Spaces:
Running
Running
| <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Mingru Huang - Computer Vision Researcher</title> | |
| <script src="https://cdn.tailwindcss.com"></script> | |
| <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css"> | |
| <style> | |
| @import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&display=swap'); | |
| body { | |
| font-family: 'Inter', sans-serif; | |
| scroll-behavior: smooth; | |
| } | |
| .gradient-text { | |
| background: linear-gradient(90deg, #3b82f6, #8b5cf6); | |
| -webkit-background-clip: text; | |
| background-clip: text; | |
| color: transparent; | |
| } | |
| .hero-image { | |
| clip-path: circle(50% at 50% 50%); | |
| transition: all 0.3s ease; | |
| } | |
| .hero-image:hover { | |
| transform: scale(1.05); | |
| box-shadow: 0 10px 25px rgba(0, 0, 0, 0.1); | |
| } | |
| .publication-card { | |
| transition: all 0.3s ease; | |
| } | |
| .publication-card:hover { | |
| transform: translateY(-5px); | |
| box-shadow: 0 10px 25px rgba(0, 0, 0, 0.1); | |
| } | |
| .timeline-item:not(:last-child)::after { | |
| content: ''; | |
| position: absolute; | |
| left: 23px; | |
| top: 32px; | |
| height: calc(100% - 32px); | |
| width: 2px; | |
| background: #e5e7eb; | |
| } | |
| .news-item { | |
| position: relative; | |
| padding-left: 2rem; | |
| } | |
| .news-item::before { | |
| content: ''; | |
| position: absolute; | |
| left: 0.5rem; | |
| top: 0.5rem; | |
| width: 0.75rem; | |
| height: 0.75rem; | |
| border-radius: 50%; | |
| background: #3b82f6; | |
| } | |
| </style> | |
| </head> | |
| <body class="bg-gray-50 text-gray-800"> | |
| <!-- Navigation --> | |
| <nav class="bg-white shadow-sm sticky top-0 z-50"> | |
| <div class="max-w-6xl mx-auto px-4 sm:px-6 lg:px-8"> | |
| <div class="flex justify-between h-16"> | |
| <div class="flex items-center"> | |
| <a href="#" class="text-xl font-bold gradient-text">Mingru Huang</a> | |
| </div> | |
| <div class="hidden md:flex items-center space-x-8"> | |
| <a href="#about" class="text-gray-700 hover:text-blue-600 transition">About</a> | |
| <a href="#news" class="text-gray-700 hover:text-blue-600 transition">News</a> | |
| <a href="#publications" class="text-gray-700 hover:text-blue-600 transition">Publications</a> | |
| <a href="#contact" class="text-gray-700 hover:text-blue-600 transition">Contact</a> | |
| </div> | |
| <div class="md:hidden flex items-center"> | |
| <button id="menu-toggle" class="text-gray-700 focus:outline-none"> | |
| <svg class="h-6 w-6" fill="none" viewBox="0 0 24 24" stroke="currentColor"> | |
| <path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M4 6h16M4 12h16M4 18h16"></path> | |
| </svg> | |
| </button> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- Mobile menu --> | |
| <div id="mobile-menu" class="hidden md:hidden bg-white shadow-lg"> | |
| <div class="px-2 pt-2 pb-3 space-y-1 sm:px-3"> | |
| <a href="#about" class="block px-3 py-2 rounded-md text-base font-medium text-gray-700 hover:text-blue-600 hover:bg-gray-50">About</a> | |
| <a href="#news" class="block px-3 py-2 rounded-md text-base font-medium text-gray-700 hover:text-blue-600 hover:bg-gray-50">News</a> | |
| <a href="#publications" class="block px-3 py-2 rounded-md text-base font-medium text-gray-700 hover:text-blue-600 hover:bg-gray-50">Publications</a> | |
| <a href="#contact" class="block px-3 py-2 rounded-md text-base font-medium text-gray-700 hover:text-blue-600 hover:bg-gray-50">Contact</a> | |
| </div> | |
| </div> | |
| </nav> | |
| <!-- Hero Section --> | |
| <section id="about" class="py-12 md:py-20 bg-gradient-to-r from-blue-50 to-purple-50"> | |
| <div class="max-w-6xl mx-auto px-4 sm:px-6 lg:px-8"> | |
| <div class="flex flex-col md:flex-row items-center"> | |
| <div class="md:w-1/3 mb-8 md:mb-0 flex justify-center"> | |
| <img src="https://huangmr0719.github.io/images/portrait.png" alt="Mingru Huang" class="hero-image w-64 h-64 object-cover border-4 border-white shadow-lg"> | |
| </div> | |
| <div class="md:w-2/3 md:pl-12 text-center md:text-left"> | |
| <h1 class="text-4xl md:text-5xl font-bold mb-4"> | |
| <span class="gradient-text">Hello, I'm Mingru Huang</span> | |
| </h1> | |
| <p class="text-lg text-gray-700 mb-6 leading-relaxed"> | |
| I am a Master's degree student at Wuhan University of Technology. I'm passionate about computer vision research, particularly video understanding. My work spans video Q&A, video-text retrieval, and video captioning. I also explore large language models, prompt engineering, operator development, knowledge graphs, and Q&A systems. My goal is to develop an affordable, secure, and trustworthy generalized multimodal video model for everyone. | |
| </p> | |
| <div class="flex justify-center md:justify-start space-x-4"> | |
| <a href="https://huangmr0719.github.io/cv.html" class="px-6 py-2 bg-blue-600 text-white rounded-lg hover:bg-blue-700 transition flex items-center"> | |
| <i class="fas fa-file-alt mr-2"></i> CV | |
| </a> | |
| <a href="https://scholar.google.com/citations?user=NeFDR38AAAAJ" class="px-6 py-2 bg-gray-800 text-white rounded-lg hover:bg-gray-900 transition flex items-center"> | |
| <i class="fas fa-graduation-cap mr-2"></i> Scholar | |
| </a> | |
| <a href="https://github.com/Huangmr0719" class="px-6 py-2 bg-gray-700 text-white rounded-lg hover:bg-gray-800 transition flex items-center"> | |
| <i class="fab fa-github mr-2"></i> GitHub | |
| </a> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- News Section --> | |
| <section id="news" class="py-12 md:py-20 bg-white"> | |
| <div class="max-w-6xl mx-auto px-4 sm:px-6 lg:px-8"> | |
| <h2 class="text-3xl font-bold text-center mb-12"> | |
| <span class="gradient-text">Latest News</span> | |
| </h2> | |
| <div class="grid grid-cols-1 md:grid-cols-2 gap-8"> | |
| <div class="bg-gray-50 p-6 rounded-xl shadow-sm"> | |
| <h3 class="text-xl font-semibold mb-4 text-blue-600">2024</h3> | |
| <ul class="space-y-4"> | |
| <li class="news-item"> | |
| <span class="font-medium">Nov. 2024:</span> Invited as a reviewer for the ICME2025 conference. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Aug. 2024:</span> Incorporated a project on automotive maintenance inspection using a multimodal large model. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Jul. 2024:</span> Joined the SpConv operator optimization project based on MetaX MXMACA computing platform. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Jun. 2024:</span> Approved for the Chinese Software Copyright "Dermatology Clinical Feature Detection and Diagnosis System". | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">May 2024:</span> The paper "ST-CLIP" has been accepted at ICIC 2024 conference. | |
| </li> | |
| </ul> | |
| </div> | |
| <div class="bg-gray-50 p-6 rounded-xl shadow-sm"> | |
| <h3 class="text-xl font-semibold mb-4 text-blue-600">2023</h3> | |
| <ul class="space-y-4"> | |
| <li class="news-item"> | |
| <span class="font-medium">Jan. 2024:</span> Invited as a reviewer for the ICME2024 conference. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Dec. 2023:</span> Joined the school-enterprise cooperation program of Haluo Corporation, responsible for the AI speech generation part. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Nov. 2023:</span> Completed the Transformer Heterogeneous Bisheng C++ Arithmetic Development Project of Huawei Crowd Intelligence Program. | |
| </li> | |
| <li class="news-item"> | |
| <span class="font-medium">Sept. 2023:</span> Joined a video understanding project focused on dense video captioning. | |
| </li> | |
| </ul> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Publications Section --> | |
| <section id="publications" class="py-12 md:py-20 bg-gray-50"> | |
| <div class="max-w-6xl mx-auto px-4 sm:px-6 lg:px-8"> | |
| <h2 class="text-3xl font-bold text-center mb-12"> | |
| <span class="gradient-text">Publications</span> | |
| </h2> | |
| <div class="space-y-8"> | |
| <!-- Publication 1 --> | |
| <div class="publication-card bg-white p-6 rounded-xl shadow-sm hover:shadow-md transition"> | |
| <div class="flex flex-col md:flex-row"> | |
| <div class="md:w-1/3 mb-4 md:mb-0"> | |
| <img src="https://huangmr0719.github.io/images/skmr.png" alt="Publication Image" class="w-full h-auto rounded-lg"> | |
| </div> | |
| <div class="md:w-2/3 md:pl-6"> | |
| <h3 class="text-xl font-bold mb-2 text-blue-600"> | |
| <a href="https://github.com/Huangmr0719/MVSA" class="hover:underline">Scene Knowledge Enhanced Multimodal Retrieval Model for Dense Video Captioning</a> | |
| </h3> | |
| <p class="text-gray-700 mb-2"> | |
| Mingru Huang, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876872.shtml" class="text-blue-600 hover:underline">Pengfei Duan</a>, Yifang Zhang, Huimin Chen, Jiawang Peng, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876901.shtml" class="text-blue-600 hover:underline">Shengwu Xiong</a> | |
| </p> | |
| <p class="text-gray-600 mb-4"> | |
| 2025 Twenty-first International Conference on Intelligent Computing (ICIC 2025) | |
| </p> | |
| <p class="text-gray-700 mb-4"> | |
| Introducing a Memory Enhanced Visual-Speech Aggregation model for dense video captioning, inspired by cognitive informatics on human memory recall. The model enhances visual representations by merging them with relevant text features retrieved from a memory bank through multimodal retrieval involving transcribed speech and visual inputs. | |
| </p> | |
| <div class="flex flex-wrap gap-2"> | |
| <a href="https://github.com/Huangmr0719/MVSA" class="px-4 py-1 bg-blue-100 text-blue-700 rounded-full text-sm hover:bg-blue-200 transition flex items-center"> | |
| <i class="fas fa-link mr-1"></i> Project Page | |
| </a> | |
| <a href="https://arxiv.org/pdf/.pdf" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-file-pdf mr-1"></i> PDF | |
| </a> | |
| <a href="https://arxiv.org/abs/" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-book-open mr-1"></i> arXiv | |
| </a> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- Publication 2 --> | |
| <div class="publication-card bg-white p-6 rounded-xl shadow-sm hover:shadow-md transition"> | |
| <div class="flex flex-col md:flex-row"> | |
| <div class="md:w-1/3 mb-4 md:mb-0"> | |
| <img src="https://huangmr0719.github.io/images/ldit.png" alt="Publication Image" class="w-full h-auto rounded-lg"> | |
| </div> | |
| <div class="md:w-2/3 md:pl-6"> | |
| <h3 class="text-xl font-bold mb-2 text-blue-600"> | |
| LDIT: Pseudo-Label Noise Adaptation via Label Diffusion Transformer | |
| </h3> | |
| <p class="text-gray-700 mb-2"> | |
| Jiawang Peng, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876872.shtml" class="text-blue-600 hover:underline">Pengfei Duan</a>, Mingru Huang, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876901.shtml" class="text-blue-600 hover:underline">Shengwu Xiong</a> | |
| </p> | |
| <p class="text-gray-600 mb-4"> | |
| 2025 Twenty-first International Conference on Intelligent Computing (ICIC 2025) | |
| </p> | |
| <p class="text-gray-700 mb-4"> | |
| We reformulate label prediction as a progressive refinement process starting from an initial random guess, and propose LDiT (Label Diffusion Transformer) for pseudo-label noise adaptation. By modeling label uncertainty through a diffusion process, LDiT enables more robust learning under noisy supervision. In addition, to effectively capture the long-range dependencies in textual data, we adopt a Transformer-based latent denoising architecture with self-attention mechanisms. | |
| </p> | |
| <div class="flex flex-wrap gap-2"> | |
| <a href="https://arxiv.org/pdf/.pdf" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-file-pdf mr-1"></i> PDF | |
| </a> | |
| <a href="https://arxiv.org/abs/" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-book-open mr-1"></i> arXiv | |
| </a> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- Publication 3 --> | |
| <div class="publication-card bg-white p-6 rounded-xl shadow-sm hover:shadow-md transition"> | |
| <div class="flex flex-col md:flex-row"> | |
| <div class="md:w-1/3 mb-4 md:mb-0"> | |
| <img src="https://huangmr0719.github.io/images/stclip.png" alt="Publication Image" class="w-full h-auto rounded-lg"> | |
| </div> | |
| <div class="md:w-2/3 md:pl-6"> | |
| <h3 class="text-xl font-bold mb-2 text-blue-600"> | |
| <a href="https://link.springer.com/content/pdf/10.1007/978-981-97-5612-4.pdf" class="hover:underline">ST-CLIP: Spatio-Temporal enhanced CLIP towards Dense Video Captioning</a> | |
| </h3> | |
| <p class="text-gray-700 mb-2"> | |
| Huimin Chen, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876872.shtml" class="text-blue-600 hover:underline">Pengfei Duan</a>, Mingru Huang, Jingyi Guo, <a href="http://cst.whut.edu.cn/xygk/szdw/201505/t20150527_876901.shtml" class="text-blue-600 hover:underline">Shengwu Xiong</a> | |
| </p> | |
| <p class="text-gray-600 mb-4"> | |
| 2024 Twentieth International Conference on Intelligent Computing (ICIC 2024) | |
| </p> | |
| <p class="text-gray-700 mb-4"> | |
| Proposing a new factorized spatio-temporal self-attention paradigm to address inaccurate event descriptions caused by insufficient temporal relationship modeling between video frames and apply it to dense video captioning tasks. | |
| </p> | |
| <div class="flex flex-wrap gap-2"> | |
| <a href="https://link.springer.com/content/pdf/10.1007/978-981-97-5612-4.pdf" class="px-4 py-1 bg-blue-100 text-blue-700 rounded-full text-sm hover:bg-blue-200 transition flex items-center"> | |
| <i class="fas fa-link mr-1"></i> Project Page | |
| </a> | |
| <a href="https://arxiv.org/pdf/.pdf" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-file-pdf mr-1"></i> PDF | |
| </a> | |
| <a href="https://arxiv.org/abs/" class="px-4 py-1 bg-gray-100 text-gray-700 rounded-full text-sm hover:bg-gray-200 transition flex items-center"> | |
| <i class="fas fa-book-open mr-1"></i> arXiv | |
| </a> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Contact Section --> | |
| <section id="contact" class="py-12 md:py-20 bg-white"> | |
| <div class="max-w-6xl mx-auto px-4 sm:px-6 lg:px-8"> | |
| <h2 class="text-3xl font-bold text-center mb-12"> | |
| <span class="gradient-text">Get In Touch</span> | |
| </h2> | |
| <div class="flex flex-col items-center"> | |
| <p class="text-lg text-gray-700 mb-8 max-w-2xl text-center"> | |
| I'm always open to discussing research collaborations, new projects, or opportunities. Feel free to reach out! | |
| </p> | |
| <div class="flex space-x-6 mb-8"> | |
| <a href="mailto:[email protected]" class="w-12 h-12 rounded-full bg-blue-100 flex items-center justify-center text-blue-600 hover:bg-blue-200 transition"> | |
| <i class="fas fa-envelope text-xl"></i> | |
| </a> | |
| <a href="https://github.com/Huangmr0719" class="w-12 h-12 rounded-full bg-gray-100 flex items-center justify-center text-gray-700 hover:bg-gray-200 transition"> | |
| <i class="fab fa-github text-xl"></i> | |
| </a> | |
| <a href="https://scholar.google.com/citations?user=NeFDR38AAAAJ" class="w-12 h-12 rounded-full bg-gray-100 flex items-center justify-center text-gray-700 hover:bg-gray-200 transition"> | |
| <i class="fas fa-graduation-cap text-xl"></i> | |
| </a> | |
| <a href="https://twitter.com/ZyKINvice" class="w-12 h-12 rounded-full bg-blue-100 flex items-center justify-center text-blue-400 hover:bg-blue-200 transition"> | |
| <i class="fab fa-twitter text-xl"></i> | |
| </a> | |
| </div> | |
| <div class="text-center text-gray-500 text-sm"> | |
| <p>© 2024 Mingru Huang. All rights reserved.</p> | |
| <p class="mt-2">Template inspired by <a href="https://github.com/keunhong/keunhong.github.io" class="text-blue-600 hover:underline">Keunhong Park</a></p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <script> | |
| // Mobile menu toggle | |
| document.getElementById('menu-toggle').addEventListener('click', function() { | |
| const menu = document.getElementById('mobile-menu'); | |
| menu.classList.toggle('hidden'); | |
| }); | |
| // Smooth scrolling for anchor links | |
| document.querySelectorAll('a[href^="#"]').forEach(anchor => { | |
| anchor.addEventListener('click', function (e) { | |
| e.preventDefault(); | |
| const targetId = this.getAttribute('href'); | |
| const targetElement = document.querySelector(targetId); | |
| if (targetElement) { | |
| window.scrollTo({ | |
| top: targetElement.offsetTop - 80, | |
| behavior: 'smooth' | |
| }); | |
| // Close mobile menu if open | |
| const menu = document.getElementById('mobile-menu'); | |
| if (!menu.classList.contains('hidden')) { | |
| menu.classList.add('hidden'); | |
| } | |
| } | |
| }); | |
| }); | |
| // Add shadow to navbar on scroll | |
| window.addEventListener('scroll', function() { | |
| const nav = document.querySelector('nav'); | |
| if (window.scrollY > 10) { | |
| nav.classList.add('shadow-md'); | |
| } else { | |
| nav.classList.remove('shadow-md'); | |
| } | |
| }); | |
| </script> | |
| <p style="border-radius: 8px; text-align: center; font-size: 12px; color: #fff; margin-top: 16px;position: fixed; left: 8px; bottom: 8px; z-index: 10; background: rgba(0, 0, 0, 0.8); padding: 4px 8px;">Made with <img src="https://enzostvs-deepsite.hf.space/logo.svg" alt="DeepSite Logo" style="width: 16px; height: 16px; vertical-align: middle;display:inline-block;margin-right:3px;filter:brightness(0) invert(1);"><a href="https://enzostvs-deepsite.hf.space" style="color: #fff;text-decoration: underline;" target="_blank" >DeepSite</a> - 🧬 <a href="https://enzostvs-deepsite.hf.space?remix=ZyKINvice/githubpage" style="color: #fff;text-decoration: underline;" target="_blank" >Remix</a></p></body> | |
| </html> |