Proceedings of the 1st ACM International Conference on Multimedia Retrieval最新文献_第3页

ShotTagger: tag location for internet videos ShotTagger:网络视频的标签位置

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992033

Guangda Li, Meng Wang, Yantao Zheng, Haojie Li, Zhengjun Zha, Tat-Seng Chua

{"title":"ShotTagger: tag location for internet videos","authors":"Guangda Li, Meng Wang, Yantao Zheng, Haojie Li, Zhengjun Zha, Tat-Seng Chua","doi":"10.1145/1991996.1992033","DOIUrl":"https://doi.org/10.1145/1991996.1992033","url":null,"abstract":"Social video sharing websites allow users to annotate videos with descriptive keywords called tags, which greatly facilitate video search and browsing. However, many tags only describe part of the video content, without any temporal indication on when the tag actually appears. Currently, there is very little research on automatically assigning tags to shot-level segments of a video. In this paper, we leverage user's tags as a source to analyze the content within the video and develop a novel system named ShotTagger to assign tags at the shot level. There are two steps to accomplish the location of tags at shot level. The first is to estimate the distribution of tags within the video, which is based on a multiple instance learning framework. The second is to perform the semantic correlation of a tag with other tags in a video in an optimization framework and impose the temporal smoothness across adjacent video shots to refine the tagging results at shot level. We present different applications to demonstrate the usefulness of the tag location scheme in searching, and browsing of videos. A series of experiments conducted on a set of Youtube videos has demonstrated the feasibility and effectiveness of our approach.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"5 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116796382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 30

Botanical data retrieval system supporting discovery learning 支持发现学习的植物数据检索系统

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992032

T. Kajiyama

{"title":"Botanical data retrieval system supporting discovery learning","authors":"T. Kajiyama","doi":"10.1145/1991996.1992032","DOIUrl":"https://doi.org/10.1145/1991996.1992032","url":null,"abstract":"We constructed a botanical data retrieval system applying our proposed search interface named 'Concentric Ring View' for multi-faceted metadata. This system allows users to search flexibly and intuitively by combining attributes with simple operation. The attributes used as search keys are visual and botanical features such as flower color, leaf shape, blooming season, and so on. Users can create their own dynamic knowledge hierarchies by selecting these attributes and adjusting attribute values. We considered that this system enables users not only to search for plant names but also to learn morphological features and the taxonomy of plants, and performed a usability testing. We confirmed that users could finally find the correct plant names even if each user selected different attributes for searching, and users could also find correct plants by grasping visual features even if the images shown focused on flower and leaf. In discovery learning, users could learn plant features and botanical properties by finding out the common properties from the relationships between attributes and attribute values, and attribute values and retrieved results.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134232491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Social negative bootstrapping for visual categorization 视觉分类的社会负性自举

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992008

Xirong Li, Cees G. M. Snoek, M. Worring, A. Smeulders

{"title":"Social negative bootstrapping for visual categorization","authors":"Xirong Li, Cees G. M. Snoek, M. Worring, A. Smeulders","doi":"10.1145/1991996.1992008","DOIUrl":"https://doi.org/10.1145/1991996.1992008","url":null,"abstract":"To learn classifiers for many visual categories, obtaining labeled training examples in an efficient way is crucial. Since a classifier tends to misclassify negative examples which are visually similar to positive examples, inclusion of such informative negatives should be stressed in the learning process. However, they are unlikely to be hit by random sampling, the de facto standard in literature. In this paper, we go beyond random sampling by introducing a novel social negative bootstrapping approach. Given a visual category and a few positive examples, the proposed approach adaptively and iteratively harvests informative negatives from a large amount of social-tagged images. To label negative examples without human interaction, we design an effective virtual labeling procedure based on simple tag reasoning. Virtual labeling, in combination with adaptive sampling, enables us to select the most misclassified negatives as the informative samples. Learning from the positive set and the informative negative sets results in visual classifiers with higher accuracy. Experiments on two present-day image benchmarks employing 650K virtually labeled negative examples show the viability of the proposed approach. On a popular visual categorization benchmark our precision at 20 increases by 34%, compared to baselines trained on randomly sampled negatives. We achieve more accurate visual categorization without the need of manually labeling any negatives.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132965093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22

Large-scale EMM identification based on geometry-constrained visual word correspondence voting 基于几何约束的视觉词对应投票的大规模EMM识别

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992031

Xin Yang, Qiong Liu, Chunyuan Liao, K. Cheng, Andreas Girgensohn

{"title":"Large-scale EMM identification based on geometry-constrained visual word correspondence voting","authors":"Xin Yang, Qiong Liu, Chunyuan Liao, K. Cheng, Andreas Girgensohn","doi":"10.1145/1991996.1992031","DOIUrl":"https://doi.org/10.1145/1991996.1992031","url":null,"abstract":"We present a large-scale Embedded Media Marker (EMM) identification system which allows users to retrieve relevant dynamic media associated with a static paper document via camera-phones. The user supplies a query image by capturing an EMM-signified patch of a paper document through a camera phone. The system recognizes the query and in turn retrieves and plays the corresponding media on the phone. Accurate image matching is crucial for positive user experience in this application. To address the challenges posed by large datasets and variation in camera-phone-captured query images, we introduce a novel image matching scheme based on geometrically consistent correspondences. A hierarchical scheme, combined with two constraining methods, is designed to detect geometric constrained correspondences between images. A spatial neighborhood search approach is further proposed to address challenging cases of query images with a large translational shift. Experimental results on a 200k+ dataset show that our solution achieves high accuracy with low memory and time complexity and outperforms the baseline bag-of-words approach.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126756468","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Multimedia retrieval in social networks for photo book creation 多媒体检索在社交网络的照片书创作

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992068

Mohammad Rabbath, Philipp Sandhaus, Susanne CJ Boll

{"title":"Multimedia retrieval in social networks for photo book creation","authors":"Mohammad Rabbath, Philipp Sandhaus, Susanne CJ Boll","doi":"10.1145/1991996.1992068","DOIUrl":"https://doi.org/10.1145/1991996.1992068","url":null,"abstract":"Social networks such as Facebook witness an explosively growing number of shared photos. People enjoy taking photos of each other in public and private events, upload them, tag each other and continue commenting on each other's photos. These photos are considered to be great assets for many users who would like to create photo books from them, so that they can show their experience and special events to friends and family. However, finding the required photos is not an easy task, because they can be distributed over different friends and albums with different tags and annotations, and they can be of different importance to the user. In this paper we propose a software prototype which employs multimedia retrieval methods to allow an easy creation of photo books from social networks. In our system photos are first clustered to events which can potentially be distributed over the social network, and then selected based on their importance and finally distributed and laid out over the pages of a photo book. The functionalities of our system are implemented and deployed as web services and our presentation layer is a wizard-like Facebook application.","PeriodicalId":390933,"journal":{"name":"Proceedings of the 1st ACM International Conference on Multimedia Retrieval","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123372707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

A comparison of extended fingerprint hashing and locality sensitive hashing for binary audio fingerprints 二进制音频指纹扩展哈希和位置敏感哈希的比较

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992027

K. Moravec, I. Cox

引用次数: 10

Pairwise weak geometric consistency for large scale image search 大规模图像搜索的两两弱几何一致性

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992038

Hongtao Xie, Ke Gao, Yongdong Zhang, Jintao Li, Yizhi Liu

引用次数: 18

Interpretable visual models for human perception-based object retrieval 基于人类感知的对象检索的可解释视觉模型

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992017

A. Rebai, A. Joly, N. Boujemaa

引用次数: 1

Water reflection recognition via minimizing reflection cost based on motion blur invariant moments 基于运动模糊不变矩最小化反射代价的水面反射识别

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992001

S. Zhong, Yan Liu, Ling Shao, K. F. Chung

引用次数: 2

The hyper media news system for multimodal and personalised fruition of informative content 该超媒体新闻系统实现了多模式和个性化的信息内容

Proceedings of the 1st ACM International Conference on Multimedia Retrieval Pub Date : 2011-04-18 DOI: 10.1145/1991996.1992060

A. Messina, M. Montagnuolo, Riccardo Di Massa, Andrea Elia

引用次数: 4