发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval最新文献

筛选
英文 中文
Efficient Indexing of Regional Maximum Activations of Convolutions using Full-Text Search Engines 利用全文搜索引擎高效索引卷积的区域最大激活
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079035
Giuseppe Amato, F. Carrara, F. Falchi, C. Gennaro
{"title":"Efficient Indexing of Regional Maximum Activations of Convolutions using Full-Text Search Engines","authors":"Giuseppe Amato, F. Carrara, F. Falchi, C. Gennaro","doi":"10.1145/3078971.3079035","DOIUrl":"https://doi.org/10.1145/3078971.3079035","url":null,"abstract":"In this paper, we adapt a surrogate text representation technique to develop efficient instance-level image retrieval using Regional Maximum Activations of Convolutions (R-MAC). R-MAC features have recently showed outstanding performance in visual instance retrieval. However, contrary to the activations of hidden layers adopting ReLU (Rectified Linear Unit), these features are dense. This constitutes an obstacle to the direct use of inverted indexes, which rely on sparsity of data. We propose the use of deep permutations, a recent approach for efficient evaluation of permutations, to generate surrogate text representation of R-MAC features, enabling indexing of visual features as text into a standard search-engine. The experiments, conducted on Lucene, show the effectiveness and efficiency of the proposed approach.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133865867","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
Video Indexing, Search, Detection, and Description with Focus on TRECVID 视频索引，搜索，检测和描述与重点在TRECVID
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079044
G. Awad, Duy-Dinh Le, C. Ngo, Vinh-Tiep Nguyen, G. Quénot, Cees G. M. Snoek, S. Satoh
{"title":"Video Indexing, Search, Detection, and Description with Focus on TRECVID","authors":"G. Awad, Duy-Dinh Le, C. Ngo, Vinh-Tiep Nguyen, G. Quénot, Cees G. M. Snoek, S. Satoh","doi":"10.1145/3078971.3079044","DOIUrl":"https://doi.org/10.1145/3078971.3079044","url":null,"abstract":"There has been a tremendous growth in video data the last decade. People are using mobile phones and tablets to take, share or watch videos more than ever before. Video cameras are around us almost everywhere in the public domain (e.g. stores, streets, public facilities, ...etc). Efficient and effective retrieval methods are critically needed in different applications. The goal of TRECVID is to encourage research in content-based video retrieval by providing large test collections, uniform scoring procedures, and a forum for organizations interested in comparing their results. In this tutorial, we present and discuss some of the most important and fundamental content-based video retrieval problems such as recognizing predefined visual concepts, searching in videos for complex ad-hoc user queries, searching by image/video examples in a video dataset to retrieve specific objects, persons, or locations, detecting events, and finally bridging the gap between vision and language by looking into how can systems automatically describe videos in a natural language. A review of the state of the art, current challenges, and future directions along with pointers to useful resources will be presented by different regular TRECVID participating teams. Each team will present one of the following tasks: Semantic INdexing (SIN) Zero-example (0Ex) Video Search (AVS) Instance Search (INS) Multimedia Event Detection (MED) Video to Text (VTT)","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"93-94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132630420","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: 11
Session details: Oral Session 2: Multimedia Indexing (Spotlight presentations) 会议详情:口头会议2:多媒体索引(重点演讲)
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254621
A. Ulges
{"title":"Session details: Oral Session 2: Multimedia Indexing (Spotlight presentations)","authors":"A. Ulges","doi":"10.1145/3254621","DOIUrl":"https://doi.org/10.1145/3254621","url":null,"abstract":"","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132829326","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: 0
Multimodal Video Retrieval with the 2017 IMOTION System 基于2017 IMOTION系统的多模态视频检索
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079012
Luca Rossetto, Ivan Giangreco, Claudiu Tanase, H. Schuldt
{"title":"Multimodal Video Retrieval with the 2017 IMOTION System","authors":"Luca Rossetto, Ivan Giangreco, Claudiu Tanase, H. Schuldt","doi":"10.1145/3078971.3079012","DOIUrl":"https://doi.org/10.1145/3078971.3079012","url":null,"abstract":"The IMOTION system is a multimodal content-based video search and browsing application offering a rich set of query modes on the basis of a broad range of different features. It is able to scale with the size of the collection due to its underlying flexible polystore called ADAMpro and its very effective retrieval engine Cineast, optimized for multi-feature fusion. IMOTION is simultaneously geared towards precision-focused searches, i.e., known-item search with image or text queries, and recall-focused, exploratory searches. In this demo, we will present the 2017 IMOTION system deployed on the IACC.3 collection consisting of 600 hours of Internet Archive video, which was also used in the TRECVID 2016 Ad-Hoc Video Search and in the 2017 Video Browser Showdown (VBS) challenge in which IMOTION ranked first. Conference attendees will have the chance to interact with the 2017 IMOTION system and quickly solve various retrieval tasks.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122007151","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: 9
Tiny Transform Net for Mobile Image Stylization 移动图像风格化的微小变换网
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079034
Shilun Lin, Pengfei Xiong, Hailong Liu
{"title":"Tiny Transform Net for Mobile Image Stylization","authors":"Shilun Lin, Pengfei Xiong, Hailong Liu","doi":"10.1145/3078971.3079034","DOIUrl":"https://doi.org/10.1145/3078971.3079034","url":null,"abstract":"Artistic stylization is an image transformation problem that renders an image in the style of another one. Existing methods either regard image style transfer as an optimization of perceptual loss function based on a pre-trained network, or train a feed forward network that achieves style transfer through one forward propagation. However, time-consuming optimization processes or relatively large feed forward networks are unacceptable for mobile application. In this work we propose a tiny transform net to accomplish image stylization on mobile devices. The advantages of our proposed architecture come from that: (i) The size of the carefully designed network is less than 40KB, which is more than 166 times smaller than the current popular network; (ii) Progressive training is put forward to keep the training stable, which is implemental to achieve semantics aware stylization; (iii) Deep convolutional network inference algorithm is reconstructed on mobile platform to reduce the overhead of storage and time. In addition, well-trained tiny transform nets and demo application will be made available.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125790326","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: 1
Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection 零例事件检测的概念语言模型和基于事件的概念号选择
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079043
Damianos Galanopoulos, Fotini Markatopoulou, V. Mezaris, I. Patras
{"title":"Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection","authors":"Damianos Galanopoulos, Fotini Markatopoulou, V. Mezaris, I. Patras","doi":"10.1145/3078971.3079043","DOIUrl":"https://doi.org/10.1145/3078971.3079043","url":null,"abstract":"Zero-example event detection is a problem where, given an event query as input but no example videos for training a detector, the system retrieves the most closely related videos. In this paper we present a fully-automatic zero-example event detection method that is based on translating the event description to a predefined set of concepts for which previously trained visual concept detectors are available. We adopt the use of Concept Language Models (CLMs), which is a method of augmenting semantic concept definition, and we propose a new concept-selection method for deciding on the appropriate number of the concepts needed to describe an event query. The proposed system achieves state-of-the-art performance in automatic zero-example event detection.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125606857","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: 8
Session details: Special Oral Session: Beyond Semantics: Multimodal Understanding of Subjective Properties 特别口头讨论:超越语义学:主观属性的多模态理解
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254617
Miriam Redi
{"title":"Session details: Special Oral Session: Beyond Semantics: Multimodal Understanding of Subjective Properties","authors":"Miriam Redi","doi":"10.1145/3254617","DOIUrl":"https://doi.org/10.1145/3254617","url":null,"abstract":"","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130743995","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: 0
Searching for A Thing 寻找一个东西
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079006
A. Smeulders, R. Tao
{"title":"Searching for A Thing","authors":"A. Smeulders, R. Tao","doi":"10.1145/3078971.3079006","DOIUrl":"https://doi.org/10.1145/3078971.3079006","url":null,"abstract":"For humans, one picture usually suffices to identify an object of search. I am looking for this little girl, have you seen her? or Do you have such another one? are two ways to specify a target even to someone who has never seen the object of search before. Searching from one example in digital multimedia retrieval is a hard problem. From the one example one needs to derive an accurate estimate of all accidental variations in the target picture as well as the structural variation of the target in all other potential pictures. From the one example one needs to derive an accurate estimate of all accidental variations the target instance might have.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127497205","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: 0
Session details: Keynote 2 会议详情:主题演讲2
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254613
N. Sebe
{"title":"Session details: Keynote 2","authors":"N. Sebe","doi":"10.1145/3254613","DOIUrl":"https://doi.org/10.1145/3254613","url":null,"abstract":"","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126461068","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: 0
Manga FaceNet: Face Detection in Manga based on Deep Neural Network 漫画FaceNet:基于深度神经网络的漫画人脸检测
Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079031
W. Chu, Wei-Wei Li
{"title":"Manga FaceNet: Face Detection in Manga based on Deep Neural Network","authors":"W. Chu, Wei-Wei Li","doi":"10.1145/3078971.3079031","DOIUrl":"https://doi.org/10.1145/3078971.3079031","url":null,"abstract":"Among various elements of manga, character's face plays one of the most important role in access and retrieval. We propose a DNN-based method to do manga face detection, which is a challenging but relatively unexplored topic. Given a manga page, we first find candidate regions based on the selective search scheme. A deep neural network is then proposed to detect manga faces of various appearance. We evaluate the proposed method based on a large-scale benchmark, and show performance comparison and convincing evaluation results that have rarely done before.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115075931","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: 32
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信