Ning, Ping Liu, Xiaochuan Fan, Chi Zhang
Both the tasks of multi-person human pose estimation and pose tracking in videos are quite challenging.
3 code implementations • CVPR 2019 • Yang He, Ping Liu, Ziwei Wang, Zhilan Hu, Yi Yang
In this paper, we analyze this norm-based criterion and point out that its effectiveness depends on two requirements that are not always met: (1) the norm deviation of the filters should be large; (2) the minimum norm of the filters should be small.
1 code implementation • 26 Sep 2018 • Yawei Luo, Tao Guan, Junqing Yu, Ping Liu, Yi Yang
To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning.
Ranked #4 on
Node Classification
on Cora: fixed 20 node per class
1 code implementation • 18 Apr 2018 • Ping Liu, Joshua Guberman, Libby Hemphill, Aron Culotta
Online antisocial behavior, such as cyberbullying, harassment, and trolling, is a widespread problem that threatens free discussion and has negative physical and mental health consequences for victims and communities.
no code implementations • 14 Mar 2018 • Zhang Li, Zheyu Hu, Jiaolong Xu, Tao Tan, Hui Chen, Zhi Duan, Ping Liu, Jun Tang, Guoping Cai, Quchang Ouyang, Yuling Tang, Geert Litjens, Qiang Li
Aim: Early detection and correct diagnosis of lung cancer are the most important steps in improving patient outcome.
no code implementations • 10 Feb 2018 • Tao Tan, Zhang Li, Haixia Liu, Ping Liu, Wenfang Tang, Hui Li, Yue Sun, Yusheng Yan, Keyu Li, Tao Xu, Shanshan Wan, Ke Lou, Jun Xu, Huiming Ying, Quchang Ouyang, Yuling Tang, Zheyu Hu, Qiang Li
To help doctors to be more selective on biopsies and provide a second opinion on diagnosis, in this work, we propose a computer-aided diagnosis (CAD) system for lung diseases including cancers and tuberculosis (TB).
no code implementations • 29 Jun 2017 • Zibo Meng, Shizhong Han, Ping Liu, Yan Tong
Instead of solely improving visual observations, this paper presents a novel audiovisual fusion framework, which makes the best use of visual and acoustic cues in recognizing speech-related facial AUs.
no code implementations • CVPR 2014 • Ping Liu, Shizhong Han, Zibo Meng, Yan Tong
A training process for facial expression recognition is usually performed sequentially in three individual stages: feature learning, feature selection, and classifier construction.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1