Filters








398,766 Hits in 4.6 sec

Discovery of activity patterns using topic models

Tâm Huynh, Mario Fritz, Bernt Schiele
<span title="">2008</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tbl7svy7dzb65af4vqu34wmt7i" style="color: black;">Proceedings of the 10th international conference on Ubiquitous computing - UbiComp &#39;08</a> </i> &nbsp;
The use of topic models enables the automatic discovery of such patterns in a user's daily routine.  ...  In this work we propose a novel method to recognize daily routines as a probabilistic combination of activity patterns.  ...  DISCOVERY OF DAILY ROUTINES BASED ON ACTIVITY RECOGNITION As discussed earlier, the proposed approach using topic models can be used to model daily routines based on wearable sensors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1409635.1409638">doi:10.1145/1409635.1409638</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/huc/HuynhFS08.html">dblp:conf/huc/HuynhFS08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q66kljh2i5hsrnsmxp73kneq6m">fatcat:q66kljh2i5hsrnsmxp73kneq6m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170809151652/http://www.eecs.wsu.edu/~holder/courses/CptS570/fall10/papers/HuynhUbiComp08.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d4/20/d420b7d474c9873249aa2896b529183d2222790c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1409635.1409638"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Recognizing activities of daily living from patterns and extraction of web knowledge

Isibor Kennedy Ihianle, Usman Naeem, Abdel-Rahman Tawil, Muhammad Awais Azam
<span title="">2016</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/tbl7svy7dzb65af4vqu34wmt7i" style="color: black;">Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing Adjunct - UbiComp &#39;16</a> </i> &nbsp;
in order to build dynamic activity models based on the objects used to perform the activity.  ...  Current activity recognition approaches are also based on knowledge driven techniques that require extensive modelling of the activities that needs to be inferred.  ...  We use these to build the activity model for recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2968219.2968440">doi:10.1145/2968219.2968440</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/huc/IhianleNTA16.html">dblp:conf/huc/IhianleNTA16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h667artmsjb7hhy265mv2av6xi">fatcat:h667artmsjb7hhy265mv2av6xi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180720211138/http://roar.uel.ac.uk/5890/1/Recognizing%20Activities%20of%20Daily%20Living-%20Usman%20Naeem.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/99/ec/99eccad68afbf34d1b3d15e32603327e5539ea17.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2968219.2968440"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Dominant Codewords Selection with Topic Model for Action Recognition [article]

Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic
<span title="2016-05-01">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a framework for recognizing human activities that uses only in-topic dominant codewords and a mixture of intertopic vectors.  ...  In LDA topic modeling, action videos (documents) are represented by a bag-of-words (input from a dictionary), and these are based on improved dense trajectories.  ...  This model is a simple but effective way to create a dominant vector for action recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00324v1">arXiv:1605.00324v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jvwcorpb2fcbpmzp6uxcemb4bm">fatcat:jvwcorpb2fcbpmzp6uxcemb4bm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014113935/https://arxiv.org/pdf/1605.00324v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1e/48/1e489690c811d1eda06eccbb4c9461dea41f9e64.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1605.00324v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Recognizing Actions from Different Views by Topic Transfer

<span title="2017-04-30">2017</span> <i title="Korean Society for Internet Information (KSII)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hupfbobgkvepdnt5g32qxkypsy" style="color: black;">KSII Transactions on Internet and Information Systems</a> </i> &nbsp;
Our approach is characterized by two aspects: 1) We propose a unsupervised topic transfer model (TTM) to model two view-dependent vocabularies, where the original bag of visual words (BoVW) representation  ...  The higher-level BoT features, which can be shared across views, can connect action models for different views. 2) Our features make it possible to obtain a discriminative model of action under one view  ...  First, we clustered the shared activities to 1000 clusters using k-means clustering on the descriptive features to form a codebook.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2017.04.015">doi:10.3837/tiis.2017.04.015</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ycmikdli4fggvomwq6enrrcsrm">fatcat:ycmikdli4fggvomwq6enrrcsrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220226185732/http://itiis.org/digital-library/manuscript/file/21428/TIISVol11No4-15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4c/81/4c81857796edc086fd81161a41204c997ff30b3a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3837/tiis.2017.04.015"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Recognition of Activities of Daily Living from Topic Model

Isibor Kennedy Ihianle, Usman Naeem, Abdel-Rahman Tawil
<span title="">2016</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cx3f4s3qmfe6bg4qvuy2cxezyu" style="color: black;">Procedia Computer Science</a> </i> &nbsp;
In this paper, we propose a topic model process of discovering activities and activity-object patterns from the interactions of low level state-change sensors.  ...  We also develop a recognition and segmentation algorithm to recognise activities and recognise activity boundaries.  ...  Conclusion In this paper, we presented ADL recognition from sensor data using the PLSA topic model. We used the PLSA to discover activity topics and activity-object patterns.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.procs.2016.09.007">doi:10.1016/j.procs.2016.09.007</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ducjjyhvbjdm3n6sghgbn6cobu">fatcat:ducjjyhvbjdm3n6sghgbn6cobu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190318083557/https://core.ac.uk/download/pdf/82156840.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/65/bf/65bf7e2a7351ca12568497590b9b62538c09b33b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.procs.2016.09.007"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Action Recognition Using Topic Models [chapter]

Xiaogang Wang
<span title="">2011</span> <i title="Springer London"> Visual Analysis of Humans </i> &nbsp;
In this book chapter, we will introduce approaches of using topic models for action recognition. Topic models were originally developed in language processing.  ...  In recent years, they were applied to action recognition and other computer vision problems, and achieved great success. Topic models are unsupervised.  ...  In some approaches, objects (or their parts) were first detected, tracked and classified into different classes. Their tracks were used as features to model activities [21, 22, 23] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-85729-997-0_16">doi:10.1007/978-0-85729-997-0_16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zehfiq2arjdrrgtvgdkp4njyj4">fatcat:zehfiq2arjdrrgtvgdkp4njyj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160909154531/http://www.ee.cuhk.edu.hk:80/~xgwang/papers/topicmodel.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/61/9d/619d3b4d35f32cd910d80bfe191279a657ccc9ee.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-0-85729-997-0_16"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Dominant Codewords Selection with Topic Model for Action Recognition

Hirokatsu Kataoka, Kenji Iwata, Yutaka Satoh, Masaki Hayashi, Yoshimitsu Aoki, Slobodan Ilic
<span title="">2016</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)</a> </i> &nbsp;
In this paper, we propose a framework for recognizing human activities that uses only in-topic dominant codewords and a mixture of intertopic vectors.  ...  In LDA topic modeling, action videos (documents) are represented by a bag-of-words (input from a dictionary), and these are based on improved dense trajectories ([18]).  ...  This model is a simple but effective way to create a dominant vector for action recognition.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2016.101">doi:10.1109/cvprw.2016.101</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/KataokaISHAI16.html">dblp:conf/cvpr/KataokaISHAI16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/te5ndoqkyvftfkzryg5bgrm5l4">fatcat:te5ndoqkyvftfkzryg5bgrm5l4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170828170212/http://www.cv-foundation.org:80/openaccess/content_cvpr_2016_workshops/w18/papers/Kataokai_Dominant_Codewords_Selection_CVPR_2016_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/82/76/82765c2abbe4c20a25e71ec6aa5e65a710636486.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvprw.2016.101"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Mining complex activities in the wild via a single smartphone accelerometer

Angshu Rai, Zhixian Yan, Dipanjan Chakraborty, Tri Kurniawan Wijaya, Karl Aberer
<span title="">2012</span> <i title="ACM Press"> Proceedings of the Sixth International Workshop on Knowledge Discovery from Sensor Data - SensorKDD &#39;12 </i> &nbsp;
Recently, a new and challenging problem is to investigate recognition accuracy of complex activities in the wild using the smartphone.  ...  Complex activity recognition is an active area of interest amongst sensing and knowledge mining community today.  ...  Topic models have successfully been utilized in several applications including activity recognition [10, 2] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2350182.2350187">doi:10.1145/2350182.2350187</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lvdosnvljjfd5jdmmf3jszxjti">fatcat:lvdosnvljjfd5jdmmf3jszxjti</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170818180555/https://infoscience.epfl.ch/record/183140/files/p43-rai.pdf?version=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a6/6e/a66e1fab955ce0a87224934116c06b2b061148cf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2350182.2350187"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Unsupervised vocabulary selection for real-time speech recognition of lectures

Paul Maergner, Alex Waibel, Ian Lane
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rc5jnc4ldvhs3dswicq5wk3vsq" style="color: black;">2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</a> </i> &nbsp;
In this work, we propose a novel method for vocabulary selection to automatically adapt automatic speech recognition systems to the diverse topics that occur in educational and scientific lectures.  ...  using a combination of word features.  ...  Acknowledgments We would like to thank Sebastian Stüker and Kevin Kilgour for providing the Baseline German speech recognition system used in this work as well as their technical expertise throughout the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2012.6288899">doi:10.1109/icassp.2012.6288899</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icassp/MaergnerWL12.html">dblp:conf/icassp/MaergnerWL12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/373ex6p4hrdezp4icj3sl2rpfu">fatcat:373ex6p4hrdezp4icj3sl2rpfu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829000232/http://www.cs.cmu.edu/~ianlane/publications/2011_Maergner_ICASSP.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/42/24/422484690bb732f681e56c4b61a0d7af2296ee31.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2012.6288899"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Time-sensitive topic models for action recognition in videos

Romain Tavenard, Remi Emonet, Jean-Marc Odobez
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2013 IEEE International Conference on Image Processing</a> </i> &nbsp;
We propose to use timesensitive probabilistic topic models and we extend them for the context of supervised learning. Our time-sensitive approach is compared to both PLSA and Bag-of-Words.  ...  Our approach is shown to both capture semantics from data and yield classification performance comparable to other methods, outperforming them when the amount of training data is low.  ...  Still, overall the temporal modeling and segmentation of activities using topic models was seldom addressed until recently.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2013.6738615">doi:10.1109/icip.2013.6738615</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/TavenardEO13.html">dblp:conf/icip/TavenardEO13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/exsbvglzavh6jj2zujfc3d3d4y">fatcat:exsbvglzavh6jj2zujfc3d3d4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170921210327/http://www.idiap.ch/~odobez/publications/TavenardEmonetOdobez-ICIP-2013.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/55/67/5567593c83eb3a8d523b60e0f304dc0133ff2ee9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2013.6738615"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Human Activity Recognition and Pattern Discovery

Eunju Kim, Sumi Helal, Diane Cook
<span title="">2010</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/c6iy2woaknguto5xgrekwb5ysq" style="color: black;">IEEE pervasive computing</a> </i> &nbsp;
In the topic model approach to activity pattern discovery [4] , activity patterns are recognized in a fashion similar to how topics can be pulled from a document using a bagof-words approach.  ...  Therefore, an activity recognition researcher builds a highlevel conceptual model first, and then implements the model by building a suitable pervasive system.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mprv.2010.7">doi:10.1109/mprv.2010.7</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/21258659">pmid:21258659</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3023457/">pmcid:PMC3023457</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5qca2kbzbneptl2457ouduhabi">fatcat:5qca2kbzbneptl2457ouduhabi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20100531212744/http://www.eecs.wsu.edu/~cook/pubs/pc10.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cc/a3/cca38902ebf0035c27a7e363b5a17b2f11e457fa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mprv.2010.7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3023457" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment

Isibor Ihianle, Usman Naeem, Syed Islam, Abdel-Rahman Tawil
<span title="2018-01-13">2018</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/x7fwifzpv5bljlhjn7g4qri7ni" style="color: black;">Informatics</a> </i> &nbsp;
This paper presents a hybrid framework for automatic consumption of sensor data and associating object usage to routine activities using Latent Dirichlet Allocation (LDA) topic modelling.  ...  Modelling activities from such information can lead to incorrect recognition of particular routine activities resulting in possible failure to detect abnormal activity trends.  ...  Our approached also aims to use this process to determine the number of activities topics which is a measure of the optimal number of clusters.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/informatics5010006">doi:10.3390/informatics5010006</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dp5mbujy4ja2vm3pvgea3sdhg4">fatcat:dp5mbujy4ja2vm3pvgea3sdhg4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190216023124/http://pdfs.semanticscholar.org/0000/5167ed23b55c962632576e666cb3d0d81c30.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/00/00005167ed23b55c962632576e666cb3d0d81c30.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/informatics5010006"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Human Activity Clustering for Online Anomaly Detection

Xudong Zhu, Zhijing Liu, Juehui Zhang
<span title="2011-06-03">2011</span> <i title="International Academy Publishing (IAP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3uo3zcmrgvgspdzqe6w6sjoezq" style="color: black;">Journal of Computers</a> </i> &nbsp;
of activities is discovered through a novel clustering algorithm with unsupervised model selection. 3) A runtime accumulative anomaly measure is introduced to detect abnormal activities, whereas normal  ...  Experimental results demonstrate the effectiveness and robustness of our approach using noisy and sparse datasets collected from a real surveillance scenario.  ...  This is different from most previous approaches such as [1] , [2] , [3] that tries to model the full dynamics of activity structures using sophisticated probabilistic models (e.g., hidden Markov models  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4304/jcp.6.6.1071-1079">doi:10.4304/jcp.6.6.1071-1079</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m7jtw33qezdchfx56z5xv2teay">fatcat:m7jtw33qezdchfx56z5xv2teay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20151026115141/http://ojs.academypublisher.com:80/index.php/jcp/article/viewFile/060610711079/3103" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1f/d3/1fd3c432998225250b16dd417c436ecf3a85212d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.4304/jcp.6.6.1071-1079"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

BAG OF WORDS APPROACH AND DOCUMENT-TOPIC MODELING FOR HUMAN ACTIVITY RECOGNITION FROM VIDEOS

Janson Hendryli
<span title="2017-05-12">2017</span> <i title="Universitas Tarumanagara"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hzc6p3cddfexloxi4rupqdnol4" style="color: black;">Jurnal Muara Sains, Teknologi, Kedokteran dan Ilmu Kesehatan</a> </i> &nbsp;
In this paper, an approach inspired by a popular text document, namely the bag of words and document topic modeling, is explored.  ...  The NMF achieved higher F1-score than the LDA when both SVM and logistic regression is used as the classifier.Keywords: human activity recognition, bag of words, document topic modeling  ...  This paper explores an approach to activity recognition from a video using techniques widely used on text document: the bag of words and document topic modeling.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24912/jmstkik.v1i1.433">doi:10.24912/jmstkik.v1i1.433</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qaksguhpgjhylkxfmjf7bygfhe">fatcat:qaksguhpgjhylkxfmjf7bygfhe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220312040130/https://journal.untar.ac.id/index.php/jmistki/article/download/433/378" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9d/aa/9daa2b59f505aa704f0a059507cac8925ca82044.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24912/jmstkik.v1i1.433"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Watch-n-patch: Unsupervised understanding of actions and relations

Chenxia Wu, Jiemi Zhang, Silvio Savarese, Ashutosh Saxena
<span title="">2015</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
It allows us to model long-range action relations that commonly exist in the complex activity, which is challenging to capture in the previous works.  ...  We apply our model to unsupervised action segmentation and recognition, and also to a novel application that detects forgotten actions, which we call action patching.  ...  We first show that our model is able to learn meaningful representations from the unlabeled activity videos. We use the model to temporally segment videos to segments assigned with action-topics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7299065">doi:10.1109/cvpr.2015.7299065</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WuZSS15.html">dblp:conf/cvpr/WuZSS15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u3xyhbrml5eqjnt7fzotgznlvi">fatcat:u3xyhbrml5eqjnt7fzotgznlvi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20160328230042/http://jiemizhang.org/paper/cvpr15.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6b/2f/6b2f7b009ba3adbd2fedc6f01bc67f58f1b931e5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2015.7299065"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 398,766 results