Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval最新文献_第6页

Quadruplet Networks for Sketch-Based Image Retrieval 基于草图的图像检索四重网络

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3078985

Omar Seddati, S. Dupont, S. Mahmoudi

{"title":"Quadruplet Networks for Sketch-Based Image Retrieval","authors":"Omar Seddati, S. Dupont, S. Mahmoudi","doi":"10.1145/3078971.3078985","DOIUrl":"https://doi.org/10.1145/3078971.3078985","url":null,"abstract":"Freehand sketches are a simple and powerful tool for communication. They are easily recognized across cultures and suitable for various applications. In this paper, we use deep convolutional neural networks (ConvNets) to address sketch-based image retrieval (SBIR). We first train our ConvNets on sketch and image object recognition in a large scale benchmark for SBIR (the sketchy database). We then conduct a comprehensive study of ConvNets features for SBIR, using a kNN similarity search paradigm in the ConvNet feature space. In contrast to recent SBIR works, we propose a new architecture the quadruplet networks which enhance ConvNet features for SBIR. This new architecture enables ConvNets to extract more robust global and local features. We evaluate our approach on three large scale datasets. Our quadruplet networks outperform previous state-of-the-art on two of them by a significant margin and gives competitive results on the third. Our system achieves a recall of 42.16% (at k=1) for the sketchy database (more than 5% improvement), a Kendal score of 43.28Τb on the TU-Berlin SBIR benchmark (close to 6Τb improvement) and a mean average precision (MAP) of 32.16% on Flickr15k (a category level SBIR benchmark).","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"67 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":"114382483","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: 33

Leveraging Semantic Facets for Adaptive Ranking of Social Comments 利用语义方面的社会评论自适应排名

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079004

Elaheh Momeni, Reza Rawassizadeh, Eytan Adar

{"title":"Leveraging Semantic Facets for Adaptive Ranking of Social Comments","authors":"Elaheh Momeni, Reza Rawassizadeh, Eytan Adar","doi":"10.1145/3078971.3079004","DOIUrl":"https://doi.org/10.1145/3078971.3079004","url":null,"abstract":"An essential part of the social media ecosystem is user-generated comments. However, not all comments are useful to all people as both authors of comments and readers have different intentions and perspectives. Consequently, the development of automated approaches for the ranking of comments and the optimization of viewers' interaction experiences are becoming increasingly important. This work proposes an adaptive faceted ranking framework which enriches comments along multiple semantic facets (e.g., subjectivity, informativeness, and topics), thus enabling users to explore different facets and select combinations of facets in order to extract and rank comments that match their interests. A prototype implementation of the framework has been developed which allows us to evaluate different ranking strategies of the proposed framework. We find that adaptive faceted ranking shows significant improvements over prevalent ranking methods which are utilized by many platforms such as YouTube or The Economist. We observe substantial improvements in user experience when enriching each element of a comment along multiple explicit semantic facets rather than in a single topic or subjective facets.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"7 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":"134578702","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: 3

Session details: Oral Session: Doctoral Symposium 会议细节:口头会议:博士研讨会

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254631

T. Piatrik

引用次数: 0

On the Effectiveness of Distance Measures for Similarity Search in Multi-Variate Sensory Data: Effectiveness of Distance Measures for Similarity Search 多变量感官数据中相似度搜索距离测度的有效性:相似度搜索距离测度的有效性

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079009

Yash Garg, S. Poccia

引用次数: 6

Classification of sMRI for Alzheimer's disease Diagnosis with CNN: Single Siamese Networks with 2D+? Approach and Fusion on ADNI 用CNN诊断阿尔茨海默病的sMRI分类:2D+的单暹罗网络?ADNI的入路与融合

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079010

Karim Aderghal, J. Benois-Pineau, K. Afdel

引用次数: 39

Expo: An Expectation-oriented System for Selecting Important Photos from Personal Collections 博览会:从个人收藏中选择重要照片的期望导向系统

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079011

Andrea Ceroni, V. Solachidis, C. Niederée, Olga Papadopoulou, V. Mezaris

引用次数: 3

Scalable Hadoop-Based Pooled Time Series of Big Video Data from the Deep Web 基于hadoop的深度网络大视频数据池时间序列

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3079019

C. Mattmann, M. Sharan

引用次数: 3

Session details: Oral Session 1: Vision and Language (Spotlight Presentations) 口头部分1:视觉与语言(重点演讲)

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254616

H. Cucu

引用次数: 0

Session details: Oral Session 4: Cross-media Retrieval (Oral presentations) 口头会议4:跨媒体检索(口头报告)

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3254626

Giorgos Tolias

引用次数: 0

Deep Supervised Hashing for Multi-Label and Large-Scale Image Retrieval 基于深度监督哈希的多标签大规模图像检索

Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval Pub Date : 2017-06-06 DOI: 10.1145/3078971.3078989

Dayan Wu, Zheng Lin, Bo Li, Mingzhen Ye, Weiping Wang

{"title":"Deep Supervised Hashing for Multi-Label and Large-Scale Image Retrieval","authors":"Dayan Wu, Zheng Lin, Bo Li, Mingzhen Ye, Weiping Wang","doi":"10.1145/3078971.3078989","DOIUrl":"https://doi.org/10.1145/3078971.3078989","url":null,"abstract":"One of the most challenging tasks in large-scale multi-label image retrieval is to map images into binary codes while preserving multilevel semantic similarity. Recently, several deep supervised hashing methods have been proposed to learn hash functions that preserve multilevel semantic similarity with deep convolutional neural networks. However, these triplet label based methods try to preserve the ranking order of images according to their similarity degrees to the queries while not putting direct constraints on the distance between the codes of very similar images. Besides, the current evaluation criteria are not able to measure the performance of existing hashing methods on preserving fine-grained multilevel semantic similarity. To tackle these issues, we propose a novel Deep Multilevel Semantic Similarity Preserving Hashing (DMSSPH) method to learn compact similarity-preserving binary codes for the huge body of multi-label image data with deep convolutional neural networks. In our approach, we make the best of the supervised information in the form of pairwise labels to maximize the discriminability of output binary codes. Extensive evaluations conducted on several benchmark datasets demonstrate that the proposed method significantly outperforms the state-of-the-art supervised and unsupervised hashing methods at the accuracies of top returned images, especially for shorter binary codes. Meanwhile, the proposed method shows better performance on preserving fine-grained multilevel semantic similarity according to the results under the Jaccard coefficient based evaluation criteria we propose.","PeriodicalId":403556,"journal":{"name":"Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval","volume":"104 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":"116265271","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: 61