Filters








723 Hits in 4.8 sec

VideoGraph: Recognizing Minutes-Long Human Activities in Videos [article]

Noureldien Hussein, Efstratios Gavves, Arnold W.M. Smeulders
2019 arXiv   pre-print
Besides, we demonstrate that VideoGraph is able to learn the temporal structure of human activities in minutes-long videos.  ...  We propose VideoGraph, a method to achieve the best of two worlds: represent minutes-long human activities and learn their underlying temporal structure.  ...  The goal of this paper is to recognize minutes-long human activities as defined by [1] , also referred to as complex actions in [2] .  ... 
arXiv:1905.05143v2 fatcat:fq6tnbjukfa2hhvdritzeb7ope

Videographic geographies: Using digital video for geographic research

Bradley L. Garrett
2010 Progress in Human Geography  
This article is a review of the ways in which human geography has engaged with film and video.  ...  and an increase in digital publication to create what we might call videographic geographies.  ...  The session held on visual methodologies in January 2009 seeded much of my thought on the distinctions between photography and video as 'visual methods'.  ... 
doi:10.1177/0309132510388337 fatcat:bnele5govrhxtjnf6dfdbog7za

Video Activity Recognition with Varying Rhythms

Bulent Ayhan, Chiman Kwan, Bence Budavari, Jude Larkin, David Gribben, Baoxin Li
2020 IEEE Access  
Other than the difficulty in recognizing activities in long videos, one other essential challenge is the varying activity rhythms. The rhythm of sub-actions in an activity can differ in nature.  ...  The edges in the graph are considered to represent the temporal relationship between the latent concepts. VideoGraph is noted to model human activities for up-to thirty-minute videos [34] .  ... 
doi:10.1109/access.2020.3033190 fatcat:2ucgezqwyjh73gmhjwro34drd4

Automating lecture capture and broadcast: technology and videography

Yong Rui, Anoop Gupta, Jonathan Grudin, Liwei He
2004 Multimedia Systems  
The aesthetic component comprises the rules and idioms that human videographers follow to make a video visually engaging, which guide hardware placement and software algorithms.  ...  We report a user study and a detailed set of video-production rules obtained from professional videographers who critiqued the system, which has been deployed in our organization for two years.  ...  The authors would like to thank Qiong Liu for help in building the first prototype, Jim Crawford and Dave Crosier for help in deploying the system in the MSR lecture room, JJ Cadiz for help with the user  ... 
doi:10.1007/s00530-004-0132-9 fatcat:uanlv5neqvcvdky7uhxynjtsdu

Videography for telepresentations

Yong Rui, Anoop Gupta, Jonathan Grudin
2003 Proceedings of the conference on Human factors in computing systems - CHI '03  
., video cameras) and associated software (e.g., speaker-tracking). The aesthetic component embodies the rules and idioms that human videographers follow to make a video visually engaging.  ...  We present a lecture room automation system and a substantial number of new video-production rules obtained from professional videographers who critiqued it.  ...  viewers, although in practice they allow quite long (up to a few minutes) medium-close shots of the lecturer.  ... 
doi:10.1145/642611.642691 dblp:conf/chi/RuiGG03 fatcat:o36q2dit3jfexhijs2qw7g6say

Videography for telepresentations

Yong Rui, Anoop Gupta, Jonathan Grudin
2003 Proceedings of the conference on Human factors in computing systems - CHI '03  
., video cameras) and associated software (e.g., speaker-tracking). The aesthetic component embodies the rules and idioms that human videographers follow to make a video visually engaging.  ...  We present a lecture room automation system and a substantial number of new video-production rules obtained from professional videographers who critiqued it.  ...  viewers, although in practice they allow quite long (up to a few minutes) medium-close shots of the lecturer.  ... 
doi:10.1145/642689.642691 fatcat:ocdfd655dnhplp6rl5f2irswoa

Shifting Focus: A Videographic Inquiry of Hope and Unplanned Pregnancy

J. Lauren Johnson
2013
In a medium-sized Western Canadian city, I engaged in a videographic inquiry (an arts-based qualitative research study) to address the following questions: (a) how is unplanned pregnancy described by women  ...  ourselves through the audio-visual medium of video.  ...  The task of transcribing our creative videos was daunting, not because our videos were long or complex-in fact, they ranged in length from 3 to 5 minutes, which is quite (2000) developed a two-column  ... 
doi:10.7939/r3071n fatcat:wm34ntlllvcwrml6kx65zcylq4

Companion for the videography 'Monstrous Organizing—The Dubstep Electronic Music Scene'

Joel Hietanen, Joonas Rokka
2017 Organization  
In doing so, we argue that video-based organizing of research activities can be seen as 'monstrous', an entire emergent mode of aesthetic storytelling that comes into being not in 'capturing' or 'recording  ...  To advance this perspective and to inspire future research, we present our videography (length 30 minutes) that integrates various 'expressive' elements in montage form.  ...  active encounter with it.  ... 
doi:10.1177/1350508417738572 fatcat:jp3ejqdnyvgi5pkex7jjzi5kea

Extracting physiological information in experimental biology via Eulerian video magnification

Henrik Lauridsen, Selina Gonzales, Daniela Hedwig, Kathryn L. Perrin, Catherine J. A. Williams, Peter H. Wrege, Mads F. Bertelsen, Michael Pedersen, Jonathan T. Butcher
2019 BMC Biology  
Eulerian video magnification allows the enhancement of such signals to enable their detection.  ...  The purpose of this study is to demonstrate how signals relevant to experimental physiology can be extracted from non-contact videographic material of animals.  ...  The amphibian dorsal aorta (DA) originates from the efferent gill arteries and runs in the caudal direction along the long axis of the animal ( Eulerian video magnification of non-dedicated videographic  ... 
doi:10.1186/s12915-019-0716-7 pmid:31831016 pmcid:PMC6907275 fatcat:zhvui6k3q5eltishzrbr4ydese

Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos [article]

Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos
2021 arXiv   pre-print
We propose a two-stream framework, which exploits semantic and temporal hierarchies to recognize top-level tasks in instructional videos.  ...  This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training.  ...  Task Classification Results on 10 Classes of the Breakfast Dataset Timception [18] , VideoGraph [19] and RhyRNN [54] are the latest state-of-the-art methods to classify tasks in minutes-long videos  ... 
arXiv:2110.05697v1 fatcat:nrxass56fvapfovylsyeatd72e

Live-action Communication Design: A Technical How-To Video Case Study

Per Erik Eriksson, Yvonne Eriksson
2018 Technical Communication Quarterly  
In the study, four key liveaction video affordances are identified: verifiability, comparability, recordability, and visibility.  ...  The identification of these affordances when related to the users' assessments resulted in several design implementations that would warrant sought-for communication efficacies.  ...  Comparability affords the activation of humans' mirror neurons.  ... 
doi:10.1080/10572252.2018.1528388 fatcat:gdtnzplrkzgx7b2n7fziiktf5i

Changing times for scholarly communication: The case of the academic research video and the online video journal

Fernando Canet
2019 El Profesional de la Informacion  
Although the use of video could be a worthwhile option for any field of study in which videographic practice would facilitate the communication of the research findings and thus enhance our understanding  ...  For this reason and because the number of media scholars communicating their research outputs in videos has increased in recent years to the extent of becoming a new trend, I focus on the exploration of  ...  We should recognize that for a videographic work to be considered an academic research video, it must meet the standards of the academic world.  ... 
doi:10.3145/epi.2019.jul.06 fatcat:tv2namno55etrgofu3wc3i2hoe

Experiences in Personal Lecture Video Capture

Surendar Chandra
2011 IEEE Transactions on Learning Technologies  
Some universities use trained videographers. Though they produce excellent videos, these efforts are expensive. Several research projects automate the video capture.  ...  Based on our experience in capturing lecture videos over three and a half years, we describe the technical challenges encountered in this endeavor.  ...  Supported in part by the U.S. National Science Foundation (CNS-0447671).  ... 
doi:10.1109/tlt.2011.10 fatcat:ofgvufiqtvad3gobcatgpljvdu

Intimate Clips: Sealskin Sewing, Digital Archives and the Mittimatalik Arnait Miqsuqtuit Collective

Nancy Wachowich
2018 Museum Anthropology Review  
, videographers, and sealskin seamstresses in the Canadian Eastern High Arctic Inuit settlement of Mittimatalik (Pond Inlet).  ...  I illustrate the documentation work of our Mittimatalik Arnait Miqsuqtuit Collective, situating it in the new media landscapes that have developed in the Canadian Arctic, and draw on case studies to challenge  ...  The younger women videographers often shared in the task.  ... 
doi:10.14434/mar.v12i2.22478 fatcat:sdxzggq54nd4vbc3v2erfxndnm

Virtual videography

Rachel Heck, Michael Wallick, Michael Gleicher
2007 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
In this paper, we offer a new way to create lecture videos that retain many of the advantages of well-composed recordings without the cost and intrusion of a video production crew.  ...  The system uses the data recorded by unattended video cameras and microphones to produce a new edited video as an offline post-process.  ...  Acknowledgements This work was supported in part by NSF grants CCR-9984506, IIS-0097456, and IIS-0416284. Michael Wallick is funded by a Microsoft Research Graduate Fellowship.  ... 
doi:10.1145/1198302.1198306 fatcat:p5e4uxiv7vdxjhau6mgegp6p3i
« Previous Showing results 1 — 15 out of 723 results