Personal media capturing devices, such as smartphones or personal image and video cameras, are rarely synchronized. As a result, common tasks, like event detection and summarization across different multi-user media galleries, are considerably impeded and error-prone. In this paper, we investigate different approaches for the synchronization of image collections using visual information only. We perform a thorough evaluation of the performance of several global features on three datasets. Additionally, we explore the feasibility of common clustering algorithms for the detection of sub-events in the presence of synchronization misalignment.
{"title":"Media Synchronization and Sub-Event Detection in Multi-User Image Collections","authors":"M. Zaharieva, M. Riegler","doi":"10.1145/2815244.2815248","DOIUrl":"https://doi.org/10.1145/2815244.2815248","url":null,"abstract":"Personal media capturing devices, such as smartphones or personal image and video cameras, are rarely synchronized. As a result, common tasks, like event detection and summarization across different multi-user media galleries, are considerably impeded and error-prone. In this paper, we investigate different approaches for the synchronization of image collections using visual information only. We perform a thorough evaluation of the performance of several global features on three datasets. Additionally, we explore the feasibility of common clustering algorithms for the detection of sub-events in the presence of synchronization misalignment.","PeriodicalId":372942,"journal":{"name":"HuEvent '15","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132364325","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}
This paper describes a method to temporally align photo collections that have been created during the same event by different users using their own unsynchronized digital photo capture devices. Using multiple similarity measures, we identify pairs of similar photos from different collections. We then temporally align the photo collections by traversing a graph, whose nodes represent the collections, and edges represent the similar photo pairs between collections. Outcome of this process is a set of modified timestamps for the photos, which could be used in applications such as time-based clustering and sub-event detection in multi-user photo collections. We evaluate the proposed synchronization method on benchmark datasets and we compare it to state-of-the-art methods, demonstrating its superiority.
{"title":"Using Photo Similarity and Weighted Graphs for the Temporal Synchronization of Event-Centered Multi-User Photo Collections","authors":"Konstantinos Apostolidis, V. Mezaris","doi":"10.1145/2815244.2815246","DOIUrl":"https://doi.org/10.1145/2815244.2815246","url":null,"abstract":"This paper describes a method to temporally align photo collections that have been created during the same event by different users using their own unsynchronized digital photo capture devices. Using multiple similarity measures, we identify pairs of similar photos from different collections. We then temporally align the photo collections by traversing a graph, whose nodes represent the collections, and edges represent the similar photo pairs between collections. Outcome of this process is a set of modified timestamps for the photos, which could be used in applications such as time-based clustering and sub-event detection in multi-user photo collections. We evaluate the proposed synchronization method on benchmark datasets and we compare it to state-of-the-art methods, demonstrating its superiority.","PeriodicalId":372942,"journal":{"name":"HuEvent '15","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133530749","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}
Tingting Yao, Zhiyong Wang, Zhao Xie, Jun Gao, D. Feng
Human action recognition remains a challenging problem though having been intensively researched for decades. Recently, many sparse coding based approaches have been proposed to advance the progress in this research field. However, most of these approaches aim to learn a more discriminative dictionary by incorporating various regularization terms so that sparse codes are more representative for better recognition performance. Instead, in this paper, we propose a novel discriminative dictionary learning method which recognizes the commonness and specificness among different action classes. That is, we aim to obtain a universal dictionary which consists of two parts, a shared dictionary for all action classes and a set of class-specific dictionaries. As a result, inter-class differences can be better characterized with sparse codes obtained from the class-specific dictionaries. In addition, group sparsity constraint is utilized to ensure that similar descriptors of the same action class have similar sparse codes and locality constraint is utilized to ensure data locality. The experimental results on the popular UCF sports dataset demonstrate that our proposed approach outperforms the state-of-the-art of related methods.
{"title":"Discovering Commonness and Specificness for Human Action Recognition","authors":"Tingting Yao, Zhiyong Wang, Zhao Xie, Jun Gao, D. Feng","doi":"10.1145/2815244.2815247","DOIUrl":"https://doi.org/10.1145/2815244.2815247","url":null,"abstract":"Human action recognition remains a challenging problem though having been intensively researched for decades. Recently, many sparse coding based approaches have been proposed to advance the progress in this research field. However, most of these approaches aim to learn a more discriminative dictionary by incorporating various regularization terms so that sparse codes are more representative for better recognition performance. Instead, in this paper, we propose a novel discriminative dictionary learning method which recognizes the commonness and specificness among different action classes. That is, we aim to obtain a universal dictionary which consists of two parts, a shared dictionary for all action classes and a set of class-specific dictionaries. As a result, inter-class differences can be better characterized with sparse codes obtained from the class-specific dictionaries. In addition, group sparsity constraint is utilized to ensure that similar descriptors of the same action class have similar sparse codes and locality constraint is utilized to ensure data locality. The experimental results on the popular UCF sports dataset demonstrate that our proposed approach outperforms the state-of-the-art of related methods.","PeriodicalId":372942,"journal":{"name":"HuEvent '15","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127913560","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：