Filters








2,352 Hits in 5.8 sec

Spatio-temporal Person Retrieval via Natural Language Queries [article]

Masataka Yamaguchi, Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada
2017 arXiv   pre-print
To retrieve the tube of the person described by a given natural language query, we design a model that combines methods for spatio-temporal human detection and multimodal retrieval.  ...  In this paper, we address the problem of spatio-temporal person retrieval from multiple videos using a natural language query, in which we output a tube (i.e., a sequence of bounding boxes) which encloses  ...  Conclusion In this paper, we have addressed spatio-temporal person retrieval from multiple videos using natural language queries.  ... 
arXiv:1704.07945v2 fatcat:qsuffsssdfetramwoetipbidky

Spatio-Temporal Small Worlds for Decentralized Information Retrieval in Social Networking [article]

Georg Groh and Florian Straub and Benjamin Koster
2012 arXiv   pre-print
cohesion, giving rise to the concept of Spatio-Temporal Small Worlds.  ...  In addition to usual semantic contexts, these approaches make use of long-term social and spatio-temporal contexts in order to satisfy conscious as well as unconscious information needs according to Human  ...  The query is a formalization of a request which, in turn, is a natural language expression of a PIN. The PIN is the information need that a user subjectively perceives in the problematic situation.  ... 
arXiv:1209.2868v1 fatcat:w3dbwdhb2vd3lgt74zneejmhnu

Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences [article]

Zhu Zhang, Zhou Zhao, Yang Zhao, Qi Wang, Huasheng Liu, Lianli Gao
2020 arXiv   pre-print
Next, we introduce a spatio-temporal localizer with a dynamic selection method to directly retrieve the spatio-temporal tubes without tube pre-generation.  ...  Given an untrimmed video and a declarative/interrogative sentence depicting an object, STVG aims to localize the spatio-temporal tube of the queried object.  ...  Related Work Temporal Localization via Natural Language Temporal natural language localization is to detect the video clip depicting the given sentence.  ... 
arXiv:2001.06891v3 fatcat:df3uigkdrzbxdnfcze3ydpicpi

Person Tube Retrieval via Language Description

Hehe Fan, Yi Yang
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
This paper focuses on the problem of person tube (a sequence of bounding boxes which encloses a person in a video) retrieval using a natural language query.  ...  Experimental results on person tube retrieval via language description and other two related tasks demonstrate the efficacy of MSSP.  ...  Person Tube Gallery Natural Language Query Person Tube of Interest Figure 1 : Examples of person tube retrieval via natural language queries.  ... 
doi:10.1609/aaai.v34i07.6704 fatcat:4k6brjtprvgwxjbrupnpe25l64

The picture of health

Rongjian Lan, Michael D. Lieberman, Hanan Samet
2012 Proceedings of the First ACM SIGSPATIAL International Workshop on Use of GIS in Public Health - HealthGIS '12  
While STEWARD was previously used in a disease tracking role, improvements to STEWARD are described including an innovative time slider that allows powerful and intuitive spatio-textual querying.  ...  DATA PROCESSING In this section, we describe the format of the ProMED data, and how we retrieve and process it for spatio-temporal querying and retrieval in STEWARD.  ...  To execute spatio-temporal queries, the keyword and spatial components of the query are first executed in STEWARD's database, and relevant documents R are retrieved.  ... 
doi:10.1145/2452516.2452522 dblp:conf/gis/LanLS12 fatcat:cojp2dcon5hvda7oz7xpzbgxfu

Querying Video Data by Spatio-Temporal Relationships of Moving Object Traces [chapter]

Chikashi Yajima, Yoshihiro Nakanishi, Katsumi Tanaka
2002 Visual and Multimedia Information Management  
We propose a query method that allows viewers to search video data based on the spatio-temporal relationships of moving objects using a simple and intuitive mode of input.  ...  , querying of movements of multiple moving objects specifying the spatio-temporal relationships among objects by expressing each object's trace on a timeline or multicanvas, and providing a non-linear  ...  That is, the horizontal positions of the canvases by nature signify the temporal relationship of video.  ... 
doi:10.1007/978-0-387-35592-4_25 fatcat:6gdgexxah5dxbh3dwnoswcv7ua

Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences

Zhu Zhang, Zhou Zhao, Yang Zhao, Qi Wang, Huasheng Liu, Lianli Gao
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Next, we introduce a spatiotemporal localizer with a dynamic selection method to directly retrieve the spatio-temporal tubes without tube pregeneration.  ...  In this paper, we consider a novel task, Spatio-Temporal Video Grounding for Multi-Form Sentences (STVG).  ...  Related Work Temporal Localization via Natural Language Temporal natural language localization is to detect the video clip depicting the given sentence.  ... 
doi:10.1109/cvpr42600.2020.01068 dblp:conf/cvpr/ZhangZZWLG20 fatcat:umcnf6qsajcezfx6k2sa2a6t5e

HERO: HiErarchical spatio-tempoRal reasOning with Contrastive Action Correspondence for End-to-End Video Object Grounding [article]

Mengze Li and Tianbao Wang and Haoyu Zhang and Shengyu Zhang and Zhou Zhao and Wenqiao Zhang and Jiaxu Miao and Shiliang Pu and Fei Wu
2022 arXiv   pre-print
Video Object Grounding (VOG) is the problem of associating spatial object regions in the video to a descriptive natural language query.  ...  This is a challenging vision-language task that necessitates constructing the correct cross-modal correspondence and modeling the appropriate spatio-temporal context of the query video and caption, thereby  ...  (B) Insensitive Spatio-Temporal Locality Inference.  ... 
arXiv:2208.05818v1 fatcat:cq7mh2dl5bdbfhwsj74buty2k4

Making Large Information Sources Better Accessible Using Fuzzy Set Theory [chapter]

Guy De Tré
2013 Studies in Fuzziness and Soft Computing  
As users most efficiently express their retrieval preferences using natural language and as matching in information retrieval and query processing in such cases often becomes a matter of degree or in some  ...  Along with the availability of the huge quantity of data comes the need for query engines and tools to efficiently explore and access these data and provide users with the facilities to retrieve exactly  ...  As users most efficiently express their retrieval preferences using natural language and as matching in information retrieval and query processing in such cases often becomes a matter of degree or in some  ... 
doi:10.1007/978-3-642-35641-4_21 fatcat:jc34sh44kbdfrfourtcvx5hjte

Visual Relation Grounding in Videos [article]

Junbin Xiao, Xindi Shang, Xun Yang, Sheng Tang, Tat-Seng Chua
2020 arXiv   pre-print
The challenges in this task include but not limited to: (1) both the subject and object are required to be spatio-temporally localized to ground a query relation; (2) the temporal dynamic nature of visual  ...  The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive visual facts for other high-level video-language tasks  ...  Yamaguchi, M., Saito, K., Ushiku, Y., Harada, T.: Spatio-temporal person retrieval via natural language queries.  ... 
arXiv:2007.08814v2 fatcat:24nbfoj3kbcvtpjcqm22ndsqj4

Natural language querying for video databases

Guzen Erozel, Nihan Kesim Cicekli, Ilyas Cicekli
2008 Information Sciences  
Spatio-temporal relationships between video objects and also trajectories of moving objects can be queried with this data model.  ...  Video archive systems need user-friendly interfaces to retrieve video frames. In this paper, a user interface based on natural language processing (NLP) to a video database system is described.  ...  Conclusion The system described in this paper uses a natural language querying interface to retrieve information from a video database which supports content-based spatio-temporal querying.  ... 
doi:10.1016/j.ins.2008.02.001 fatcat:iylyjnge7rbbbnef77ttqeb43m

Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding [article]

Yang Jin, Yongzhi Li, Zehuan Yuan, Yadong Mu
2022 arXiv   pre-print
Spatio-Temporal video grounding (STVG) focuses on retrieving the spatio-temporal tube of a specific object depicted by a free-form textual expression.  ...  language.  ...  It aims to localize a region from the visual content specified by a given natural language query.  ... 
arXiv:2209.13306v1 fatcat:ip7u7474kzbirph3wbktm74qyy

Language Bindings for Spatio-Temporal Database Programming in Tripod [chapter]

Tony Griffiths, Norman W. Paton, Alvaro A. A. Fernandes, Seung-Hyun Jeong, Nassima Djafri
2004 Lecture Notes in Computer Science  
While there are many proposals for spatio-temporal data models and query languages, there is a lack of research into application development using spatio-temporal database systems.  ...  This paper seeks to redress the balance by exploring how to support database programming for spatio-temporal object databases, with specific reference to the Tripod spatio-temporal OODBMS.  ...  If adopted to support spatio-temporal data, ADTs would make operations for querying and updating spatio-temporal data available from within a query language, but have a number of limitations for wider  ... 
doi:10.1007/978-3-540-27811-5_20 fatcat:no243nnbabfhvczxp2tdkeuohe

Spatio-temporal Indexing in Database Semantics [chapter]

Roland Hausser
2001 Lecture Notes in Computer Science  
Such an analysis is important for modeling natural language communication because spatio-temporal information is constantly coded into language by the speaker and decoded by the hearer.  ...  Starting from the spatio-temporal characterization of direct observation in cognitive agents without language, the speaker's coding of spatio-temporal information into language is analyzed, followed by  ...  Reconstructing spatio-temporal location In natural language communication, the spatio-temporal location of the speaker's propositional content must be reconstructed by the hearer.  ... 
doi:10.1007/3-540-44686-9_5 fatcat:jbvwqg56y5e2zm2v267wb4b4tq

Spatio-temporal data access for information-based decision making

R. Ladner, E. Warner, F. Petry
2003 Oceans 2003. Celebrating the Past ... Teaming Toward the Future (IEEE Cat. No.03CH37492)  
the time varying nature of moving objects, namely spatio-temporal structures.  ...  and retrieving data.  ...  Meteorological and oceanographic data presents many issues pertinent to access and retrieval of such data from heterogeneous sources in a distributed system.  ... 
doi:10.1109/oceans.2003.178477 fatcat:lfz4arjfnzcnpbmofaif7btg4q
« Previous Showing results 1 — 15 out of 2,352 results