4,714 Hits in 7.2 sec

A Natural-language-based Visual Query Approach of Uncertain Human Trajectories

Zhaosong Huang, Ye Zhao, Wei Chen, Shengjie Gao, Kejie Yu, Weixia Xu, Mingjie Tang, Minfeng Zhu, Mingliang Xu
2019 IEEE Transactions on Visualization and Computer Graphics  
In this paper, we propose a visual analytics approach that can extract spatial-temporal constraints from a textual sentence and support an effective query method over uncertain mobile trajectory data.  ...  On the other hand, domain experts and general users prefer a natural way, such as using a natural language sentence, to access and analyze massive movement data.  ...  ACKNOWLEDGMENTS This work was supported in part by National Natural Science Foundation of China (U1609217, 61772456, 61761136020). Y. Zhao's work was supported in part by the U.S.  ... 
doi:10.1109/tvcg.2019.2934671 pmid:31443013 fatcat:pa7womdqdrasnl6awvhoynuuhi

Mining Massive-Scale Spatiotemporal Trajectories in Parallel: A Survey [chapter]

Pengtao Huang, Bo Yuan
2015 Lecture Notes in Computer Science  
For many trajectory mining problems, a number of computationally efficient approaches have been proposed.  ...  In this paper, we present a comprehensive survey of the state-of-the-art techniques for mining massive-scale spatiotemporal trajectory data based on parallel computing platforms such as Graphics Processing  ...  [40] presented a GPU-based approach to index and query largescale geospatial data using R-Trees.  ... 
doi:10.1007/978-3-319-25660-3_4 fatcat:qdkslwlgjzesdfnzvkbrpsgmti

Visually-Enabled Active Deep Learning for (Geo) Text and Image Classification: A Review

Liping Yang, Alan MacEachren, Prasenjit Mitra, Teresa Onorati
2018 ISPRS International Journal of Geo-Information  
of spatial language, and related geo-semantics challenges.  ...  Based on this framing and our systematic review of key research, we then discuss some of the main challenges of integrating active learning with visual analytics and deep learning, and point out research  ...  Their examples also demonstrated how the ANALYTiC web-based visual interface can support the domain expert in the AL process and specifically in the trajectory annotation using a set of visual solutions  ... 
doi:10.3390/ijgi7020065 fatcat:2vjluil5zfbvzmlvbvbb7i433q

I2T: Image Parsing to Text Description

Benjamin Z Yao, Xiong Yang, Liang Lin, Mun Wai Lee, Song-Chun Zhu
2010 Proceedings of the IEEE  
is a formal and unambiguous knowledge representation. 3) A text generation engine converts the semantic representation into a semantically meaningful, human readable and query-able text report.  ...  The core of the visual knowledge base is an And-Or graph representation.  ...  End users can access the semantic information of image by either directly reading the natural language text report or querying the semantic web using semantic querying language.  ... 
doi:10.1109/jproc.2010.2050411 fatcat:efostazxbrhghmtctxr6uoqdfu

Anomaly detection in GPS data based on visual analytics

Zicheng Liao, Yizhou Yu, Baoquan Chen
2010 2010 IEEE Symposium on Visual Analytics Science and Technology  
In this paper we introduce GPSvas (GPS Visual Analytics System), a system that detects anomalies in GPS data using the approach of visual analytics: a conditional random field (CRF) model is used as the  ...  We combine the power of the two for anomaly detection in GPS data by integrating them through a visualization and human-computer interaction interface.  ...  ACKNOWLEDGEMENTS This work was partially supported by National Science Foundation (IIS 09-14631), National Natural Science Foundation of China (60728204, 60902104), National High-tech R&D Program of China  ... 
doi:10.1109/vast.2010.5652467 dblp:conf/ieeevast/LiaoYC10 fatcat:yedzkjiwnneezdkbrccwdcsjrq

Human action recognition with MPEG-7 descriptors and architectures

Zia Moghaddam, Massimo Piccardi
2010 Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams - ARTEMIS '10  
The descriptors and architectures are evaluated in the paper by way of a scenario analysis.  ...  In addition, surveillance applications need to be portable over a variety of platforms, from servers to mobile devices.  ...  Moreover, as we discuss in the next section, the use of MPEG-7 Motion Trajectory Descriptor may imply a considerable overhead due to the uncertain time segmentation of human actions.  ... 
doi:10.1145/1877868.1877885 dblp:conf/mm/MoghaddamP10 fatcat:m6jn2noyazejfljbgk7dt3ik4q

Towards Natural Language Interfaces for Data Visualization: A Survey [article]

Leixian Shen, Enya Shen, Yuyu Luo, Xiaocong Yang, Xuming Hu, Xiongshuai Zhang, Zhiwei Tai, Jianmin Wang
2021 arXiv   pre-print
In order to classify each paper, we develop categorical dimensions based on a classic information visualization pipeline with the extension of a V-NLI layer.  ...  Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience.  ...  [90] proposed a query engine to convert, store and retrieve spatial uncertain mobile trajectories via intuitive NL input. Leo John et al.  ... 
arXiv:2109.03506v1 fatcat:7cz5ibrwyrhdlbkij3e74u6lem

Sharing Cognition: Human Gesture and Natural Language Grounding Based Planning and Navigation for Indoor Robots [article]

Gourav Kumar, Soumyadip Maity, Ruddra dev Roychoudhury, Brojeshwar Bhowmick
2021 arXiv   pre-print
This shows a big advantage over using only Vision and Language-based Navigation, Language Grounding or Human-Robot Interaction in a task requiring the development of cognition and indoor navigation.  ...  We adapt the state-of-the-art modules of Language Grounding and Human-Robot Interaction to demonstrate a novel system pipeline in real-world environments on a Telepresence robot for performing a set of  ...  Replying to the query of robot about a location environment, a human guide communicates the information using natural language and body gesture while the robot observes him/her.  ... 
arXiv:2108.06478v1 fatcat:fnhy3eo27za7dm72ryooawr36u

A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment [article]

Homagni Saha, Fateme Fotouhif, Qisai Liu, Soumik Sarkar
2021 arXiv   pre-print
In this paper we propose a new framework - MoViLan (Modular Vision and Language) for execution of visually grounded natural language instructions for day to day indoor household tasks.  ...  We propose a modular approach to deal with the combined navigation and object interaction problem without the need for strictly aligned vision and language training data (e.g., in the form of expert demonstrated  ...  Introduction Vision language navigation received a lot of attention recently as its inherent cross modal nature in anchoring natural language commands to visual perception is highly relevant for practical  ... 
arXiv:2101.07891v1 fatcat:zlmzxormu5emtlctuaklxbfmoq

Ego4D: Around the World in 3,000 Hours of Egocentric Video [article]

Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan (+73 others)
2022 arXiv   pre-print
Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation  ...  We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.  ...  Acknowledgements We gratefully acknowledge the following colleagues for valuable discussions and support of our project: Aaron Adcock, Andrew Allen, Behrouz Behmardi, Serge Belongie, Mark Broyles, Xiao  ... 
arXiv:2110.07058v3 fatcat:lgh27km63nhcdcpkvbr2qarsru

Closed-loop Bayesian Semantic Data Fusion for Collaborative Human-Autonomy Target Search [article]

Luke Burks, Ian Loefgren, Luke Barbier, Jeremy Muesing, Jamison McGinley, Sousheel Vunnam, Nisar Ahmed
2018 arXiv   pre-print
as semantic natural language observations that can be specifically requested from human sensors.  ...  The approach is demonstrated and validated with a real human-robot team engaged in dynamic indoor target search and capture scenarios on a custom testbed.  ...  natural language observations that can be requested from human sensors.  ... 
arXiv:1806.00727v1 fatcat:vrcjppnsxbbvrk4houlwdvsm2u

Why? Why not? When? Visual Explanations of Agent Behavior in Reinforcement Learning [article]

Aditi Mishra, Utkarsh Soni, Jinbin Huang, Chris Bryan
2021 arXiv   pre-print
We find that PolicyExplainer promotes trust and understanding of agent decisions better than a state-of-the-art text-based explanation approach.  ...  Our results help demonstrate how visualization-based approaches can be leveraged to decode the behavior of autonomous RL agents, particularly for RL non-experts.  ...  natural language generation technique [15] .  ... 
arXiv:2104.02818v2 fatcat:cvaxyrbpivfxvnu2ym5kyz7qp4

An intelligent fuzzy object-oriented database framework for video database applications

Nezihe Burcu Ozgur, Murat Koyuncu, Adnan Yazici
2009 Fuzzy sets and systems (Print)  
Moreover, it allows (fuzzy) semantic, temporal, (fuzzy) spatial, hierarchical, regional and trajectory queries, based on the video data model.  ...  UML (Unified Modeling Language) is utilized and extended to represent uncertain information along with video specific properties at the conceptual level.  ...  Among the previous approaches handling uncertain information in databases and knowledge bases, we base our study on the IFOOD architecture proposed in [30] .  ... 
doi:10.1016/j.fss.2009.02.017 fatcat:ys6jbz3bkvcfbiylo6vqld5d6m

Knowledge Processing for Cognitive Robots

Moritz Tenorth, Dominik Jain, Michael Beetz
2010 Künstliche Intelligenz  
In this article, we discuss some of these challenges and our approaches to solving them.  ...  When applied to robot control, such methods allow to write more general and flexible control programs and enable reasoning about the robot's observations, the actions involved in a task, action parameters  ...  Our approach: Verbal Communication and Knowledge-based Action Interpretation For understanding natural language, we have the techniques that are described in [25] in the context of importing task instructions  ... 
doi:10.1007/s13218-010-0044-0 fatcat:pur4jvsmfbbt7kznsqefqdxxiq

Interpretation of complex situations in a semantic-based surveillance framework

Carles Fernández, Pau Baiget, Xavier Roca, Jordi Gonzàlez
2008 Signal processing. Image communication  
, which leads to the conception of a situation-based ontology; (iii) the use of situational analysis for content detection and a progressive interpretation of semantically rich scenes, by managing incomplete  ...  Experimental results are provided to show the feasibility of the proposed approach.  ...  Jordi Gonzà lez also acknowledges the support of a Juan de la Cierva Postdoctoral fellowship from the Spanish MEC.  ... 
doi:10.1016/j.image.2008.04.015 fatcat:7hun6y3evndodcfcqvic2zszvy
« Previous Showing results 1 — 15 out of 4,714 results