ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream最新文献

A non-parametric unsupervised approach for content based image retrieval and clustering 基于内容的图像检索和聚类的非参数无监督方法

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510656

Konstantinos Makantasis, A. Doulamis, N. Doulamis

{"title":"A non-parametric unsupervised approach for content based image retrieval and clustering","authors":"Konstantinos Makantasis, A. Doulamis, N. Doulamis","doi":"10.1145/2510650.2510656","DOIUrl":"https://doi.org/10.1145/2510650.2510656","url":null,"abstract":"Nowadays, there are available extremely large collections of images located on distributed and heterogeneous platforms over the web. The proliferation of billions of shared photos has outpaced the current technology for browsing such collections, but at the same time it spurred the emergence of new image retrieval techniques based not only on photos' visual information, but on geo-location tags and camera exif data. Although, additional image information may be proven very useful for preliminary image retrieval, the final retrieved result is necessary to be refined by exploiting visual information.\u0000 In this paper we present a process for refining image retrieval results by exploiting and fusing two unsupervised clustering techniques: DBSCAN and spectral clustering. DBSCAN algorithm is used to remove outliers from the initially retrieved image set, and spectral clustering finalizes retrieval process by clustering together visually similar images. However, DBSCAN and spectral clustering require manual tunning of their parameters, which usually requires a priori knowledge of the dataset. To overcome this problem we developed a tuning mechanism that automatically tunes the parameters of both algorithms. For the evaluation of the proposed approach we used thousands of images from Flickr downloaded using text queries for well known cultural heritage monuments.","PeriodicalId":360789,"journal":{"name":"ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129925117","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

Behavior recognition from video based on human constrained descriptor and adaptable neural networks 基于人类约束描述符和自适应神经网络的视频行为识别

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510659

A. Voulodimos, N. Doulamis, S. Tsafarakis

引用次数: 2

On improving the robustness of variational optical flow against illumination changes 提高变分光流对光照变化的鲁棒性

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510660

M. A. Mohamed, Hatem A. Rashwan, B. Mertsching, M. García, D. Puig

引用次数: 8

Domain transfer for person re-identification 域名转移用于人员重新识别

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510658

Ryan Layne, Timothy M. Hospedales, S. Gong

{"title":"Domain transfer for person re-identification","authors":"Ryan Layne, Timothy M. Hospedales, S. Gong","doi":"10.1145/2510650.2510658","DOIUrl":"https://doi.org/10.1145/2510650.2510658","url":null,"abstract":"Automatic person re-identification in is a crucial capability underpinning many applications in public space video surveillance. It is challenging due to intra-class variation in person appearance when observed in different views, together with limited inter-class variability. Various recent approaches have made great progress in re-identification performance using discriminative learning techniques. However, these approaches are fundamentally limited by the requirement of extensive annotated training data for every pair of views. For practical re-identification, this is an unreasonable assumption, as annotating extensive volumes of data for every pair of cameras to be re-identified may be impossible or prohibitively expensive.\u0000 In this paper we move toward relaxing this strong assumption by investigating flexible multi-source transfer of re-identification models across camera pairs. Specifically, we show how to leverage prior re-identification models learned for a set of source view pairs (domains), and flexibly combine these to obtain good re-identification performance in a target view pair (domain) with greatly reduced training data requirements in the target domain.","PeriodicalId":360789,"journal":{"name":"ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134100219","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

Cross-domain traffic scene understanding by motion model transfer 基于运动模型迁移的跨域交通场景理解

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510657

Xun Xu, S. Gong, Timothy M. Hospedales

{"title":"Cross-domain traffic scene understanding by motion model transfer","authors":"Xun Xu, S. Gong, Timothy M. Hospedales","doi":"10.1145/2510650.2510657","DOIUrl":"https://doi.org/10.1145/2510650.2510657","url":null,"abstract":"This paper proposes a novel framework for cross-domain traffic scene understanding. Existing learning-based outdoor wide-area scene interpretation models suffer from requiring long term data collection in order to acquire statistically sufficient model training samples for every new scene. This makes installation costly, prevents models from being easily relocated, and from being used in UAVs with continuously changing scenes. In contrast, our method adopts a geometrical matching approach to relate motion models learned from a database of source scenes (source domains) with a handful sparsely observed data in a new target scene (target domain). This framework is capable of online ''sparse-shot'' anomaly detection and motion event classification in the unseen target domain, without the need for extensive data collection, labelling and offline model training for each new target domain. That is, trained models in different source domains can be deployed to a new target domain with only a few unlabelled observations and without any training in the new target domain. Crucially, to provide cross-domain interpretation without risk of dramatic negative transfer, we introduce and formulate a scene association criterion to quantify transferability of motion models from one scene to another. Extensive experiments show the effectiveness of the proposed framework for cross-domain motion event classification, anomaly detection and scene association.","PeriodicalId":360789,"journal":{"name":"ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134579907","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

Warping trajectories for video synchronization 视频同步的扭曲轨迹

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510654

S. Shankar, Joan Lasenby, A. Kokaram

{"title":"Warping trajectories for video synchronization","authors":"S. Shankar, Joan Lasenby, A. Kokaram","doi":"10.1145/2510650.2510654","DOIUrl":"https://doi.org/10.1145/2510650.2510654","url":null,"abstract":"Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied, since recordings are made using the same timebase, or time-stamp information is embedded in the video streams. Recordings using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. In this paper, we propose a technique which exploits feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. Our method automatically selects the moving feature points in the two unsynchronized videos whose 2D trajectories can be best related, thereby helping to infer the synchronization index. We evaluate performance using a number of real recordings and show that synchronization can be achieved to within 1 sec, which is better than previous approaches.","PeriodicalId":360789,"journal":{"name":"ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream","volume":"115 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130028267","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: 5

Abnormal crowd behavior detection and localization using maximum sub-sequence search 基于最大子序列搜索的人群异常行为检测与定位

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510655

Kai-wen Cheng, Yie-Tarng Chen, Wen-Hsien Fang

引用次数: 21

Background modeling methods for visual detection of maritime targets 海上目标视觉检测的背景建模方法

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510652

Paris Kaimakis, N. Tsapatsoulis

引用次数: 8

Hand gesture recognition with depth data 手势识别与深度数据

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510651

Fabio Dominio, Mauro Donadeo, Giulio Marin, P. Zanuttigh, G. Cortelazzo

引用次数: 51

Nobody likes Mondays: foreground detection and behavioral patterns analysis in complex urban scenes 没有人喜欢星期一:在复杂的城市场景中进行前景检测和行为模式分析

ACM/IEEE international workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Stream Pub Date : 2013-10-21 DOI: 10.1145/2510650.2510653

Gloria Zen, John Krumm, N. Sebe, E. Horvitz, Ashish Kapoor

引用次数: 9