{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:47:30Z","timestamp":1771955250875,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":58,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:00:00Z","timestamp":1545091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,12,18]]},"DOI":"10.1145\/3293353.3293415","type":"proceedings-article","created":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T22:07:32Z","timestamp":1588630052000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Temporal Cricket Stroke Localization from Untrimmed Highlight Videos"],"prefix":"10.1145","author":[{"given":"Arpan","family":"Gupta","sequence":"first","affiliation":[{"name":"The LNM Institute of Information Technology, Jaipur, Rajasthan"}]},{"given":"Sakthi Balan","family":"M.","sequence":"additional","affiliation":[{"name":"The LNM Institute of Information Technology, Jaipur, Rajasthan"}]}],"member":"320","published-online":{"date-parts":[[2020,5,3]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"YouTube-8M: A Large-Scale Video Classification Benchmark. CoRR abs\/1609.08675","author":"Abu-El-Haija Sami","year":"2016","unstructured":"Sami Abu-El-Haija , Nisarg Kothari , Joonseok Lee , Paul Natsev , George Toderici , Balakrishnan Varadarajan , and Sudheendra Vijayanarasimhan . 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. CoRR abs\/1609.08675 ( 2016 ).arXiv:1609.08675 http:\/\/arxiv.org\/abs\/1609.08675 Sami Abu-El-Haija, Nisarg Kothari, Joonseok Lee, Paul Natsev, George Toderici, Balakrishnan Varadarajan, and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. CoRR abs\/1609.08675 (2016).arXiv:1609.08675 http:\/\/arxiv.org\/abs\/1609.08675"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"e_1_3_2_1_3_1","volume-title":"Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs\/1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs\/1409.0473 ( 2014 ). arXiv:1409.0473 http:\/\/arxiv.org\/abs\/1409.0473 Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural Machine Translation by Jointly Learning to Align and Translate. CoRR abs\/1409.0473 (2014). arXiv:1409.0473 http:\/\/arxiv.org\/abs\/1409.0473"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"e_1_3_2_1_5_1","volume-title":"The OpenCV Library. Dr. Dobb's Journal of Software Tools","author":"Bradski G.","year":"2000","unstructured":"G. Bradski . 2000. The OpenCV Library. Dr. Dobb's Journal of Software Tools ( 2000 ). G. Bradski. 2000. The OpenCV Library. Dr. Dobb's Journal of Software Tools (2000)."},{"key":"e_1_3_2_1_6_1","volume-title":"Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750","author":"Carreira Jo\u00e3o","year":"2017","unstructured":"Jo\u00e3o Carreira and Andrew Zisserman . 2017. Quo Vadis , Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750 ( 2017 ). arXiv:1705.07750 http:\/\/arxiv.org\/abs\/1705.07750 Jo\u00e3o Carreira and Andrew Zisserman. 2017. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset. CoRR abs\/1705.07750 (2017). arXiv:1705.07750 http:\/\/arxiv.org\/abs\/1705.07750"},{"key":"e_1_3_2_1_7_1","volume-title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. CoRR abs\/1409.1259","author":"Cho KyungHyun","year":"2014","unstructured":"KyungHyun Cho , Bart van Merrienboer , Dzmitry Bahdanau , and Yoshua Bengio . 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. CoRR abs\/1409.1259 ( 2014 ). arXiv:1409.1259 http:\/\/arxiv.org\/abs\/1409.1259 KyungHyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio. 2014. On the Properties of Neural Machine Translation: Encoder-Decoder Approaches. CoRR abs\/1409.1259 (2014). arXiv:1409.1259 http:\/\/arxiv.org\/abs\/1409.1259"},{"key":"e_1_3_2_1_8_1","volume-title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. CoRR abs\/1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung , \u00c7aglar G\u00fcl\u00e7ehre , KyungHyun Cho , and Yoshua Bengio . 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. CoRR abs\/1412.3555 ( 2014 ). arXiv:1412.3555 http:\/\/arxiv.org\/abs\/1412.3555 Junyoung Chung, \u00c7aglar G\u00fcl\u00e7ehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. CoRR abs\/1412.3555 (2014). arXiv:1412.3555 http:\/\/arxiv.org\/abs\/1412.3555"},{"key":"e_1_3_2_1_9_1","volume-title":"2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)","volume":"1","author":"Dalal N.","year":"2005","unstructured":"N. Dalal and B. Triggs . 2005. Histograms of oriented gradients for human detection . In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) , Vol. 1 . 886--893 vol. 1. https:\/\/doi.org\/10.1109\/CVPR. 2005 .177 10.1109\/CVPR.2005.177 N. Dalal and B. Triggs. 2005. Histograms of oriented gradients for human detection. In 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), Vol. 1. 886--893 vol. 1. https:\/\/doi.org\/10.1109\/CVPR.2005.177"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1763974.1764031"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.65"},{"key":"e_1_3_2_1_13_1","volume-title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals. In The IEEE International Conference on Computer Vision (ICCV).","author":"Gao Jiyang","year":"2017","unstructured":"Jiyang Gao , Zhenheng Yang , Kan Chen , Chen Sun , and Ram Nevatia . 2017 . TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals. In The IEEE International Conference on Computer Vision (ICCV). Jiyang Gao, Zhenheng Yang, Kan Chen, Chen Sun, and Ram Nevatia. 2017. TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals. In The IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_14_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow , Yoshua Bengio , and Aaron Courville . 2016. Deep Learning . MIT Press . http:\/\/www.deeplearningbook.org. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_15_1","unstructured":"A. Gorban H. Idrees Y.-G. Jiang A. Roshan Zamir I. Laptev M. Shah and R. Sukthankar. 2015. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/www.thumos.info\/.  A. Gorban H. Idrees Y.-G. Jiang A. Roshan Zamir I. Laptev M. Shah and R. Sukthankar. 2015. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/www.thumos.info\/."},{"key":"e_1_3_2_1_16_1","volume-title":"Generating Sequences With Recurrent Neural Networks. CoRR abs\/1308.0850","author":"Graves Alex","year":"2013","unstructured":"Alex Graves . 2013. Generating Sequences With Recurrent Neural Networks. CoRR abs\/1308.0850 ( 2013 ). arXiv:1308.0850 http:\/\/arxiv.org\/abs\/1308.0850 Alex Graves. 2013. Generating Sequences With Recurrent Neural Networks. CoRR abs\/1308.0850 (2013). arXiv:1308.0850 http:\/\/arxiv.org\/abs\/1308.0850"},{"key":"e_1_3_2_1_17_1","volume-title":"AVA: A Video Dataset of Spatiotemporally Localized Atomic Visual Actions. CoRR abs\/1705.08421","author":"Gu Chunhui","year":"2017","unstructured":"Chunhui Gu , Chen Sun , Sudheendra Vijayanarasimhan , Caroline Pantofaru , David A. Ross , George Toderici , Yeqing Li , Susanna Ricco , Rahul Sukthankar , Cordelia Schmid , and Jitendra Malik . 2017 . AVA: A Video Dataset of Spatiotemporally Localized Atomic Visual Actions. CoRR abs\/1705.08421 (2017). arXiv:1705.08421 http:\/\/arxiv.org\/abs\/1705.08421 Chunhui Gu, Chen Sun, Sudheendra Vijayanarasimhan, Caroline Pantofaru, David A. Ross, George Toderici, Yeqing Li, Susanna Ricco, Rahul Sukthankar, Cordelia Schmid, and Jitendra Malik. 2017. AVA: A Video Dataset of Spatiotemporally Localized Atomic Visual Actions. CoRR abs\/1705.08421 (2017). arXiv:1705.08421 http:\/\/arxiv.org\/abs\/1705.08421"},{"key":"e_1_3_2_1_18_1","first-page":"171","article-title":"Deep Residual Learning for Image Recognition","volume":"7","author":"He Kaiming","year":"2015","unstructured":"Kaiming He , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2015 . Deep Residual Learning for Image Recognition . Arxiv.Org 7 , 3 (2015), 171 -- 180 . https:\/\/doi.org\/10.3389\/fpsyg.2013.00124 arXiv:1512.03385 10.3389\/fpsyg.2013.00124 Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Deep Residual Learning for Image Recognition. Arxiv.Org 7, 3 (2015), 171--180. https:\/\/doi.org\/10.3389\/fpsyg.2013.00124 arXiv:1512.03385","journal-title":"Arxiv.Org"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_21_1","volume-title":"Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery. Bmvc","author":"Hou Rui","year":"2017","unstructured":"Rui Hou , Rahul Sukthankar , and Mubarak Shah . 2017. Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery. Bmvc ( 2017 ). Rui Hou, Rahul Sukthankar, and Mubarak Shah. 2017. Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery. Bmvc (2017)."},{"key":"e_1_3_2_1_22_1","volume-title":"Yu-Gang Jiang, Alex Gorban, Ivan Laptev, Rahul Sukthankar, and Mubarak Shah.","author":"Idrees Haroon","year":"2016","unstructured":"Haroon Idrees , Amir Roshan Zamir , Yu-Gang Jiang, Alex Gorban, Ivan Laptev, Rahul Sukthankar, and Mubarak Shah. 2016 . The THUMOS Challenge on Action Recognition for Videos \"in the Wild\". CoRR abs\/1604.06182 (2016). arXiv:1604.06182 http:\/\/arxiv.org\/abs\/1604.06182 Haroon Idrees, Amir Roshan Zamir, Yu-Gang Jiang, Alex Gorban, Ivan Laptev, Rahul Sukthankar, and Mubarak Shah. 2016. The THUMOS Challenge on Action Recognition for Videos \"in the Wild\". CoRR abs\/1604.06182 (2016). arXiv:1604.06182 http:\/\/arxiv.org\/abs\/1604.06182"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.100"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_25_1","unstructured":"Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/crcv.ucf.edu\/THUMOS14\/.  Y.-G. Jiang J. Liu A. Roshan Zamir G. Toderici I. Laptev M. Shah and R. Sukthankar. 2014. THUMOS Challenge: Action Recognition with a Large Number of Classes. http:\/\/crcv.ucf.edu\/THUMOS14\/."},{"key":"e_1_3_2_1_26_1","volume-title":"Action Tubelet Detector for Spatio-Temporal Action Localization. CoRR abs\/1705.01861","author":"Kalogeiton Vicky","year":"2017","unstructured":"Vicky Kalogeiton , Philippe Weinzaepfel , Vittorio Ferrari , and Cordelia Schmid . 2017. Action Tubelet Detector for Spatio-Temporal Action Localization. CoRR abs\/1705.01861 ( 2017 ). arXiv:1705.01861 http:\/\/arxiv.org\/abs\/1705.01861 Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari, and Cordelia Schmid. 2017. Action Tubelet Detector for Spatio-Temporal Action Localization. CoRR abs\/1705.01861 (2017). arXiv:1705.01861 http:\/\/arxiv.org\/abs\/1705.01861"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_28_1","volume-title":"The Kinetics Human Action Video Dataset. CoRR abs\/1705.06950","author":"Kay Will","year":"2017","unstructured":"Will Kay , Joao Carreira , Karen Simonyan , Brian Zhang , Chloe Hillier , Sudheendra Vijayanarasimhan , Fabio Viola , Tim Green , Trevor Back , Paul Natsev , Mustafa Suleyman , and Andrew Zisserman . 2017. The Kinetics Human Action Video Dataset. CoRR abs\/1705.06950 ( 2017 ). arXiv:1705.06950 http:\/\/arxiv.org\/abs\/1705.06950 Will Kay, Joao Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, Mustafa Suleyman, and Andrew Zisserman. 2017. The Kinetics Human Action Video Dataset. CoRR abs\/1705.06950 (2017). arXiv:1705.06950 http:\/\/arxiv.org\/abs\/1705.06950"},{"key":"e_1_3_2_1_29_1","volume-title":"Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs]","author":"Kingma Diederik","year":"2014","unstructured":"Diederik Kingma and Jimmy Ba . 2014 . Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs] (2014), 1--15. arXiv:1412.6980 http:\/\/arxiv.org\/abs\/1412.6980$\\delimiter\"026E30F$nhttp:\/\/www.arxiv.org\/pdf\/1412.6980.pdf Diederik Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. arXiv:1412.6980 [cs] (2014), 1--15. arXiv:1412.6980 http:\/\/arxiv.org\/abs\/1412.6980$\\delimiter\"026E30F$nhttp:\/\/www.arxiv.org\/pdf\/1412.6980.pdf"},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky Alex","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012. ImageNet Classification with Deep Convolutional Neural Networks . In Advances in Neural Information Processing Systems 25 , F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc. , 1097--1105. http:\/\/papers.nips.cc\/paper\/4824- imagenet- classification-with- deep- convolutional- neural- networks.pdf Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097--1105. http:\/\/papers.nips.cc\/paper\/4824- imagenet- classification-with- deep- convolutional- neural- networks.pdf"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_32_1","volume-title":"Applications and Systems Conference, IPAS 2014 (2014","author":"Kumar Ashok","year":"2014","unstructured":"Ashok Kumar , Javesh Garg , and Amitabha Mukerjee . 2014 . Cricket activity detection. International Image Processing , Applications and Systems Conference, IPAS 2014 (2014 ), 1--6. https:\/\/doi.org\/10.1109\/IPAS.2014.7043264 10.1109\/IPAS.2014.7043264 Ashok Kumar, Javesh Garg, and Amitabha Mukerjee. 2014. Cricket activity detection. International Image Processing, Applications and Systems Conference, IPAS 2014 (2014), 1--6. https:\/\/doi.org\/10.1109\/IPAS.2014.7043264"},{"key":"e_1_3_2_1_33_1","volume-title":"Microsoft COCO: Common Objects in Context. CoRR abs\/1405.0312","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin , Michael Maire , Serge J. Belongie , Lubomir D. Bourdev , Ross B. Girshick , James Hays , Pietro Perona , Deva Ramanan , Piotr Doll\u00e1r , and C. Lawrence Zitnick . 2014. Microsoft COCO: Common Objects in Context. CoRR abs\/1405.0312 ( 2014 ). arXiv:1405.0312 http:\/\/arxiv.org\/abs\/1405.0312 Tsung-Yi Lin, Michael Maire, Serge J. Belongie, Lubomir D. Bourdev, Ross B. Girshick, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common Objects in Context. CoRR abs\/1405.0312 (2014). arXiv:1405.0312 http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"e_1_3_2_1_34_1","volume-title":"A Critical Review of Recurrent Neural Networks for Sequence Learning. CoRR abs\/1506.00019","author":"Lipton Zachary Chase","year":"2015","unstructured":"Zachary Chase Lipton . 2015. A Critical Review of Recurrent Neural Networks for Sequence Learning. CoRR abs\/1506.00019 ( 2015 ). arXiv:1506.00019 http:\/\/arxiv.org\/abs\/1506.00019 Zachary Chase Lipton. 2015. A Critical Review of Recurrent Neural Networks for Sequence Learning. CoRR abs\/1506.00019 (2015). arXiv:1506.00019 http:\/\/arxiv.org\/abs\/1506.00019"},{"key":"e_1_3_2_1_35_1","volume-title":"Weakly Supervised Action Localization by Sparse Temporal Pooling Network. CoRR abs\/1712.05080","author":"Nguyen Phuc","year":"2017","unstructured":"Phuc Nguyen , Ting Liu , Gautam Prasad , and Bohyung Han . 2017. Weakly Supervised Action Localization by Sparse Temporal Pooling Network. CoRR abs\/1712.05080 ( 2017 ). arXiv:1712.05080 http:\/\/arxiv.org\/abs\/1712.05080 Phuc Nguyen, Ting Liu, Gautam Prasad, and Bohyung Han. 2017. Weakly Supervised Action Localization by Sparse Temporal Pooling Network. CoRR abs\/1712.05080 (2017). arXiv:1712.05080 http:\/\/arxiv.org\/abs\/1712.05080"},{"key":"e_1_3_2_1_36_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017).  Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_37_1","volume-title":"Precise Temporal Action Localization by Evolving Temporal Proposals. CoRR abs\/1804.04803","author":"Qiu Haonan","year":"2018","unstructured":"Haonan Qiu , Yingbin Zheng , Hao Ye , Yao Lu , Feng Wang , and Liang He. 2018. Precise Temporal Action Localization by Evolving Temporal Proposals. CoRR abs\/1804.04803 ( 2018 ). arXiv:1804.04803 http:\/\/arxiv.org\/abs\/1804.04803 Haonan Qiu, Yingbin Zheng, Hao Ye, Yao Lu, Feng Wang, and Liang He. 2018. Precise Temporal Action Localization by Evolving Temporal Proposals. CoRR abs\/1804.04803 (2018). arXiv:1804.04803 http:\/\/arxiv.org\/abs\/1804.04803"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_39_1","unstructured":"Rahul Anand Sharma K. Pramod Sankar and C. V. Jawahar. 2015. Fine-Grain Annotation of Cricket Videos. CoRRabs\/1511.07607 (2015). arXiv:1511.07607http:\/\/arxiv.org\/abs\/1511.07607  Rahul Anand Sharma K. Pramod Sankar and C. V. Jawahar. 2015. Fine-Grain Annotation of Cricket Videos. CoRRabs\/1511.07607 (2015). arXiv:1511.07607http:\/\/arxiv.org\/abs\/1511.07607"},{"key":"e_1_3_2_1_40_1","volume-title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos. CoRR abs\/1703.01515","author":"Shou Zheng","year":"2017","unstructured":"Zheng Shou , Jonathan Chan , Alireza Zareian , Kazuyuki Miyazawa , and Shih-Fu Chang . 2017 . CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos. CoRR abs\/1703.01515 (2017). arXiv:1703.01515 http:\/\/arxiv.org\/abs\/1703.01515 Zheng Shou, Jonathan Chan, Alireza Zareian, Kazuyuki Miyazawa, and Shih-Fu Chang. 2017. CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos. CoRR abs\/1703.01515 (2017). arXiv:1703.01515 http:\/\/arxiv.org\/abs\/1703.01515"},{"key":"e_1_3_2_1_41_1","volume-title":"Two-Stream Convolutional Networks for Action Recognition in Videos. arXiv preprint arXiv 1406.2199","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. arXiv preprint arXiv 1406.2199 ( 2014 ), 1--11. arXiv:arXiv:1406.2199v1 http:\/\/arxiv.org\/abs\/1406.2199 Karen Simonyan and Andrew Zisserman. 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. arXiv preprint arXiv 1406.2199 (2014), 1--11. arXiv:arXiv:1406.2199v1 http:\/\/arxiv.org\/abs\/1406.2199"},{"key":"e_1_3_2_1_42_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. ImageNet Challenge","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. ImageNet Challenge ( 2014 ), 1--10. https:\/\/doi.org\/10.1016\/j.infsof.2008.09.005 arXiv:1409.1556 10.1016\/j.infsof.2008.09.005 Karen Simonyan and Andrew Zisserman. 2014. Very Deep Convolutional Networks for Large-Scale Image Recognition. ImageNet Challenge (2014), 1--10. https:\/\/doi.org\/10.1016\/j.infsof.2008.09.005 arXiv:1409.1556"},{"key":"e_1_3_2_1_43_1","volume-title":"Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction. In The IEEE International Conference on Computer Vision (ICCV).","author":"Singh Gurkirt","year":"2017","unstructured":"Gurkirt Singh , Suman Saha , Michael Sapienza , Philip H. S. Torr , and Fabio Cuzzolin . 2017 . Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction. In The IEEE International Conference on Computer Vision (ICCV). Gurkirt Singh, Suman Saha, Michael Sapienza, Philip H. S. Torr, and Fabio Cuzzolin. 2017. Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction. In The IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.375"},{"key":"e_1_3_2_1_45_1","volume-title":"Unsupervised Action Discovery and Localization in Videos. In The IEEE International Conference on Computer Vision (ICCV).","author":"Soomro Khurram","year":"2017","unstructured":"Khurram Soomro and Mubarak Shah . 2017 . Unsupervised Action Discovery and Localization in Videos. In The IEEE International Conference on Computer Vision (ICCV). Khurram Soomro and Mubarak Shah. 2017. Unsupervised Action Discovery and Localization in Videos. In The IEEE International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_46_1","volume-title":"Zamir","author":"Soomro Khurram","year":"2014","unstructured":"Khurram Soomro and Amir R . Zamir . 2014 . Action Recognition in Realistic Sports Videos. Springer International Publishing , Cham, 181--208. https:\/\/doi.org\/10.1007\/978-3-319-09396-3_9 10.1007\/978-3-319-09396-3_9 Khurram Soomro and Amir R. Zamir. 2014. Action Recognition in Realistic Sports Videos. Springer International Publishing, Cham, 181--208. https:\/\/doi.org\/10.1007\/978-3-319-09396-3_9"},{"key":"e_1_3_2_1_47_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro , Amir Roshan Zamir, and Mubarak Shah . 2012 . UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR abs\/1212.0402 (2012). arXiv:1212.0402 http:\/\/arxiv.org\/abs\/1212.0402 Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. CoRR abs\/1212.0402 (2012). arXiv:1212.0402 http:\/\/arxiv.org\/abs\/1212.0402"},{"key":"e_1_3_2_1_48_1","volume-title":"Le","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever , Oriol Vinyals , and Quoc V . Le . 2014 . Sequence to Sequence Learning with Neural Networks. CoRR abs\/1409.3215 (2014). arXiv:1409.3215 http:\/\/arxiv.org\/abs\/1409.3215 Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to Sequence Learning with Neural Networks. CoRR abs\/1409.3215 (2014). arXiv:1409.3215 http:\/\/arxiv.org\/abs\/1409.3215"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.04.011"},{"key":"e_1_3_2_1_50_1","volume-title":"Learning Spatiotemporal Features with 3D Convolutional Networks. Iccv","author":"Tran Du","year":"2015","unstructured":"Du Tran , Lubomir Bourdev , Rob Fergus , Lorenzo Torresani , and Manohar Paluri . 2015. Learning Spatiotemporal Features with 3D Convolutional Networks. Iccv ( 2015 ). https:\/\/doi.org\/10.1109\/CVPR.2014.223 arXiv:1412.0767 10.1109\/CVPR.2014.223 Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2015. Learning Spatiotemporal Features with 3D Convolutional Networks. Iccv (2015). https:\/\/doi.org\/10.1109\/CVPR.2014.223 arXiv:1412.0767"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_52_1","volume-title":"Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation. Sensors 18, 5","author":"Wang Le","year":"2018","unstructured":"Le Wang , Xuhuan Duan , Qilin Zhang , Zhenxing Niu , Gang Hua , and Nanning Zheng . 2018. Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation. Sensors 18, 5 ( 2018 ). https:\/\/doi.org\/10.3390\/s18051657 10.3390\/s18051657 Le Wang, Xuhuan Duan, Qilin Zhang, Zhenxing Niu, Gang Hua, and Nanning Zheng. 2018. Segment-Tube: Spatio-Temporal Action Localization in Untrimmed Videos with Per-Frame Segmentation. Sensors 18, 5 (2018). https:\/\/doi.org\/10.3390\/s18051657"},{"key":"e_1_3_2_1_53_1","volume-title":"ECCV2014 THUMOS Challenge","author":"Wang Limin","year":"2014","unstructured":"Limin Wang , Yu Qiao , and Xiaoou Tang . 2014 . Action Recognition and Detection by Combining Motion and Appearance Features . ECCV2014 THUMOS Challenge (2014), 1--6. http:\/\/crcv.ucf.edu\/THUMOS14\/papers\/CUHK{&}SIAT.pdf 2nd in detection task. Limin Wang, Yu Qiao, and Xiaoou Tang. 2014. Action Recognition and Detection by Combining Motion and Appearance Features. ECCV2014 THUMOS Challenge (2014), 1--6. http:\/\/crcv.ucf.edu\/THUMOS14\/papers\/CUHK{&}SIAT.pdf 2nd in detection task."},{"key":"e_1_3_2_1_54_1","volume-title":"UntrimmedNets for Weakly Supervised Action Recognition and Detection. CoRR abs\/1703.03329","author":"Wang Limin","year":"2017","unstructured":"Limin Wang , Yuanjun Xiong , Dahua Lin , and Luc Van Gool . 2017. UntrimmedNets for Weakly Supervised Action Recognition and Detection. CoRR abs\/1703.03329 ( 2017 ). arXiv:1703.03329 http:\/\/arxiv.org\/abs\/1703.03329 Limin Wang, Yuanjun Xiong, Dahua Lin, and Luc Van Gool. 2017. UntrimmedNets for Weakly Supervised Action Recognition and Detection. CoRR abs\/1703.03329 (2017). arXiv:1703.03329 http:\/\/arxiv.org\/abs\/1703.03329"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"e_1_3_2_1_56_1","volume-title":"End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv","author":"Yeung Serena","year":"2015","unstructured":"Serena Yeung , Olga Russakovsky , Greg Mori , and Li Fei-Fei . 2015. End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv ( 2015 ). https:\/\/doi.org\/10.1109\/CVPR.2016.293 arXiv:1511.06984 10.1109\/CVPR.2016.293 Serena Yeung, Olga Russakovsky, Greg Mori, and Li Fei-Fei. 2015. End-to-end Learning of Action Detection from Frame Glimpses in Videos. arXiv (2015). https:\/\/doi.org\/10.1109\/CVPR.2016.293 arXiv:1511.06984"},{"key":"e_1_3_2_1_57_1","volume-title":"Temporal Action Localization by Structured Maximal Sums. CoRR abs\/1704.04671","author":"Yuan Ze-Huan","year":"2017","unstructured":"Ze-Huan Yuan , Jonathan C. Stroud , Tong Lu , and Jia Deng . 2017. Temporal Action Localization by Structured Maximal Sums. CoRR abs\/1704.04671 ( 2017 ). arXiv:1704.04671 http:\/\/arxiv.org\/abs\/1704.04671 Ze-Huan Yuan, Jonathan C. Stroud, Tong Lu, and Jia Deng. 2017. Temporal Action Localization by Structured Maximal Sums. CoRR abs\/1704.04671 (2017). arXiv:1704.04671 http:\/\/arxiv.org\/abs\/1704.04671"},{"key":"e_1_3_2_1_58_1","first-page":"2016","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zheng Shou","year":"2016","unstructured":"Shou Zheng , Wang Dongang , and Chang Shih-Fu . 2016 . Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs . IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2016 (2016), 1049--1058. https:\/\/doi.org\/10.1109\/CVPR.2016.119 arXiv:1601.02129 10.1109\/CVPR.2016.119 Shou Zheng, Wang Dongang, and Chang Shih-Fu. 2016. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 (2016), 1049--1058. https:\/\/doi.org\/10.1109\/CVPR.2016.119 arXiv:1601.02129"}],"event":{"name":"ICVGIP 2018: 11th Indian Conference on Computer Vision, Graphics and Image Processing","location":"Hyderabad India","acronym":"ICVGIP 2018"},"container-title":["Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3293353.3293415","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3293353.3293415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:58:08Z","timestamp":1750208288000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3293353.3293415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,18]]},"references-count":58,"alternative-id":["10.1145\/3293353.3293415","10.1145\/3293353"],"URL":"https:\/\/doi.org\/10.1145\/3293353.3293415","relation":{},"subject":[],"published":{"date-parts":[[2018,12,18]]},"assertion":[{"value":"2020-05-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}