Filters








11,910 Hits in 3.2 sec

FASTER Recurrent Networks for Efficient Video Classification [article]

Linchao Zhu, Laura Sevilla-Lara, Du Tran, Matt Feiszli, Yi Yang, Heng Wang
<span title="2019-09-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10x?  ...  In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy.  ...  First, we propose a novel framework for efficient video classification that we call FASTER for Feature Aggregation for Spatio-TEmporal Redundancy (Fig. 1 (b) ).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.04226v2">arXiv:1906.04226v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/45mfn6rmjrc55km56vxbrjbiyu">fatcat:45mfn6rmjrc55km56vxbrjbiyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823080245/https://arxiv.org/pdf/1906.04226v2.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/d7/18/d718baf9187fa5851a9389e5e250d47ba1210e0e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.04226v2" 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>

FASTER Recurrent Networks for Efficient Video Classification

Linchao Zhu, Du Tran, Laura Sevilla-Lara, Yi Yang, Matt Feiszli, Heng Wang
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations.  ...  In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy.  ...  Conclusion In this paper, we propose a novel framework called FASTER for efficient video classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.7012">doi:10.1609/aaai.v34i07.7012</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2xvutspqqffvdmxf2qmjwiwxka">fatcat:2xvutspqqffvdmxf2qmjwiwxka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104163334/https://aaai.org/ojs/index.php/AAAI/article/download/7012/6866" 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/98/33/9833367fe7055d08399db9b04b3f21c324179c52.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i07.7012"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Object-Adaptive LSTM Network for Visual Tracking

Yihan Du, Yan Yan, Si Chen, Yang Hua, Hanzi Wang
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jsl2pgelqja2piczru3a6nqkg4" style="color: black;">2018 24th International Conference on Pattern Recognition (ICPR)</a> </i> &nbsp;
Besides, we adopt simple online updating techniques for computational efficiency (since the L-STM network can dynamically update the recurrent parameters during forward passes).  ...  , which enables our method to operate faster than conventional CNN-based classification tracking methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2018.8545096">doi:10.1109/icpr.2018.8545096</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icpr/Du0CHW18.html">dblp:conf/icpr/Du0CHW18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mn5od3tfhrajnbvt2wiphnoijm">fatcat:mn5od3tfhrajnbvt2wiphnoijm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305112936/https://pureadmin.qub.ac.uk/ws/files/153824535/Object_Adaptive_LSTM_Network_icpr2018.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/ab/b1/abb1cd9f7cfdf712896471bbeaff70e81e0caabe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icpr.2018.8545096"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Video Classification for Video Service Providers : A Survey

Sourav Joshi, Ameya Karhadkar, Niranjan Thatte, Kunwar Chopra, Tanaji Khadtare
<span title="2020-05-01">2020</span> <i title="Technoscience Academy"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cwo66igunvdiplkdqwpqsgzpem" style="color: black;">International Journal of Scientific Research in Computer Science Engineering and Information Technology</a> </i> &nbsp;
Video classification is an important task for archiving digital contents for various video service providers.  ...  Videos being an important source to recognize any activity by the humans, video classification becomes an important and critical job for video service providers.  ...  Long Short Term Memory(LSTM) Recurrent Neural Networks (RNN) models are then used to improve efficiency.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32628/cseit2062109">doi:10.32628/cseit2062109</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wjhj4ksp6nbfjdnniwappgy7km">fatcat:wjhj4ksp6nbfjdnniwappgy7km</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001161414/http://ijsrcseit.com/paper/CSEIT2062109.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/e4/af/e4afa2facb300cc0daeec54a3361499e31a1435b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32628/cseit2062109"> <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>

Semantic video segmentation for autonomous driving [article]

Minh Triet Chau
<span title="2020-10-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While fully convolutional network gives good result, we show that the speed can be halved while preserving the accuracy.  ...  We aim to solve semantic video segmentation in autonomous driving, namely road detection in real time video, using techniques discussed in (Shelhamer et al., 2016a).  ...  Spatiotemporal filtering For video classification, networks can be integrated over time by fusion of frame features (Karpathy et al., 2014) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.15250v1">arXiv:2010.15250v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mst43gqub5fd5ch4blrowxdmhy">fatcat:mst43gqub5fd5ch4blrowxdmhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201031032214/https://arxiv.org/pdf/2010.15250v1.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/19/fc/19fce41ffcf5bc293749444eb9ebf788e99bb77b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.15250v1" 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>

Recurrent Fully Convolutional Networks for Video Segmentation [article]

Sepehr Valipour, Mennatullah Siam, Martin Jagersand, Nilanjan Ray
<span title="2016-10-31">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
While convolutional neural networks have shown to perform well on single image segmentation, to our knowledge, no study has been been done on leveraging recurrent gated architectures for video segmentation  ...  Accordingly, we propose a novel method for online segmentation of video sequences that incorporates temporal data.  ...  Small variations of this method are used for context classification on one million youtube videos [12] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.00487v3">arXiv:1606.00487v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5uh63wn37rbshk6nriec3iu23y">fatcat:5uh63wn37rbshk6nriec3iu23y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902161640/https://arxiv.org/pdf/1606.00487v3.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/3d/04/3d04bc62a30f4d6329db2099cc318cb89974a872.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.00487v3" 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>

ECO: Efficient Convolutional Network for Online Video Understanding [chapter]

Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
span several seconds. (2) While there are local methods with fast perframe processing, the processing of the whole video is not efficient and hampers fast video retrieval or online classification of long-term  ...  In this paper, we introduce a network architecture 1 that takes longterm content into account and enables fast per-video processing at the same time.  ...  Acknowledgements We thank Facebook for providing us a GPU server with Tesla P100 processors for this research work.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01216-8_43">doi:10.1007/978-3-030-01216-8_43</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bjwjwxf6j5c2piomvho7y7hssa">fatcat:bjwjwxf6j5c2piomvho7y7hssa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180922005831/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Mohammadreza_Zolfaghari_ECO_Efficient_Convolutional_ECCV_2018_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/29/33/2933b26f88722e6f186ce8d0b5f8945e510b939c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01216-8_43"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

NeXtVLAD: An Efficient Neural Network to Aggregate Frame-Level Features for Large-Scale Video Classification [chapter]

Rongcheng Lin, Jing Xiao, Jianping Fan
<span title="">2019</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
This paper introduces a fast and efficient network architecture, NeXtVLAD, to aggregate frame-level features into a compact feature vector for large-scale video classification.  ...  This NeXtVLAD approach turns out to be both effective and parameter efficient in aggregating temporal information.  ...  (c) Recurrent Spatial Networks [15] [22] , which applies Recurrent Neural Networks, including LSTM or GRU to model temporal information in videos.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11018-5_19">doi:10.1007/978-3-030-11018-5_19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3nbhqmpuhrdg3ahov5inv7fzim">fatcat:3nbhqmpuhrdg3ahov5inv7fzim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819011216/http://openaccess.thecvf.com:80/content_ECCVW_2018/papers/11132/Lin_NeXtVLAD_An_Efficient_Neural_Network_to_Aggregate_Frame-level_Features_for_ECCVW_2018_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/91/95/919548553251d5cf92a2cb50e87d29b862613bb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-11018-5_19"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

NeXtVLAD: An Efficient Neural Network to Aggregate Frame-level Features for Large-scale Video Classification [article]

Rongcheng Lin, Jing Xiao, Jianping Fan
<span title="2018-11-12">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper introduces a fast and efficient network architecture, NeXtVLAD, to aggregate frame-level features into a compact feature vector for large-scale video classification.  ...  This NeXtVLAD approach turns out to be both effective and parameter efficient in aggregating temporal information.  ...  (c) Recurrent Spatial Networks [15] [22] , which applies Recurrent Neural Networks, including LSTM or GRU to model temporal information in videos.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.05014v1">arXiv:1811.05014v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7rgwofrxsfbprphmebngtrgs6y">fatcat:7rgwofrxsfbprphmebngtrgs6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911160613/https://arxiv.org/pdf/1811.05014v1.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/07/a0/07a05173660d0c0796b0590fb3874486b1b9f1fe.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.05014v1" 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>

Comprehensive Analysis of Forest Fire Detection using Deep Learning Models and Conventional Machine Learning Algorithms

Süha Berk KUKUK, Zeynep Hilal KİLİMCİ
<span title="2021-07-06">2021</span> <i title="International Journal of Computational and Experimental Science and Engineering (IJCESEN)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u7qqmb3syrgjfod7iafycomxly" style="color: black;">International Journal of Computational and Experimental Science and Engineering</a> </i> &nbsp;
Experiment results demonstrate that convolutional neural networks outperform other methods with 99.32% of accuracy result.  ...  Fire detection-based image analysis have advantages such as usage on wide open areas, the possibility for operator to visually confirm presence, intensity and the size of the hazards, lower cost for installation  ...  Faster Recurrent-Convolutional Neural Network (Faster R-CNN) Faster R-CNN is model of R-CNN technology. The model is improved by Girshick et al [22] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22399/ijcesen.950045">doi:10.22399/ijcesen.950045</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mxszvnhh2jdy7hzf5wcn4eql5i">fatcat:mxszvnhh2jdy7hzf5wcn4eql5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210804025111/https://dergipark.org.tr/en/download/article-file/1815116" 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/77/25/7725feaae400c80c24c8014487aaf82ddeaa2ac2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.22399/ijcesen.950045"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Watching a Small Portion could be as Good as Watching All: Towards Efficient Video Classification

Hehe Fan, Zhongwen Xu, Linchao Zhu, Chenggang Yan, Jianjun Ge, Yi Yang
<span title="">2018</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
We aim to significantly reduce the computational cost for classification of temporally untrimmed videos while retaining similar accuracy.  ...  We incorporate an adaptive stop network to measure confidence score and generate timely trigger to stop the agent watching videos, which improves efficiency without loss of accuracy.  ...  Generally, a large μ can improve the efficiency for video classification but may damage the accuracy.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/98">doi:10.24963/ijcai.2018/98</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/FanXZYGY18.html">dblp:conf/ijcai/FanXZYGY18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pyi7e6xkovearosxt3cc5z3pdu">fatcat:pyi7e6xkovearosxt3cc5z3pdu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190429124155/https://www.ijcai.org/proceedings/2018/0098.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/3d/a5/3da5de9c29e007ff2bca0cc9152bcf4dd83fe7a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/98"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

2D CNN and Gated Recurrent Network for Dynamic Hand Gesture Recognition with A Fusion of RGB-D and Optical Flow Data

<span title="2019-08-10">2019</span> <i title="Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cj3bm7tgcffurfop7xzswxuks4" style="color: black;">VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE</a> </i> &nbsp;
We have also added a newest Gated recurrent network for temporal recognition of frame and minimize training time with improved accuracy.  ...  Therefore, in this paper, we have presented an effective 2D CNN architecture with three stream networks and advances weighted feature fusion scheme with the gated recurrent network for dynamic hand gesture  ...  The processed features are merged and give input to gated recurrent network for many-to-one classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijitee.j9185.0881019">doi:10.35940/ijitee.j9185.0881019</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kqx3cymemjb3lkt2ix7lmndogm">fatcat:kqx3cymemjb3lkt2ix7lmndogm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220121004709/https://www.ijitee.org/wp-content/uploads/papers/v8i10/J91850881019.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/fe/b0/feb027605c59b350a5cfdfb6321e33e651ce2949.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.35940/ijitee.j9185.0881019"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Recurrent Residual Module for Fast Inference in Videos [article]

Bowen Pan, Wuwei Lin, Xiaolin Fang, Chaoqin Huang, Bolei Zhou, Cewu Lu
<span title="2018-02-27">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a framework called Recurrent Residual Module (RRM) to accelerate the CNN inference for video recognition tasks.  ...  than the original dense models using the efficient inference engine), and impressively 9x acceleration on some binary networks such as XNOR-Nets (thus 500x faster than the original model).  ...  Recently, deep convolutional neural networks (CNNs) advanced different tasks of video understanding, such as video classification [33, 59, 58, 60] , video pose estimation [16, 5] , and video object detection  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09723v1">arXiv:1802.09723v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lap3sjz62rcibptwvphgq3bq2y">fatcat:lap3sjz62rcibptwvphgq3bq2y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930191900/https://arxiv.org/pdf/1802.09723v1.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/2b/a5/2ba5b1996e59a7846a7191f79eda172d85bfe7b5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09723v1" 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>

Sports Intelligent Assistance System Based on Deep Learning

Boyin Wu, Le Sun
<span title="2021-11-19">2021</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fw4azkpu65d2thmrwfkoawyxse" style="color: black;">Scientific Programming</a> </i> &nbsp;
Second, an expansion plan for the dataset is provided. (3) To address the short duration of action video and the high correlation of image sequence data, we present an action recognition method based on  ...  This paper's primary research is as follows: (1) With an eye on the motion assistance system's application scenarios, the network topology and implementation details of the two-stage Faster R-CNN and the  ...  Recurrent neural networks and convolutional neural networks are being combined to address the demanding problem of processing video sequences [6] [7] [8] [9] [10] [11] [12] [13] [14] [15] . is paper studies  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2021/3481469">doi:10.1155/2021/3481469</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/prhz6okscjhdngzo5gxxgll3ye">fatcat:prhz6okscjhdngzo5gxxgll3ye</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220114135125/https://downloads.hindawi.com/journals/sp/2021/3481469.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/a4/c1/a4c13f89fc31afc131f8ea2381cee52e4431cb6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2021/3481469"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Learnable pooling with Context Gating for video classification [article]

Antoine Miech and Ivan Laptev and Josef Sivic
<span title="2018-03-05">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experimental results show the advantage of both improvements for the task of video classification.  ...  Current methods for video analysis often extract frame-level features using pre-trained convolutional neural networks (CNNs).  ...  valuable discussions as well as the Google team for providing the Youtube-8M Tensorflow Starter Code.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.06905v2">arXiv:1706.06905v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vor3iyta6rh4dlkbcntx3g3cje">fatcat:vor3iyta6rh4dlkbcntx3g3cje</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911082808/https://arxiv.org/pdf/1706.06905v2.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/ff/19/ff19ea564aeb111efcd010e740784f0451d4c49a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.06905v2" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 11,910 results