no code implementations • 29 Apr 2024 • Tianyidan Xie, Rui Ma, Qian Wang, Xiaoqian Ye, Feixuan Liu, Ying Tai, Zhenyu Zhang, Zili Yi
In the image generation module, we employ a text-guided canny-to-image generation model to create a template image based on the edge map of the foreground image and language prompts, and an image refiner to produce the outcome by blending the input foreground and the template image.
no code implementations • 22 Apr 2024 • Hao Wang, Qingshan Xu, Hongyuan Chen, Rui Ma
In this work, we introduce PGAHum, a prior-guided geometry and appearance learning framework for high-fidelity animatable human reconstruction.
no code implementations • 17 Apr 2024 • Jiaxing Zhao, Peng Zheng, Rui Ma
To address this issue, we propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes.
no code implementations • 17 Mar 2024 • Ye Wang, Zili Yi, Rui Ma
Personalized text-to-image (T2I) models not only produce lifelike and varied visuals but also allow users to tailor the images to fit their personal taste.
no code implementations • 15 Mar 2024 • Peng Zheng, Tao Liu, Zili Yi, Rui Ma
Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at $1024^2$ resolution, benefiting from our proposed 3D-aware super-resolution module.
no code implementations • 14 Mar 2024 • Frank Zhang, Yibo Zhang, Quan Zheng, Rui Ma, Wei Hua, Hujun Bao, Weiwei Xu, Changqing Zou
Text-driven 3D scene generation techniques have made rapid progress in recent years.
no code implementations • 22 Feb 2024 • Renyi Mao, Qingshan Xu, Peng Zheng, Ye Wang, Tieru Wu, Rui Ma
In this paper, we aim for both fast and high-quality implicit field learning, and propose TaylorGrid, a novel implicit field representation which can be efficiently computed via direct Taylor expansion optimization on 2D or 3D grids.
no code implementations • 31 Jan 2024 • Dong Chen, Ning Liu, Yichen Zhu, Zhengping Che, Rui Ma, Fachao Zhang, Xiaofeng Mou, Yi Chang, Jian Tang
Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.
no code implementations • 8 Jan 2024 • Ruiqi Liu, Peng Zheng, Ye Wang, Rui Ma
Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities.
no code implementations • 4 Jan 2024 • Rui Ma, Qiang Zhou, Bangjun Xiao, Yizhu Jin, Daquan Zhou, Xiuyu Li, Aishani Singh, Yi Qu, Kurt Keutzer, Xiaodong Xie, Jingtong Hu, Zhen Dong, Shanghang Zhang
Copyright is a legal right that grants creators the exclusive authority to reproduce, distribute, and profit from their creative works.
no code implementations • 29 Dec 2023 • Linlian Jiang, Pan Chen, Ye Wang, Tieru Wu, Rui Ma
Inferring missing regions from severely occluded point clouds is highly challenging.
no code implementations • 14 Oct 2023 • Hao Wang, Qiang Song, Ruofeng Yin, Rui Ma, Yizhou Yu, Yi Chang
In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images.
no code implementations • 17 Jun 2023 • Shitian Li, Chunlin Tian, Kahou Tam, Rui Ma, Li Li
In this systematic survey, we aim to explore the current state-of-the-art techniques for breaking on-device training memory walls, focusing on methods that can enable larger and more complex models to be trained on resource-constrained devices.
1 code implementation • 2 May 2023 • Yuanzheng Ma, Wangting Zhou, Rui Ma, Sihua Yang, Yansong Tang, Xun Guan
To address this challenge, we propose a novel approach that employs a super-resolution PAA method trained with forged PAA images.
no code implementations • 19 Apr 2023 • Rui Ma, Xiaowen Yang, Meng Zhan
With this simplest model, the roles of both nodes and the network become apparent. Simulations verify the proposed model framework in the modified 9-bus system.
no code implementations • 20 Mar 2023 • Ye Wang, Bowei Jiang, Changqing Zou, Rui Ma
Existing cross-modal contrastive representation learning (XM-CLR) methods such as CLIP are not fully suitable for multifold data as they only consider one positive pair and treat other pairs as negative when computing the contrastive loss.
1 code implementation • 2 Jan 2023 • Shuangmei Wang, Rui Ma, Tieru Wu, Yang Cao
Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification.
1 code implementation • 28 Dec 2022 • Ye Wang, Rui Ma, Xiaoqing Ma, Honghua Cui, Yubin Xiao, Xuan Wu, You Zhou
BMEC contains 5, 666 images of individual erythroid cells, each of which is extracted from the bone marrow erythroid cell smears and professionally annotated to one of the four types of erythroid cells.
1 code implementation • 24 Dec 2022 • Rui Ma, Mengxi Guo, Yi Hou, Fan Yang, Yuan Li, Huizhu Jia, Xiaodong Xie
The CIN is composed of the invertible part to achieve high imperceptibility and the non-invertible part to strengthen the robustness against strong noise attacks.
no code implementations • 10 Dec 2022 • Tao Yu, Jinge Ma, Guilin Li, Dongyu Yang, Rui Ma, Yishi Shi
This method can expand the application range of visual cryptography and further increase the security of visual cryptography.
1 code implementation • 15 Sep 2022 • Rui Ma, Qingbo Wu, King Ngi Ngan, Hongliang Li, Fanman Meng, Linfeng Xu
More specifically, we develop a dynamic parameter isolation strategy to sequentially update the task-specific parameter subsets, which are non-overlapped with each other.
no code implementations • 29 Aug 2022 • Rui Ma, Ning Liu, Jingsong Yuan, Huafeng Yang, Jiandong Zhang
Traditional recommendation systems mainly focus on modeling user interests.
1 code implementation • 17 Jun 2022 • Hui Li, Zihao Li, Rui Ma, Tieru Wu
In this paper, we propose a novel CAM weighting scheme, named FD-CAM, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation.
no code implementations • 31 May 2022 • Ziyuan Xia, Anchen Sun, Jingyi Xu, Yuanzhe Peng, Rui Ma, Minghui Cheng
This survey paper conducts a comprehensive analysis of the evolution and contemporary landscape of recommendation systems, which have been extensively incorporated across a myriad of web applications.
no code implementations • 27 Apr 2022 • Weidong Cao, Mouhacine Benosman, Xuan Zhang, Rui Ma
The design automation of analog circuits is a longstanding challenge.
no code implementations • 22 Apr 2022 • Rui Ma, Evangelos Georganas, Alexander Heinecke, Andrew Boutros, Eriko Nurvitadhi
The overhead of these collective communication operations in a distributed AI training system can bottleneck its performance, with more pronounced effects as the number of nodes increases.
no code implementations • CVPR 2022 • Lina Guo, Xinjie Shi, Dailan He, Yuanyuan Wang, Rui Ma, Hongwei Qin, Yan Wang
JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems.
5 code implementations • CVPR 2022 • Dailan He, Ziming Yang, Weikun Peng, Rui Ma, Hongwei Qin, Yan Wang
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders.
Ranked #1 on Image Compression on kodak
no code implementations • 26 Feb 2022 • Weidong Cao, Mouhacine Benosman, Xuan Zhang, Rui Ma
The design automation of analog circuits is a longstanding challenge in the integrated circuit field.
1 code implementation • 22 Jan 2022 • Xi Zheng, Rui Ma, Rui Gao, Qi Hao
In this paper, we propose a phase based Simultaneous Localization and Mapping (Phase-SLAM) framework for fast and accurate SLI sensor pose estimation and 3D object reconstruction.
no code implementations • 15 Dec 2021 • Rui Ma, Sara Eftekharnejad, Chen Zhong, Mustafa Cenk Gursoy
In this paper, a new data-driven TSA approach is developed for TSA with fewer data compared to the conventional methods.
1 code implementation • 13 Dec 2021 • Hang Zhou, Rui Ma, Ling-Xiao Zhang, Lin Gao, Ali Mahdavi-Amiri, Hao Zhang
Specifically, our network takes the semantic layout features from the input scene image, features encoded from the edges and silhouette in the input object patch, as well as a latent code as inputs, and generates a 2D spatial affine transform defining the translation and scaling of the object patch.
no code implementations • 18 Nov 2021 • Udara De Silva, Toshiaki Koike-Akino, Rui Ma, Ao Yamashita, Hideyuki Nakamizo
This study reports a novel hardware-friendly modular architecture for implementing one dimensional convolutional neural network (1D-CNN) digital predistortion (DPD) technique to linearize RF power amplifier (PA) real-time. The modular nature of our design enables DPD system adaptation for variable resource and timing constraints. Our work also presents a co-simulation architecture to verify the DPD performance with an actual power amplifier hardware-in-the-loop. The experimental results with 100 MHz signals show that the proposed 1D-CNN obtains superior performance compared with other neural network architectures for real-time DPD application.
no code implementations • 5 Nov 2021 • Vishnu Sanjay Ramiya Srinivasan, Rui Ma, Qiang Tang, Zili Yi, Zhan Xu
Recent learning-based inpainting algorithms have achieved compelling results for completing missing regions after removing undesired objects in videos.
no code implementations • 20 Oct 2021 • Rui Ma, Xian Du
Considering the nature of temporal continuity and consecution of the product images, in this paper, we propose a closed-loop feedback registration algorithm for matching and stitching the deformable printed patterns on a moving flexible substrate.
no code implementations • 20 Oct 2021 • Rui Ma, Johnathan Czernik, Xian Du
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e. g., bicubic downsampling.
no code implementations • 28 Jul 2021 • Yihong Yang, Sheng Ding, YuWen Liu, Shunmei Meng, Xiaoxiao Chi, Rui Ma, Chao Yan
However, traditional anomaly detection algorithms originally designed for anomaly detection in static data have not properly considered the inherent characteristics of data stream produced by wireless sensor such as infiniteness, correlations and concept drift, which may pose a considerable challenge on anomaly detection based on data stream, and lead to low detection accuracy and efficiency.
no code implementations • 9 Apr 2021 • Jiongchao Jin, Arezou Fatemi, Wallace Lira, Fenggen Yu, Biao Leng, Rui Ma, Ali Mahdavi-Amiri, Hao Zhang
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research.
no code implementations • Knowledge-Based Systems, 105916. 2020 • Yan Zhang, Hua Xu, Yunfeng Xu, Junhui Deng, Juan Gu, Rui Ma, Jie Lai, Jiangtao Hu, Xiaoshuai Yu, Lei Hou, Lidong Gu, Yanling Wei, Yichao Xiao, Junhao Lu
In this paper, we try to give a more visual and detailed definition of structural hole spanner based on the existing work, and propose a novel algorithm to identify structural hole spanner based on community forest model and diminishing marginal utility.
no code implementations • 22 Nov 2019 • Tianyang Zhang, Rui Ma
The cells' nuclei identification task is also kind of image segmentation.
1 code implementation • 18 May 2018 • Lisha Cui, Rui Ma, Pei Lv, Xiaoheng Jiang, Zhimin Gao, Bing Zhou, Mingliang Xu
The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps.
no code implementations • 29 Sep 2015 • Sanggyun Kim, Diego Mesa, Rui Ma, Todd P. Coleman
We demonstrate with optimal transport theory that when the source distribution can be easily sampled from and the target distribution is log-concave, this can be tractably solved with convex optimization.