CVPR14年关于图像检索方面的papers,汇总成一个list,方便阅读。


图像检索

  1. Triangulation embedding and democratic aggregation for image search (Orals)
  2. Collaborative Hashing (post)
  3. Packing and Padding: Coupled Multi-index for Accurate Image Retrieval (post) technical report
  4. Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval (post) technical report
  5. Fast Supervised Hashing with Decision Trees for High-Dimensional Data (post)
  6. Learning Fine-grained Image Similarity with Deep Ranking (post)
  7. Congruency-Based Reranking (post)可能
  8. Fisher and VLAD with FLAIR (post)可能
  9. Locality in Generic Instance Search from One Example (post)
  10. Asymmetric sparse kernel approximations for large-scale visual search (post)
  11. Locally Linear Hashing for Extracting Non-Linear Manifolds (post)
  12. Adaptive Object Retrieval with Kernel Reconstructive Hashing (post)
  13. Hierarchical Feature Hashing for Fast Dimensionality Reduction (post)

视频检索与事件检测

  1. Temporal Sequence Modeling For Video Event Detection (Orals)
  2. Visual Semantic Search: Retrieving Videos via Complex Textual Queries (post)

感兴趣文章

  • Robust Orthonormal Subspace Learning: Efficient Recovery of Corrupted Low-rank Matrices (Orals)

  • Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction (Orals)

  • Large-scale Video Classification using Convolutional Neural Networks (Orals)

  • Locally Optimized Product Quantization (post)

  • Product Sparse Coding (post)

  • Distance Encoded Product Quantization (post)

  • Covariance descriptors for 3D shape matching and retrieval (post)

  • Turning Mobile Phones into 3D Scanners (post)

  • Linear Ranking Analysis (post)

from: http://yongyuan.name/blog/cvpr14-reading-list.html

CVPR14 图像检索papers的更多相关文章

  1. 哈希学习(2)—— Hashing图像检索资源

    CVPR14 图像检索papers——图像检索 1.  Triangulation embedding and democratic aggregation for imagesearch (Oral ...

  2. 图像检索中为什么仍用BOW和LSH

    原文链接:http://blog.csdn.net/jwh_bupt/article/details/27713453 去年年底的时候在一篇博客中,用ANN的框架解释了BOW模型[1],并与LSH[2 ...

  3. International Conference for Smart Health 2015 Call for Papers

    Advancing Informatics for healthcare and healthcare applications has become an international researc ...

  4. IEEE/ACM ASONAM 2014 Industry Track Call for Papers

    IEEE/ACM International Conference on Advances in Social Network Analysis and Mining (ASONAM) 2014 In ...

  5. Call for Papers IEEE/ACM International Conference on Advances in Social Network Analysis and Mining (ASONAM)

    IEEE/ACM International Conference on Advances in Social Network Analysis and Mining (ASONAM) 2014 In ...

  6. Call for Papers International Conference for Smart Health (ICSH) 2014

    Call for PapersInternational Conference for Smart Health (ICSH) 2014 Beijing, China July 10-11, 2014 ...

  7. ICML历年Best Papers

    作者:我爱机器学习原文链接:ICML历年Best Papers ICML (Machine Learning)(1999-2016) 2016 Dueling Network Architecture ...

  8. CVPR历年Best Papers

    作者:我爱机器学习原文链接:CVPR历年Best Papers CVPR (Computer Vision)(2000-2016) 年份 标题 一作 一作单位 2016 Deep Residual L ...

  9. SIGKDD历年Best Papers

    作者:我爱机器学习原文链接:SIGKDD历年Best Papers SIGKDD(Data Mining)(1997-2016) 年份 标题 一作 一作单位 2016 FRAUDAR: Boundin ...

随机推荐

  1. 纯CSS实现3D图像轮转

    CSS演武场今天继续,今天看一个纯css实现的3D图像轮转效果,请大家猛戳研究效果先,也可下载收藏先. 首先看html文件,div.billboard为效果的容器,利用10个div.poster分割图 ...

  2. php7的新特性

    新增操作符1.??$username = $_GET['user'] ?? '';$username = isset($_GET['user']) ? $_GET['user'] : 'nobody' ...

  3. 1023 Have Fun with Numbers (20)(20 point(s))

    problem Notice that the number 123456789 is a 9-digit number consisting exactly the numbers from 1 t ...

  4. 机器学习之路:python 特征降维 特征筛选 feature_selection

    特征提取: 特征降维的手段 抛弃对结果没有联系的特征 抛弃对结果联系较少的特征 以这种方式,降低维度 数据集的特征过多,有些对结果没有任何关系,这个时候,将没有关系的特征删除,反而能获得更好的预测结果 ...

  5. django定时任务

    1.celery流程图: Celery的架构由三部分组成,消息中间件(message broker),任务执行单元(worker)和任务执行结果存储(task result store)组成 2.使用 ...

  6. django 动态url 可变

    首先在urls里面改,name=让一个映射敷个名字. 然后到books——list页面让编辑按钮改成这种可变的映射模式.

  7. 【CF 453A】 A. Little Pony and Expected Maximum(期望、快速幂)

    A. Little Pony and Expected Maximum time limit per test 1 second memory limit per test 256 megabytes ...

  8. PHP cURL中CURLOPT_CONNECTTIMEOUT和CURLOPT_TIMEOUT的区别

    CURLOPT_CONNECTTIMEOUT用来告诉PHP脚本在成功连接服务器前等待多久(连接成功之后就会开始缓冲输出),这个参数是为了应对目标服务器的过载,下线,或者崩溃等可能状况: CURLOPT ...

  9. MVC 设计模式与三层架构

    一.JavaEE开发模式 什么是开发模式 模式是在开发过程中总结出的"套路",总结出的一套约定俗成的设计模式 JavaEE模式 model1模式 技术组成 :jsp+javaBea ...

  10. 6.13校内互测 (DP 带权二分 斜率优化)

    丘中有麻plant 改自这儿,by ZBQ. 还有隐藏的一页不放了.. 直接走下去的话,如果开始时间确定那么到每个点的时间确定,把time减去dis就可以去掉路程的影响了. 这样对于减去d后的t,如果 ...