Explanipedia

DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition Open

Xinzhu Li, Juepeng Zheng, Yikun Chen, Xudong Mao, Guanghui Yue , et al. · 2025

Robust gait recognition requires highly discriminative representations, which are closely tied to input modalities. While binary silhouettes and skeletons have dominated recent literature, these 2D representations fall short of capturing s…

VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering Open

Yiran Meng, Jiangang Ye, Wei Zhou, Guanghui Yue, Xudong Mao , et al. · 2025

Cross-video question answering presents significant challenges beyond traditional single-video understanding, particularly in establishing meaningful connections across video streams and managing the complexity of multi-source information …

CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization Open

Feize Wu, Yun Pang, Junyi Zhang, Lianyu Pang, Jian Yin , et al. · 2025

Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our appr…

ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer Open

Bolin Chen, Baoquan Zhao, Haoran Xie, Yi Cai, Qing Li , et al. · 2025

Style transfer involves transferring the style from a reference image to the content of a target image. Recent advancements in LoRA-based (Low-Rank Adaptation) methods have shown promise in effectively capturing the style of a single image…

The Quiet Giant: Identification, Effectors, Molecular Mechanism, Physiological and Pathological Function in mRNA 5-methylcytosine Modification Open

Ruyue Wang, Lifeng Ding, Yudong Lin, Wenqin Luo, Zhehao Xu , et al. · 2024

5-Methylcytosine (m5C) is a prevalent nucleotide alteration observed in transfer RNA (tRNA) and ribosomal RNA (rRNA), and it is also widely distributed in the transcriptome, serving as one of the internal modifications of messenger RNA (mR…

CoRe: Context-Regularized Text Embedding Learning for Text-to-Image Personalization Open

Feize Wu, Yun Pang, Junyi Zhang, Lianyu Pang, Jian Yin , et al. · 2024

Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our appr…

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation Open

Lianyu Pang, Jian Yin, Baoquan Zhao, Feize Wu, Fu Lee Wang , et al. · 2024

Recent advances in text-to-image models have enabled high-quality personalized image synthesis of user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image per…

Cross Initialization for Personalized Text-to-Image Generation Open

Lianyu Pang, Jian Yin, Haoran Xie, Qiping Wang, Qing Li , et al. · 2023

Recently, there has been a surge in face personalization techniques, benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these, a notable method is Textual Inversion, which generates personalized i…

Catalytic-CO2-Desorption Studies of BZA-AEP Mixed Absorbent by the Lewis Acid Catalyst CeO2-γ-Al2O3 Open

Shenghua Liu, Xudong Mao, Hao Chen, Xinbo Zhu, Guohua Yang · 2023

Traditional organic amines exhibit inferior desorption performance and high regeneration energy consumption. The implementation of solid acid catalysts presents an efficacious approach to mitigate regeneration energy consumption. Thus, inv…

Study on Benzylamine(BZA) and Aminoethylpiperazine(AEP) Mixed Absorbent on Ship-Based Carbon Capture Open

Xudong Mao, Hao Chen, Yubing Wang, Xinbo Zhu, Guohua Yang · 2023

To find suitable absorbents for ship-based carbon capture, the absorption and desorption properties of four mixed aqueous amines based on BZA were investigated, and the results indicated that BZA-AEP had the best absorption and desorption …

Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability Open

Xudong Mao, Liujuan Cao, Aurele T. Gnanha, Zhenguo Yang, Qing Li , et al. · 2022

GAN inversion aims to invert an input image into the latent space of a pre-trained GAN. Despite the recent advances in GAN inversion, there remain challenges to mitigate the tradeoff between distortion and editability, i.e. reconstructing …

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme. Open

Shaojie Li, Jie Wu, Xuefeng Xiao, Fei Chao, Xudong Mao , et al. · 2021

Recently, a series of algorithms have been explored for GAN compression, which aims to reduce tremendous computational overhead and memory usages when deploying GANs on resource-constrained edge devices. However, most of the existing GAN c…

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme Open

Shaojie Li, Jie Wu, Xuefeng Xiao, Fei Chao, Xudong Mao , et al. · 2021

Recently, a series of algorithms have been explored for GAN compression, which aims to reduce tremendous computational overhead and memory usages when deploying GANs on resource-constrained edge devices. However, most of the existing GAN c…

The ByteDance Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2021 Open

Keke Wang, Xudong Mao, Hao Wu, Chen Ding, Chuxiang Shang , et al. · 2021

This paper describes the ByteDance speaker diarization system for the fourth track of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). The VoxSRC-21 provides both the dev set and test set of VoxConverse for use in validation an…

Generative Semi-supervised Learning for Multivariate Time Series Imputation Open

Xiaoye Miao, Yangyang Wu, Jun Wang, Yunjun Gao, Xudong Mao , et al. · 2021

The missing values, widely existed in multivariate time series data, hinder the effective data analysis. Existing time series imputation methods do not make full use of the label information in real-life time series data. In this paper, we…

Image-to-image Translation via Hierarchical Style Disentanglement Open

Xinyang Li, Shengchuan Zhang, Jie Hu, Liujuan Cao, Xiaopeng Hong , et al. · 2021

Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks. However, due to the unexplored…

Collaborative Learning of Bidirectional Decoders for Unsupervised Text Style Transfer Open

Yun Ma, Yangbin Chen, Xudong Mao, Qing Li · 2021

Unsupervised text style transfer aims to alter the underlying style of the text to a desired value while keeping its style-independent semantics, without the support of parallel training corpora. Existing methods struggle to achieve both h…

miR-194-5p negatively regulates the proliferation and differentiation of rabbit skeletal muscle satellite cells Open

Yu Shi, Xudong Mao, Mingcheng Cai, Shenqiang Hu, Xiulan Lai , et al. · 2020

Skeletal muscle satellite cells (SMSCs), also known as a multipotential stem cell population, play a crucial role during muscle growth and regeneration. In recent years, numerous miRNAs have been associated with the proliferation and diffe…

Virtual Mixup Training for Unsupervised Domain Adaptation Open

Xudong Mao, Yun Ma, Zhenguo Yang, Yangbin Chen, Qing Li · 2019

We study the problem of unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain. Recently, the cluster assumption has been applied to unsupervised domain adaptati…

Genetic diversities of <i>MT-ND3</i> and <i>MT-ND4L</i> genes are associated with high-altitude adaptation Open

Xudong Mao, Yu Shi, Xiaohu Liang, Mingcheng Cai, Xue Yang , et al. · 2018

Mitochondria can produce the energy currency of the cell through respiration which would be affected by variation in mitochondrial DNA (mtDNA). We sequenced MT-ND3 and MT-ND4L genes in 51 Tibetan yaks, 59 Tibetan cattle, and 60 Holstein-Fr…

Unpaired Multi-Domain Image Generation via Regularized Conditional GANs Open

Xudong Mao, Qing Li · 2018

In this paper, we study the problem of multi-domain image generation, the goal of which is to generate pairs of corresponding images from different domains. With the recent development in generative models, image generation has achieved gr…

Unpaired Multi-Domain Image Generation via Regularized Conditional GANs Open

Xudong Mao, Qing Li · 2018

In this paper, we study the problem of multi-domain image generation, the goal of which is to generate pairs of corresponding images from different domains. With the recent development in generative models, image generation has achieved gr…

On the Effectiveness of Least Squares Generative Adversarial Networks Open

Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang , et al. · 2017

Unsupervised learning with generative adversarial networks (GANs) has proven to be hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss…

AlignGAN: Learning to Align Cross-Domain Images with Conditional Generative Adversarial Networks Open

Xudong Mao, Qing Li, Haoran Xie · 2017

Recently, several methods based on generative adversarial network (GAN) have been proposed for the task of aligning cross-domain images or learning a joint distribution of cross-domain images. One of the methods is to use conditional GAN f…

Least Squares Generative Adversarial Networks Open

Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang , et al. · 2016

Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss funct…

Multi-class Generative Adversarial Networks with the L2 Loss Function. Open

Xudong Mao, Qing Li, Haoran Xie, Raymond Y.K. Lau, Zhen Wang · 2016

Generative adversarial networks (GANs) have achieved huge success in unsupervised learning. Most of GANs treat the discriminator as a classifier with the binary sigmoid cross entropy loss function. However, we find that the sigmoid cross e…

Xudong Mao YOU? Author Swipe