https://vilab.team/event/ 近期新闻 Hugo Blox Builder (https://hugoblox.com)en-usMon, 29 Jun 2026 00:00:00 +0000 https://vilab.team/media/icon_hu2896232876136423579.png https://vilab.team/event/ https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-qomex/ Mon, 29 Jun 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-qomex/ <p>热烈祝贺柯诗恩同学！论文《Token-Wise Attention-Guided Semantic Quality Assessment for Compressed Visual Features》已发表在 <em>QoMEX 2026</em>。</p> <h2 id="token-wise-attention-guided-semantic-quality-assessment-for-compressed-visual-features">Token-Wise Attention-Guided Semantic Quality Assessment for Compressed Visual Features</h2> <p><strong>祝贺柯诗恩同学！该论文已发表在 <em>QoMEX</em>。</strong></p> <ul> <li><strong>作者：</strong> Shien Ke、Changsheng Gao、Hadi Amirpour、Zhihua Wang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>QoMEX</em></li> <li><strong>发表时间：</strong> 2026年6月29日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11618326/" target="_blank" rel="noopener">论文链接</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对协作与分布式智能系统中压缩中间特征的语义质量评估问题，提出了一种基于Token级注意力引导的评估方法。该方法利用原始与重建Token之间的内在对应关系，在Token层面进行质量度量，以减少跨Token干扰；同时通过注意力机制区分不同Token对下游任务的重要性，从而更准确地反映压缩特征的语义效用。实验表明，该方法在多种特征编解码器上均优于传统相似性度量，具有良好的鲁棒性。</p> https://vilab.team/event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/ Thu, 18 Jun 2026 00:00:00 +0000 https://vilab.team/event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/ <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="fa01fd69fd4d964916b7b2952469e63b.jpg" srcset=" /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/91369e7011994ba4_hu10789112043179484338.webp 400w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/91369e7011994ba4_hu9603722309995507050.webp 760w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/91369e7011994ba4_hu7271104396862312426.webp 1200w" src="https://vilab.team/event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/91369e7011994ba4_hu10789112043179484338.webp" width="760" height="760" loading="lazy" data-zoomable /></div> </div></figure> </p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="f5ad67215324fd3b7a4a235de8207ea8.jpg" srcset=" /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/ece6d061a80b44ef_hu5971903943392455284.webp 400w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/ece6d061a80b44ef_hu7784706271977293400.webp 760w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/ece6d061a80b44ef_hu6729592870948179764.webp 1200w" src="https://vilab.team/event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/ece6d061a80b44ef_hu5971903943392455284.webp" width="760" height="507" loading="lazy" data-zoomable /></div> </div></figure> </p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="_20260901165407_10_347.jpg" srcset=" /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/0872be97f6724525_hu10089464972585274075.webp 400w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/0872be97f6724525_hu13561170950426516185.webp 760w, /event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/0872be97f6724525_hu5130844672678407425.webp 1200w" src="https://vilab.team/event/%E5%AE%9E%E9%AA%8C%E5%AE%A4%E6%AC%A2%E9%80%812025%E5%B1%8A%E6%AF%95%E4%B8%9A%E7%94%9F%E7%A5%9D%E5%90%8C%E5%AD%A6%E4%BB%AC%E5%89%8D%E7%A8%8B%E4%BC%BC%E9%94%A6/images/0872be97f6724525_hu10089464972585274075.webp" width="760" height="570" loading="lazy" data-zoomable /></div> </div></figure> </p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ Sun, 03 May 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ <p>热烈祝贺陈政同学、吴小满同学！近期，实验室共有 2 项科研成果正式发表。</p> <h2 id="salient-diagnostic-value-perception-for-preoperative-posterior-fossa-tumor-diagnosis">Salient Diagnostic Value Perception For Preoperative Posterior Fossa Tumor Diagnosis</h2> <p><strong>祝贺陈政同学！该论文已发表在 <em>ICASSP 2026</em>。</strong></p> <ul> <li><strong>作者：</strong> Zheng Chen、Peng Li、Zheyu Zhang、Siying Wu、Jing Zhang、Cuiling Hu、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICASSP</em></li> <li><strong>发表时间：</strong> 2026年5月3日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11460465/" target="_blank" rel="noopener">论文链接</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出显著诊断价值感知方法（SDVP），用于后颅窝肿瘤的术前准确诊断。该方法整合MRI影像与放射学报告，从三个互补视角学习关键诊断线索：通过对抗性样本内对比学习增强跨中心与设备差异的鲁棒性；借助知识增强的样本内对比学习提取专家引导的样本特异性特征；并在干净MRI样本上进行监督式类间对比学习以强化类别特征。</p> <hr> <h2 id="sscm-a-spatial-semantic-consistent-model-for-multi-contrast-mri-super-resolution">SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution</h2> <p><strong>祝贺吴小满同学！该论文已发表在 <em>ICASSP 2026</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="SSCM: A Spatial-Semantic Consistent Model for Multi-Contrast MRI Super-Resolution" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu16643979777475813095.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu13958872581769715241.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu13117256722096246496.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/images/paper-02_hu16643979777475813095.webp" width="760" height="438" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Xiaoman Wu、Lubin Gan、Siying Wu、Jing Zhang、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICASSP</em></li> <li><strong>发表时间：</strong> 2026年5月3日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11464902/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2509.18593" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍-1">论文介绍</h3> <p>本文提出空间语义一致模型（SSCM），用于多对比度磁共振成像超分辨率。该方法通过动态空间扭曲模块实现对比度间空间对齐，利用语义感知令牌聚合块建模长程依赖，并结合空间-频率融合块恢复高频细节，从而在结构差异和运动干扰下保持解剖结构的空间语义一致性。实验表明SSCM在效率和性能上优于现有方法。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/ Mon, 20 Apr 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/ <p>热烈祝贺彭岩松同学！论文《Facm: Flow-anchored consistency models》已发表在 <em>ICLR</em> 2026。</p> <h2 id="facm-flow-anchored-consistency-models">Facm: Flow-anchored consistency models</h2> <p><strong>祝贺彭岩松同学！该论文已发表在 <em>ICLR</em> 2026。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Facm: Flow-anchored consistency models" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/images/paper-01_hu12002391219066891609.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/images/paper-01_hu15036098972298221130.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/images/paper-01_hu3776373299308260365.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr-2026/images/paper-01_hu12002391219066891609.webp" width="760" height="207" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Yansong Peng、Kai Zhu、Yu Liu、Pingyu Wu、Hebei Li、Xiaoyan Sun、Feng Wu</li> <li><strong>发表载体：</strong> <em>ICLR</em> 2026</li> <li><strong>发表时间：</strong> 2026年4月20日</li> <li><strong>相关链接：</strong> <a href="https://proceedings.iclr.cc/paper_files/paper/2026/hash/0d0dac08f4199f0c348dd2feace0305a-Abstract-Conference.html" target="_blank" rel="noopener">论文链接</a> · <a href="https://proceedings.iclr.cc/paper_files/paper/2026/file/0d0dac08f4199f0c348dd2feace0305a-Paper-Conference.pdf" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/ali-vilab/FACM" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对连续时间一致性模型（CM）训练不稳定的问题，指出其根源在于捷径目标导致瞬时速度场被灾难性遗忘。为此提出流锚定一致性模型（FACM），以流匹配任务作为动态锚点，并设计扩展时间间隔策略统一优化、解耦两个任务，实现稳定且架构无关的训练。在ImageNet 256×256上，蒸馏LightningDiT模型取得NFE=2时FID 1.32、NFE=1时FID 1.70的SOTA结果；同时提出内存高效的Chain-JVP，将FACM扩展到140亿参数的Wan 2.2模型，加速文本到图像推理至2-8步。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/ Mon, 20 Apr 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/ <p>热烈祝贺李蔚同学！论文《ReactID: Synchronizing Realistic Actions and Identity in Personalized Video Generation》已发表在 <em>ICLR 2026</em>。</p> <h2 id="reactid-synchronizing-realistic-actions-and-identity-in-personalized-video-generation">ReactID: Synchronizing Realistic Actions and Identity in Personalized Video Generation</h2> <p><strong>祝贺李蔚同学！该论文已发表在 <em>ICLR</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="ReactID: Synchronizing Realistic Actions and Identity in Personalized Video Generation" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/images/paper-01_hu10185920340004675066.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/images/paper-01_hu15268550746155155384.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/images/paper-01_hu4770338007721801293.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iclr/images/paper-01_hu10185920340004675066.webp" width="760" height="288" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Wei Li、Yiheng Zhang、Fuchen Long、Zhaofan Qiu、Ting Yao、Xiaoyan Sun、Tao Mei</li> <li><strong>发表载体：</strong> <em>ICLR</em></li> <li><strong>发表时间：</strong> 2026年4月20日</li> <li><strong>相关链接：</strong> <a href="https://proceedings.iclr.cc/paper_files/paper/2026/hash/6600458132d025c68a01e82081597b32-Abstract-Conference.html" target="_blank" rel="noopener">论文链接</a> · <a href="https://proceedings.iclr.cc/paper_files/paper/2026/file/6600458132d025c68a01e82081597b32-Paper-Conference.pdf" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出ReactID框架，旨在协调个性化视频生成中身份一致性与动作真实性的矛盾。针对主体-视频对齐不精确、训练不稳定、细粒度动作建模不足三大挑战，从数据、训练和动作建模三方面协同改进：构建高精度标注的ReactID-Data数据集；设计由易到难的渐进式训练课程；提出基于时间线的条件机制，通过主体感知交叉注意力和时间自适应RoPE，将子动作与特定主体绑定并嵌入时间坐标，从而生成更自然、可控的视频。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/ Sat, 14 Mar 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/ <p>热烈祝贺开大纯同学！论文《Seeing the unseen: Zooming in the dark with event cameras》已发表在 <em>AAAI 2026</em>。</p> <h2 id="seeing-the-unseen-zooming-in-the-dark-with-event-cameras">Seeing the unseen: Zooming in the dark with event cameras</h2> <p><strong>祝贺开大纯同学！该论文已发表在 <em>AAAI</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Seeing the unseen: Zooming in the dark with event cameras" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu13636376305985334282.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu16933069341322044714.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu642809347018091764.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-aaai/images/paper-01_hu13636376305985334282.webp" width="760" height="391" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Dachun Kai、Zeyu Xiao、Huyue Zhu、Jiaxiao Wang、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>AAAI</em></li> <li><strong>发表时间：</strong> 2026年3月14日</li> <li><strong>相关链接：</strong> <a href="https://ojs.aaai.org/index.php/AAAI/article/view/37478" target="_blank" rel="noopener">论文链接</a> · <a href="https://ojs.aaai.org/index.php/AAAI/article/download/37478/41440" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/DachunKai/RetinexEVSR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出RetinexEVSR，首个事件驱动的低光视频超分辨率框架。该框架利用高对比度事件信号与Retinex先验，通过双向跨模态融合策略，有效整合噪声事件数据与退化RGB帧中的有用信息。其中，照明引导事件增强模块利用Retinex模型导出的光照图逐步细化事件特征，抑制低光伪影并保留高对比度细节；事件引导反射率增强模块则通过多尺度融合机制动态恢复反射率细节。实验表明，该方法在三个数据集上达到最优性能，在SDSD基准上相比先前事件方法提升2.95 dB，并减少65%运行时间。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/ Tue, 10 Mar 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/ <p>热烈祝贺胡张驰同学！论文《RiO-DETR: DETR for Real-time Oriented Object Detection》已发表在 ECCV 2026 Oral。</p> <h2 id="rio-detr-detr-for-real-time-oriented-object-detection">RiO-DETR: DETR for Real-time Oriented Object Detection</h2> <p><strong>祝贺胡张驰同学！该论文已发表在 ECCV 2026。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="RiO-DETR: DETR for Real-time Oriented Object Detection" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/images/paper-01_hu3774487554520496472.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/images/paper-01_hu7272795672146682259.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/images/paper-01_hu2318532274489056445.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026-2/images/paper-01_hu3774487554520496472.webp" width="760" height="393" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Zhangchi Hu、Yifan Zhao、Yansong Peng、Wenzhang Sun、Xiangchen Yin、Jie Chen、Peixi Wu、Hebei Li、Xinghao Wang、Dongsheng Jiang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> ECCV 2026</li> <li><strong>发表时间：</strong> 2026年3月10日</li> <li><strong>相关链接：</strong> <a href="https://arxiv.org/abs/2603.09411" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2603.09411" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/RicePasteM/RiO-DETR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出RiO-DETR，一种面向实时旋转目标检测的DETR框架。针对方向语义依赖、角度周期性和搜索空间扩大等挑战，设计了内容驱动的角度估计、旋转校正正交注意力、解耦周期细化以及定向密集O2O机制，在保持实时效率的同时提升角度收敛速度与检测精度。在DOTA-1.0、DIOR-R和FAIR-1M-2.0上的实验表明，该方法实现了新的速度-精度平衡。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/ Tue, 10 Mar 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/ <p>热烈祝贺胡张驰同学！论文《RiO-DETR: DETR for Real-time Oriented Object Detection》已发表在 ECCV 2026。</p> <h2 id="rio-detr-detr-for-real-time-oriented-object-detection">RiO-DETR: DETR for Real-time Oriented Object Detection</h2> <p><strong>祝贺胡张驰同学！该论文已发表在 ECCV 2026。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="RiO-DETR: DETR for Real-time Oriented Object Detection" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/images/paper-01_hu3774487554520496472.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/images/paper-01_hu7272795672146682259.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/images/paper-01_hu2318532274489056445.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-eccv-2026/images/paper-01_hu3774487554520496472.webp" width="760" height="393" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Zhangchi Hu、Yifan Zhao、Yansong Peng、Wenzhang Sun、Xiangchen Yin、Jie Chen、Peixi Wu、Hebei Li、Xinghao Wang、Dongsheng Jiang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> ECCV 2026</li> <li><strong>发表时间：</strong> 2026年3月10日</li> <li><strong>相关链接：</strong> <a href="https://arxiv.org/abs/2603.09411" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2603.09411" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/RicePasteM/RiO-DETR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出RiO-DETR，一种面向实时旋转目标检测的DETR框架。针对方向语义依赖、角度周期性和搜索空间扩大等挑战，设计了内容驱动的角度估计、旋转校正正交注意力、解耦周期细化以及定向密集O2O机制，在保持实时效率的同时提升角度收敛速度与检测精度。在DOTA-1.0、DIOR-R和FAIR-1M-2.0上的实验表明，该方法实现了新的速度-精度平衡。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/ Mon, 02 Feb 2026 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/ <p>热烈祝贺开大纯同学！论文《EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution》已发表在 <em>IEEE TPAMI</em>。</p> <h2 id="evtexture-event-driven-texture-enhancement-for-video-super-resolution">EvTexture++: Event-Driven Texture Enhancement for Video Super-Resolution</h2> <p><strong>祝贺开大纯同学！该论文已发表在 <em>IEEE TPAMI</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="EvTexture&#43;&#43;: Event-Driven Texture Enhancement for Video Super-Resolution" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/images/paper-01_hu133827975853785128.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/images/paper-01_hu10222371703703860375.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/images/paper-01_hu15191880168499112270.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-ieee-tpami/images/paper-01_hu133827975853785128.webp" width="760" height="348" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Dachun Kai、Jiayao Lu、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>IEEE TPAMI</em></li> <li><strong>发表时间：</strong> 2026年2月2日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11369964/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2606.13580" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/DachunKai/EvTexture" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出EvTexture++，一种事件驱动的视频超分辨率纹理增强框架。与以往将事件用于运动估计不同，该方法利用事件的高频时空细节显式恢复纹理，通过定制纹理增强分支和迭代纹理增强模块，逐步挖掘高时间分辨率事件信息，实现纹理区域的渐进细化，从而生成更精确、细节更丰富的高分辨率视频。该框架还可作为即插即用模块提升现有VSR模型性能。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-3-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ Mon, 27 Oct 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-3-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8/ <p>热烈祝贺第一作者 Changsheng Gao、胡张驰同学、王义钧同学！近期，实验室共有 3 项科研成果正式发表在ACM MM 2025。</p> <h2 id="dt-ufc-universal-large-model-feature-coding-via-peaky-to-balanced-distribution-transformation">DT-UFC: Universal large model feature coding via peaky-to-balanced distribution transformation</h2> <p><strong>祝贺第一作者 Changsheng Gao！该论文已发表在 <em>ACM MM</em> 2025。</strong></p> <ul> <li><strong>作者：</strong> Changsheng Gao、Zijie Liu、Li Li、Dong Liu、Xiaoyan Sun、Weisi Lin</li> <li><strong>发表载体：</strong> <em>ACM MM</em> 2025</li> <li><strong>发表时间：</strong> 2025年10月27日</li> <li><strong>相关链接：</strong> <a href="https://dl.acm.org/doi/abs/10.1145/3746027.3755814" target="_blank" rel="noopener">论文链接</a> · <a href="https://dl.acm.org/doi/pdf/10.1145/3746027.3755814" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文首次系统研究大模型通用特征编码问题，旨在降低分布式部署中的传输与存储开销。针对不同模型提取特征分布差异显著（如DINOv2特征高度集中、SD3特征分散均匀）导致压缩效率低、跨模型泛化难的问题，提出一种从峰值分布到平衡分布的变换方法，实现通用且高效的特征压缩与传输。</p> <hr> <h2 id="dome-detr-detr-with-density-oriented-feature-query-manipulation-for-efficient-tiny-object-detection">Dome-DETR: DETR with density-oriented feature-query manipulation for efficient tiny object detection</h2> <p><strong>祝贺胡张驰同学！该论文已发表在 <em>ACM MM</em>。</strong></p> <ul> <li><strong>作者：</strong> Zhangchi Hu、Peixi Wu、Jie Chen、Huyue Zhu、Yijun Wang、Yansong Peng、Hebei Li、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ACM MM</em></li> <li><strong>发表时间：</strong> 2025年10月27日</li> <li><strong>相关链接：</strong> <a href="https://dl.acm.org/doi/abs/10.1145/3746027.3754861" target="_blank" rel="noopener">论文链接</a> · <a href="https://dl.acm.org/doi/pdf/10.1145/3746027.3754861" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/RicePasteM/Dome-DETR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍-1">论文介绍</h3> <p>本文提出 Dome-DETR，一种面向微小物体检测的高效框架。针对现有方法特征利用不充分和计算成本高的问题，引入轻量级密度聚焦提取器（DeFE）生成紧凑前景掩码，并基于掩码的窗口注意力稀疏化（MWAS）将计算资源集中于关键区域。同时提出渐进自适应查询初始化（PAQI），自适应调节查询分布，提升检测效率与精度。</p> <hr> <h2 id="medkcoop-dual-knowledge-guided-graph-prompt-learning-for-biomedical-vision-language-models">MeDKCoOp: Dual Knowledge-guided Graph Prompt Learning for Biomedical Vision-Language Models</h2> <p><strong>祝贺王义钧同学！该论文已发表在 <em>ACM MM</em>。</strong></p> <ul> <li><strong>作者：</strong> Yijun Wang、Siying Wu、Lubin Gan、Zheyu Zhang、Jing Zhang、Zhangchi Hu、Huyue Zhu、Peixi Wu、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ACM MM</em></li> <li><strong>发表时间：</strong> 2025年10月27日</li> <li><strong>相关链接：</strong> <a href="https://dl.acm.org/doi/abs/10.1145/3746027.3755135" target="_blank" rel="noopener">论文链接</a> · <a href="https://dl.acm.org/doi/pdf/10.1145/3746027.3755135" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍-2">论文介绍</h3> <p>本文提出MeDKCoOp，一种面向生物医学视觉语言模型的双知识引导图提示学习方法。该方法系统整合医学领域知识，从文本与视觉分支提取专门知识并构建图结构表示，通过知识引导的关系转移实现跨模态融合，并动态优化可学习提示，以增强CLIP等模型在医学下游任务中的适应能力。实验表明其在多个生物医学基准上取得优异性能。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/ Mon, 27 Oct 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/ <p>热烈祝贺甘鲁斌同学！论文《Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment》已发表在 <em>Expert Systems with Applications</em> 130161。</p> <h2 id="enhancing-zero-shot-brain-tumor-subtype-classification-via-fine-grained-patch-text-alignment">Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment</h2> <p><strong>祝贺甘鲁斌同学！该论文已发表在 <em>Expert Systems with Applications</em> 130161。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/images/paper-01_hu479104807647607719.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/images/paper-01_hu7525044382441938419.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/images/paper-01_hu10830315984298057718.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-expert-systems-with-applications-130161/images/paper-01_hu479104807647607719.webp" width="760" height="445" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Lubin Gan、Jing Zhang、Linhao Qu、Yijun Wang、Siying Wu、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>Expert Systems with Applications</em> 130161</li> <li><strong>发表时间：</strong> 2025年10月27日</li> <li><strong>相关链接：</strong> <a href="https://www.sciencedirect.com/science/article/pii/S0957417425037765" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2508.01602" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出细粒度补丁对齐网络（FG-PAN），用于脑肿瘤亚型的零样本分类。该方法包含局部特征细化模块，通过建模代表性补丁间的空间关系增强视觉特征；以及细粒度文本描述生成模块，利用大语言模型生成病理感知的类别语义原型。通过对齐细粒度视觉与语义特征，并引入坐标感知聚合机制，FG-PAN在整张病理切片级别实现了更准确的亚型判别，缓解了标注数据稀缺和形态差异细微带来的挑战。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/ Sun, 19 Oct 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/ <p>热烈祝贺陈杰同学、吴沛熹同学！近期，实验室共有 2 项科研成果正式发表在ICCV 2025。</p> <h2 id="dash-4d-hash-encoding-with-self-supervised-decomposition-for-real-time-dynamic-scene-rendering">Dash: 4d hash encoding with self-supervised decomposition for real-time dynamic scene rendering</h2> <p><strong>祝贺陈杰同学！该论文已发表在 <em>ICCV</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Dash: 4d hash encoding with self-supervised decomposition for real-time dynamic scene rendering" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-01_hu14668970062868369588.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-01_hu9539442214703728986.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-01_hu17969550026126564787.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-01_hu14668970062868369588.webp" width="760" height="339" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Jie Chen、Zhangchi Hu、Peixi Wu、Huyue Zhu、Hebei Li、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICCV</em></li> <li><strong>发表时间：</strong> 2025年10月19日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11444039/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2507.19141" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/chenj02/DASH" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出DASH，一种实时动态场景渲染框架，采用4D哈希编码结合自监督分解。针对现有平面基动态高斯溅射方法因低秩假设导致特征重叠和渲染质量差的问题，DASH通过自监督分解机制分离动态与静态组件，无需人工标注或预计算掩码，并引入多分辨率4D哈希编码器对动态元素进行显式表示，避免低秩约束，从而减少哈希冲突和冗余，实现高质量实时渲染。</p> <hr> <h2 id="efficient-spiking-point-mamba-for-point-cloud-analysis">Efficient spiking point mamba for point cloud analysis</h2> <p><strong>祝贺吴沛熹同学！该论文已发表在 <em>ICCV</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Efficient spiking point mamba for point cloud analysis" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-02_hu18026702173288992064.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-02_hu8515574002487600796.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-02_hu2828688134925209604.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4-2-%E9%A1%B9%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8-2/images/paper-02_hu18026702173288992064.webp" width="760" height="419" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Peixi Wu、Bosong Chai、Menghua Zheng、Wei Li、Zhangchi Hu、Jie Chen、Zheyu Zhang、Hebei Li、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICCV</em></li> <li><strong>发表时间：</strong> 2025年10月19日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11445417/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2504.14371" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/PeppaWu/SPM" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍-1">论文介绍</h3> <p>本文提出 Spiking Point Mamba (SPM)，这是首个将 Mamba 引入三维点云分析的脉冲神经网络。针对直接适配 Mamba 时存在的时序动态不匹配和脉冲引起的信息损失问题，作者设计了层次动态编码 (HDE) 以增强动态时序建模，并提出 Spiking Mamba Block (SMB) 来学习跨时间步特征并减少脉冲信息丢失。此外，采用非对称 SNN 训练策略进一步提升性能。SPM 可作为高效骨干网络，适用于点云分类、部件分割与重建等任务。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/ Sun, 19 Oct 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/ <p>热烈祝贺李欣羽同学！论文《Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment》已发表在 <em>ICCV Workshops</em>。</p> <h2 id="hybrid-vision-transformer-and-convolutional-neural-network-for-super-resolution-image-quality-assessment">Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment</h2> <p><strong>祝贺李欣羽同学！该论文已发表在 <em>ICCV Workshops</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/images/paper-01_hu4220616556499505728.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/images/paper-01_hu4217849018483358210.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/images/paper-01_hu5826829679943132540.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-iccv-workshops/images/paper-01_hu4220616556499505728.webp" width="760" height="329" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Xinyu Li、Chuanbiao Song、Chenqi Zhang、Jun Lan、Huijia Zhu、Weiqiang Wang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICCV Workshops</em></li> <li><strong>发表时间：</strong> 2025年10月19日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11375208/" target="_blank" rel="noopener">论文链接</a> · <a href="https://openaccess.thecvf.com/content/ICCV2025W/VQualA/papers/Li_Hybrid_Vision_Transformer_and_Convolutional_Neural_Network_for_Super-Resolution_Image_ICCVW_2025_paper.pdf" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对超分辨率图像质量评估（SRIQA）任务，提出一种结合视觉Transformer（ViT）与卷积神经网络（CNN）的混合无参考评估模型。该方法利用ViT提取非局部特征，并通过多阶段自注意力处理图像令牌，再将其重塑为特征图，由CNN编码映射为质量分数，从而同时捕捉局部与非局部信息，克服了传统全参考指标依赖真实图像且可靠性不足的问题。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-icip/ Sun, 14 Sep 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-icip/ <p>热烈祝贺贺子龙同学！论文《Enhancing Visual Question Answering Via Clustered In-Context Sequence Configuration》已发表在 <em>ICIP</em>。</p> <h2 id="enhancing-visual-question-answering-via-clustered-in-context-sequence-configuration">Enhancing Visual Question Answering Via Clustered In-Context Sequence Configuration</h2> <p><strong>祝贺贺子龙同学！该论文已发表在 <em>ICIP</em>。</strong></p> <ul> <li><strong>作者：</strong> Zilong He、Yijun Pan、Hebei Li、Feipeng Ma、Yansong Peng、Siying Wu、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>ICIP</em></li> <li><strong>发表时间：</strong> 2025年9月14日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11084650/" target="_blank" rel="noopener">论文链接</a> · <a href="https://drive.google.com/file/d/1rivgSv2AEK1_1Q40pHnp-VK9QCfzskTK/view" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对多模态大语言模型在多模态上下文学习中的演示序列配置问题，提出一种基于聚类的上下文配置方法。该方法自适应地对候选数据进行分组，并从每个簇中选取演示样本，以增强序列内多样性并保持语义一致性，从而减少高相似演示带来的归纳偏置，使模型更关注演示的主要意图。在OK-VQA、VQAv2、VizWiz和TextVQA四个视觉问答基准上的实验验证了其有效性。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-artificial-intelligence-in-medicine/ Thu, 28 Aug 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-artificial-intelligence-in-medicine/ <p>热烈祝贺王浩宇同学！论文《MMSupcon: An image fusion-based multi-modal supervised contrastive method for brain tumor diagnosis》已发表在 <em>Artificial Intelligence in Medicine</em>。</p> <h2 id="mmsupcon-an-image-fusion-based-multi-modal-supervised-contrastive-method-for-brain-tumor-diagnosis">MMSupcon: An image fusion-based multi-modal supervised contrastive method for brain tumor diagnosis</h2> <p><strong>祝贺王浩宇同学！该论文已发表在 <em>Artificial Intelligence in Medicine</em>。</strong></p> <ul> <li><strong>作者：</strong> Haoyu Wang、Jing Zhang、Siying Wu、Haoran Wei、Xun Chen、Yunwei Ou、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>Artificial Intelligence in Medicine</em></li> <li><strong>发表时间：</strong> 2025年8月28日</li> <li><strong>相关链接：</strong> <a href="https://www.sciencedirect.com/science/article/pii/S0933365725001885" target="_blank" rel="noopener">论文链接</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文针对脑肿瘤多模态MRI诊断中融合策略受限于样本稀缺的问题，提出多模态监督对比学习方法MMSupcon。该方法通过多模态医学图像融合生成信息丰富的样本，并设计多模态监督对比损失，引导模型有效整合互补模态信息，提升诊断准确性。</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-2025-ieee-international-conference-on-multimedi/ Mon, 30 Jun 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-2025-ieee-international-conference-on-multimedi/ <p>热烈祝贺李蔚同学！论文《Create anything anywhere: Layout-controllable personalized diffusion model for multiple subjects》已发表在 ICME 2025。</p> <h2 id="create-anything-anywhere-layout-controllable-personalized-diffusion-model-for-multiple-subjects">Create anything anywhere: Layout-controllable personalized diffusion model for multiple subjects</h2> <p><strong>祝贺李蔚同学！该论文已发表在 2025 IEEE International Conference on Multimedia and Expo (ICME), 1-6。</strong></p> <ul> <li><strong>作者：</strong> Wei Li、Hebei Li、Yansong Peng、Siying Wu、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> 2025 IEEE International Conference on Multimedia and Expo (ICME), 1-6</li> <li><strong>发表时间：</strong> 2025年6月30日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11209272/" target="_blank" rel="noopener">论文链接</a> · <a href="https://arxiv.org/pdf/2505.20909" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>Diffusion models have significantly advanced text-to-image generation, laying the foundation for the development of personalized generative frameworks. However, existing methods lack precise layout controllability and overlook the potential of dynamic features of reference subjects in improving fidelity. In this work, we propose Layout-Controllable Personalized Diffusion (LCP-Diffusion) model, a novel framework that integrates subject identity preservation with flexible layout guidance in a tuning-free approach. Our model employs a Dynamic-Static Complementary Visual Refining module to comprehensively capture the intricate details of reference subjects, and introduces a Dual Layout Control mechanism to enforce robust spatial control across both training and inference stages. Extensive experiments validate that LCP-Diffusion excels in both identity preservation and layout controllability. To the best of our …</p> https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ Tue, 10 Jun 2025 00:00:00 +0000 https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/ <p>热烈祝贺张哲宇同学！论文《Incomplete multi-modal brain tumor segmentation via learnable sorting state space model》已发表在 <em>CVPR</em>。</p> <h2 id="incomplete-multi-modal-brain-tumor-segmentation-via-learnable-sorting-state-space-model">Incomplete multi-modal brain tumor segmentation via learnable sorting state space model</h2> <p><strong>祝贺张哲宇同学！该论文已发表在 <em>CVPR</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Incomplete multi-modal brain tumor segmentation via learnable sorting state space model" srcset=" /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp 400w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu11624591397241064252.webp 760w, /event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu8784721236978794445.webp 1200w" src="https://vilab.team/event/%E7%A5%9D%E8%B4%BA%E5%AE%9E%E9%AA%8C%E5%AE%A4%E7%A7%91%E7%A0%94%E6%88%90%E6%9E%9C%E5%8F%91%E8%A1%A8%E4%BA%8E-cvpr/images/paper-01_hu12446196012194697519.webp" width="760" height="210" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Zheyu Zhang、Yayuan Lu、Feipeng Ma、Yueyi Zhang、Huanjing Yue、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>CVPR</em></li> <li><strong>发表时间：</strong> 2025年6月10日</li> <li><strong>相关链接：</strong> <a href="https://ieeexplore.ieee.org/abstract/document/11094296/" target="_blank" rel="noopener">论文链接</a> · <a href="https://openaccess.thecvf.com/content/CVPR2025/papers/Zhang_Incomplete_Multi-modal_Brain_Tumor_Segmentation_via_Learnable_Sorting_State_Space_CVPR_2025_paper.pdf" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>本文提出一种可学习排序状态空间模型（LS3M），用于不完整多模态脑肿瘤分割。该方法基于Mamba架构高效建模长距离依赖，并引入可微置换矩阵，根据模态特定特征对输入序列进行动态重排序，从而保留3D脑MRI中关键的空间归纳偏置与长程语义相关性。LS3M能够充分利用可用模态信息，提升分割性能。</p> https://vilab.team/event/2025biye/ Sun, 01 Jun 2025 08:00:00 +0000 https://vilab.team/event/2025biye/ https://vilab.team/event/publication-news-06e581b9272339ee/ Thu, 01 May 2025 00:00:00 +0000 https://vilab.team/event/publication-news-06e581b9272339ee/ <p>热烈祝贺彭岩松同学！论文《D-FINE: Redefine regression task of DETRs as fine-grained distribution refinement》已发表在 <em>ICLR 2025</em>。</p> <h2 id="d-fine-redefine-regression-task-of-detrs-as-fine-grained-distribution-refinement">D-FINE: Redefine regression task of DETRs as fine-grained distribution refinement</h2> <p><strong>祝贺彭岩松同学！该论文已发表在 <em>ICLR</em>。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="D-FINE: Redefine regression task of DETRs as fine-grained distribution refinement" srcset=" /event/publication-news-06e581b9272339ee/images/paper-01_hu14730101056268865597.webp 400w, /event/publication-news-06e581b9272339ee/images/paper-01_hu1666356483600992880.webp 760w, /event/publication-news-06e581b9272339ee/images/paper-01_hu15779176642512148333.webp 1200w" src="https://vilab.team/event/publication-news-06e581b9272339ee/images/paper-01_hu14730101056268865597.webp" width="760" height="314" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Yansong Peng、Hebei Li、Peixi Wu、Yueyi Zhang、Xiaoyan Sun、Feng Wu</li> <li><strong>发表载体：</strong> <em>ICLR</em></li> <li><strong>发表时间：</strong> 2025年5月1日</li> <li><strong>相关链接：</strong> <a href="https://proceedings.iclr.cc/paper_files/paper/2025/hash/6cf58a87e3097e7d1f9be3e8693a93de-Abstract-Conference.html" target="_blank" rel="noopener">论文链接</a> · <a href="https://proceedings.iclr.cc/paper_files/paper/2025/file/6cf58a87e3097e7d1f9be3e8693a93de-Paper-Conference.pdf" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/Peterande/D-FINE" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>D-FINE是一种实时目标检测器，通过重新定义DETR中的边界框回归任务实现高精度定位。其核心包含细粒度分布细化（FDR）和全局最优定位自蒸馏（GO-LSD）。FDR将回归从预测固定坐标改为迭代细化概率分布，提供细粒度中间表示；GO-LSD通过自蒸馏将定位知识从最终层传递到浅层，并简化深层残差预测。在COCO上达到54.0%/55.8% AP，124/78 FPS，预训练后达57.1%/59.3% AP，超越现有实时检测器，并显著提升多种DETR模型性能。</p> https://vilab.team/event/publication-news-021641c63fc12e96/ Fri, 11 Apr 2025 00:00:00 +0000 https://vilab.team/event/publication-news-021641c63fc12e96/ <p>热烈祝贺开大纯同学、李和倍同学、吴沛熹同学！近期，实验室共有 3 项科研成果正式发表。</p> <h2 id="event-enhanced-blurry-video-super-resolution">Event-enhanced blurry video super-resolution</h2> <p><strong>祝贺开大纯同学！该论文已发表在 Proceedings of the AAAI Conference on Artificial Intelligence 39 (4), 4175-4183。</strong></p> <ul> <li><strong>作者：</strong> Dachun Kai、Yueyi Zhang、Jin Wang、Zeyu Xiao、Zhiwei Xiong、Xiaoyan Sun</li> <li><strong>发表载体：</strong> Proceedings of the AAAI Conference on Artificial Intelligence 39 (4), 4175-4183</li> <li><strong>发表时间：</strong> 2025年4月11日</li> <li><strong>相关链接：</strong> <a href="https://ojs.aaai.org/index.php/AAAI/article/view/32438" target="_blank" rel="noopener">论文链接</a> · <a href="https://ojs.aaai.org/index.php/AAAI/article/download/32438/34593" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/DachunKai/Ev-DeblurVSR" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍">论文介绍</h3> <p>In this paper, we tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs. Current BVSR methods often fail to restore sharp details at high resolutions, resulting in noticeable artifacts and jitter due to insufficient motion information for deconvolution and the lack of high-frequency details in LR frames. To address these challenges, we introduce event signals into BVSR and propose a novel event-enhanced network, Ev-DeblurVSR. To effectively fuse information from frames and events for feature deblurring, we introduce a reciprocal feature deblurring module that leverages motion information from intra-frame events to deblur frame features while reciprocally using global scene context from the frames to enhance event features. Furthermore, to enhance temporal consistency, we propose a hybrid deformable alignment module that fully exploits the complementary motion information from inter-frame events and optical flow to improve motion estimation in the deformable alignment process. Extensive evaluations demonstrate that Ev-DeblurVSR establishes a new state-of-the-art performance on both synthetic and real-world datasets. Notably, on real data, our method is 2.59 dB more accurate and 7.28× faster than the recent best BVSR baseline FMA-Net.</p> <hr> <h2 id="efficient-event-based-semantic-segmentation-via-exploiting-frame-event-fusion-a-hybrid-neural-network-approach">Efficient event-based semantic segmentation via exploiting frame-event fusion: A hybrid neural network approach</h2> <p><strong>祝贺李和倍同学！该论文已发表在 <em>AAAI</em> 39(17)。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Efficient event-based semantic segmentation via exploiting frame-event fusion: A hybrid neural network approach" srcset=" /event/publication-news-021641c63fc12e96/images/paper-02_hu7998433290983327509.webp 400w, /event/publication-news-021641c63fc12e96/images/paper-02_hu5742706483688984605.webp 760w, /event/publication-news-021641c63fc12e96/images/paper-02_hu5093957591575336652.webp 1200w" src="https://vilab.team/event/publication-news-021641c63fc12e96/images/paper-02_hu7998433290983327509.webp" width="760" height="237" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Hebei Li、Yansong Peng、Jiahui Yuan、Peixi Wu、Jin Wang、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>AAAI</em> 39(17)</li> <li><strong>发表时间：</strong> 2025年4月11日</li> <li><strong>相关链接：</strong> <a href="https://ojs.aaai.org/index.php/AAAI/article/view/34013" target="_blank" rel="noopener">论文链接</a> · <a href="https://ojs.aaai.org/index.php/AAAI/article/download/34013/36168" target="_blank" rel="noopener">PDF</a></li> </ul> <h3 id="论文介绍-1">论文介绍</h3> <p>本文提出一种高效的混合神经网络框架，用于事件相机语义分割。该框架包含处理事件流的脉冲神经网络（SNN）分支和处理帧图像的人工神经网络（ANN）分支，并设计了自适应时间加权（ATW）注入器、事件驱动稀疏（EDS）注入器和通道选择融合（CSF）模块，以充分融合帧与事件的互补时空信息。在DDD17-Seg、DSEC-Semantic和M3ED-Semantic数据集上取得了最先进精度，并在DSEC-Semantic上降低63%能耗。</p> <hr> <h2 id="spiking-point-transformer-for-point-cloud-classification">Spiking point transformer for point cloud classification</h2> <p><strong>祝贺吴沛熹同学！该论文已发表在 <em>AAAI</em> 39(20)。</strong></p> <p> <figure > <div class="d-flex justify-content-center"> <div class="w-100" ><img alt="Spiking point transformer for point cloud classification" srcset=" /event/publication-news-021641c63fc12e96/images/paper-03_hu7240971347687367392.webp 400w, /event/publication-news-021641c63fc12e96/images/paper-03_hu15235344109779677276.webp 760w, /event/publication-news-021641c63fc12e96/images/paper-03_hu7343380604242636640.webp 1200w" src="https://vilab.team/event/publication-news-021641c63fc12e96/images/paper-03_hu7240971347687367392.webp" width="760" height="418" loading="lazy" data-zoomable /></div> </div></figure> </p> <ul> <li><strong>作者：</strong> Peixi Wu、Bosong Chai、Hebei Li、Menghua Zheng、Yansong Peng、Zeyu Wang、Xuan Nie、Yueyi Zhang、Xiaoyan Sun</li> <li><strong>发表载体：</strong> <em>AAAI</em> 39(20)</li> <li><strong>发表时间：</strong> 2025年4月11日</li> <li><strong>相关链接：</strong> <a href="https://ojs.aaai.org/index.php/AAAI/article/view/35459" target="_blank" rel="noopener">论文链接</a> · <a href="https://ojs.aaai.org/index.php/AAAI/article/view/35459/37614" target="_blank" rel="noopener">PDF</a> · <a href="https://github.com/PeppaWu/SPT" target="_blank" rel="noopener">代码</a></li> </ul> <h3 id="论文介绍-2">论文介绍</h3> <p>本文提出Spiking Point Transformer（SPT），首个基于Transformer的脉冲神经网络框架，用于三维点云分类。SPT设计队列驱动采样直接编码，在降低计算成本的同时保留关键支撑点；并引入混合动力学积分发放神经元（HD-IF），模拟选择性神经元激活，减少对特定人工神经元的过度依赖。在多个真实与合成点云基准上取得领先结果，理论能耗较ANN对应模型降低至少6.4倍。</p> https://vilab.team/event/example/ Wed, 01 Jan 2025 19:00:00 +0000 https://vilab.team/event/example/ https://vilab.team/event/2024nianzhong/ Tue, 10 Dec 2024 14:00:00 +0000 https://vilab.team/event/2024nianzhong/ https://vilab.team/event/2023yingxin/ Sun, 05 Nov 2023 19:00:00 +0000 https://vilab.team/event/2023yingxin/ https://vilab.team/event/2023valse/ Thu, 22 Jun 2023 18:00:00 +0000 https://vilab.team/event/2023valse/ https://vilab.team/event/2022yingxin/ Fri, 18 Nov 2022 18:00:00 +0000 https://vilab.team/event/2022yingxin/