Explanipedia

Comparative Study on Photosynthetic Characteristics and Leaf Structure of Paphiopedilum parishii in Different Growth Periods Open

Li Lu, Haiying Jiang, Xin Cai, Xi Li, Guohua He , et al. · 2025

This study investigates the differences in photosynthetic characteristics of Paphiopedilum parishii (Rchb.f.) Stein during its reproductive and nutrient growth periods. Using plants from the same individual, we compared light response curv…

Proton-Pump Inhibitors Versus H2-Receptor Antagonists on the Risk of Major Osteoporotic Fractures: A Global Propensity-Score-Matched Cohort Study Open

Danling Jiang, Xi Li, W. Susan Cheng, Bing Li, Guoqing Lv , et al. · 2025

Background Long-term suppression of gastric acid is crucial for various conditions; however, proton-pump inhibitors (PPIs) may negatively impact skeletal health more than histamine-2 receptor antagonists (H2RAs). There is limited head-to-h…

Comparative Study on Leaf Functional Traits and Environmental Adaptability of Seedlings of the Endangered Plants Ormosia olivacea, Ormosia pachycarpa, and Ormosia sericeolucida Open

Junjie Yan, Guohua He, Xi Li, Shuo Feng, Yingying Wu , et al. · 2025

To investigate the photosynthetic characteristics and leaf anatomical structures of seedlings from the endangered plants Ormosia olivacea, Ormosia pachycarpa, and Ormosia sericeolucida, this study aimed to elucidate the influence of leaf s…

A Curated and Re-annotated Peripheral Blood Cell Dataset Integrating Four Public Resources Open

Lu Gan, Xi Li, Xichun Wang · 2025

We present TXL-PBC, a curated and re-annotated peripheral blood cell dataset constructed by integrating four publicly available resources: Blood Cell Count and Detection (BCCD), Blood Cell Detection Dataset (BCDD), Peripheral Blood Cells (…

InfVSR: Breaking Length Limits of Generic Video Super-Resolution Open

Ziqing Zhang, Kai Liu, Zheng Chen, Xi Li, Yucong Chen , et al. · 2025

Real-world videos often extend over thousands of frames. Existing video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of multi-step denoisi…

Architecture Considerations for ISAC in 6G Open

Sebastian Robitzsch, Laksh Bhatia, Konstantinos Filis, Neda Petreska, Mohamed Bahr , et al. · 2025

ISAC is emerging as a foundational capability in 6G, enabling mobile networks to not only offer communication services but also to sense and perceive their environment at scale. This paper explores architectural considerations to enable se…

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation Open

Qirui Li, Guangcong Zheng, Qi Zhao, Jie Li, Bin Dong , et al. · 2025

The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current approaches, such as factorized attention and fixed sparse p…

WGGLFA: Wavelet-Guided Global–Local Feature Aggregation Network for Facial Expression Recognition Open

Ke Dong, Xi Li, Cong Zhang, Zhenhua Xiao, Renjuan Nie · 2025

Facial expression plays an important role in human–computer interaction and affective computing. However, existing expression recognition methods cannot effectively capture multi-scale structural details contained in facial expressions, le…

Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection Open

Yehao Lu, Meng–Tzu Weng, Z. J. Xiao, Rui Jiang, Su Wei , et al. · 2025

The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage large-scale vision-language datasets but smaller models, r…

SphereDrag: Spherical Geometry-Aware Panoramic Image Editing Open

Zhengqian Feng, Xuewei Li, Junjie Yang, Yuxin Peng, Xi Li · 2025

Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity, t…

Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning Open

Mingxuan Cui, Qing Guo, Yuyi Wang, Di Lin, Qin Zou , et al. · 2025

3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked objects in a scene are replaced with new contents that blend …

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities Open

Tao Wu, Yong Zhang, Xintao Wang, Xianpan Zhou, Guangcong Zheng , et al. · 2025

Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of v…

RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements Open

Guangcong Zheng, Teng Li, Xianpan Zhou, Xi Li · 2025

Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they…

Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models Open

Rui Jiang, Xinghe Fu, Guangcong Zheng, Teng Li, Taiping Yao , et al. · 2025

The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially w…

Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models Open

Rui Jiang, Xinghe Fu, Guangcong Zheng, Teng Li, Taiping Yao , et al. · 2025

The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially w…

RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control Open

Teng Li, Guangcong Zheng, Rui Jiang, Shuigenzhan, Tao Wu , et al. · 2025

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant usability challenges…

Network Digital Twin for 5G-Enabled Mobile Robots Open

Luke Sanchez, Lanfranco Zanzi, Xi Li, Guillem Garí, Xavier Costa‐Pérez · 2025

The maturity and commercial roll-out of 5G networks and its deployment for private networks makes 5G a key enabler for various vertical industries and applications, including robotics. Providing ultra-low latency, high data rates, and ubiq…

An Innovative NOx Emissions Prediction Model Based on Random Forest Feature Selection and Evolutionary Reformer Open

Meng Xian-yu, Xi Li, Jialei Chen, Yongyan Fu, Chu Zhang , et al. · 2025

Developing more precise NOx emission prediction models is pivotal for effectively controlling NOx emissions from gas turbines. In this paper, a Reformer is combined with random forest (RF) feature selection and the chaos game optimization …

Analysis and comparison for image colorization with machine learning based on PyTorch and ChromaGAN Open

Jinyi Luo, Xi Li · 2025

Mdsd: Multi-Turn Diverse Synthetic Dialog Generation for Domain Specific Incomplete Requests Understanding Open

Xi Li, Xi Wu, Lijuan Xiao, Tao Liu, Ping Huang , et al. · 2025

English text topic classification using BERT-based model Open

Xi Li, Lili Jia · 2025

The rapid development of big data and artificial intelligence has made text topic classification an important part of natural language processing research, and it has also promoted the optimization of pre-trained model performance. In orde…

VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models Open

Tao Wu, Yong Zhang, Xiaodong Cun, Zhongang Qi, Jiang Pu , et al. · 2024

Zero-shot customized video generation has gained significant attention due to its substantial application potential. Existing methods rely on additional models to extract and inject reference subject features, assuming that the Video Diffu…

Linezolid combined Strontium substituted hydroxyapatite-Bi polymeric composite for Osteomyelitis affected bone regeneration analysis Open

Hua Li, Qi Du, Pei-Yu Guo, Yong-Tao Yi, Suresh Mickymaray , et al. · 2024

The primary objective of this investigation is to rectify bacterial infections in bone (osteomyelitis) and bone regeneration by utilizing an antibiotic-loaded hydroxyapatite polymer composite. In this regard, strontium (Sr)-substituted hyd…

Securing Federated Learning against Backdoor Threats with Foundation Model Integration Open

Xueyan Bi, Xi Li · 2024

Federated Learning (FL) enables decentralized model training while preserving privacy. Recently, the integration of Foundation Models (FMs) into FL has enhanced performance but introduced a novel backdoor attack mechanism. Attackers can ex…

CamI2V: Camera-Controlled Image-to-Video Diffusion Model Open

Guangcong Zheng, Teng Li, Rui Jiang, Yehao Lu, Tao Wu , et al. · 2024

Recent advancements have integrated camera pose as a user-friendly and physics-informed condition in video diffusion models, enabling precise camera control. In this paper, we identify one of the key challenges as effectively modeling nois…

Associate Everything Detected: Facilitating Tracking-by-Detection to the Unknown Open

Zhen Fang, Chao Liang, Xue Zhou, Shuyuan Zhu, Xi Li · 2024

Multi-object tracking (MOT) emerges as a pivotal and highly promising branch in the field of computer vision. Classical closed-vocabulary MOT (CV-MOT) methods aim to track objects of predefined categories. Recently, some open-vocabulary MO…

Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision Open

Weijie He, Mushui Liu, Yunlong Yu, Zhe‐Ming Lu, Xi Li · 2024

Single-frame infrared small target (SIRST) detection poses a significant challenge due to the requirement to discern minute targets amidst complex infrared background clutter. In this paper, we focus on a weakly-supervised paradigm to obta…

CLASH: Complementary Learning with Neural Architecture Search for Gait Recognition Open

Huanzhang Dou, Pengyi Zhang, Yuhan Zhao, Lu Jin, Xi Li · 2024

Gait recognition, which aims at identifying individuals by their walking patterns, has achieved great success based on silhouette. The binary silhouette sequence encodes the walking pattern within the sparse boundary representation. Theref…

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model Open

Longrong Yang, Dong Sheng, Chaoxiang Cai, Fan Yang, Size Li , et al. · 2024

The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs). It uses a sparse model to replace the dense model, achieving comparable performance while activating fewer parameters during inf…

Effects of simulated multi-sensory stimulation integration on physiological and psychological restoration in virtual urban green space environment Open

Chen Song, Saixin Cao, Hao Luo, Yinghui Huang, Siwei Jiang , et al. · 2024

Virtual urban green environment images and audio stimuli had been proven to have restorative effects on subjects’ physical and mental health. In this area, researchers predominantly focused on visual, auditory and olfactory aspects, while …

Xi Li YOU? Author Swipe