{"type":"ScholarlyArticle","title":"AutoVideo: An Automated Video Action Recognition System","authors":[{"name":"Daochen Zha","slug":"daochen-zha","given":"Daochen","family":"Zha","affiliation":"Department of Computer Science , Rice University"},{"name":"Zaid Pervaiz Bhat","slug":"zaid-pervaiz-bhat","given":"Zaid Pervaiz","family":"Bhat","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Yi-Wei Chen","slug":"yi-wei-chen","given":"Yi-Wei","family":"Chen","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Yicheng Wang","slug":"yicheng-wang","given":"Yicheng","family":"Wang","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Sirui Ding","slug":"sirui-ding","given":"Sirui","family":"Ding","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Jiaben Chen","slug":"jiaben-chen","given":"Jiaben","family":"Chen","affiliation":"School of Information Science and Technology , ShanghaiTech University"},{"name":"Kwei-Herng Lai","slug":"kwei-herng-lai","given":"Kwei-Herng","family":"Lai","affiliation":"Department of Computer Science , Rice University"},{"name":"Mohammad Qazim Bhat","slug":"mohammad-qazim-bhat","given":"Mohammad Qazim","family":"Bhat","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Anmoll Kumar Jain","slug":"anmoll-kumar-jain","given":"Anmoll Kumar","family":"Jain","affiliation":"Department of Computer Science and Engineering , Texas A&M University"},{"name":"Alfredo Costilla Reyes","slug":"alfredo-costilla-reyes","given":"Alfredo","family":"Costilla Reyes","affiliation":"Department of Computer Science , Rice University"},{"name":"Na Zou","slug":"na-zou","given":"Na","family":"Zou","affiliation":"Department of Engineering Technology and Industrial Distribution , Texas A&M University"},{"name":"Xia Hu","slug":"xia-hu","given":"Xia","family":"Hu","affiliation":"Department of Computer Science , Rice University"}],"abstract":"Action recognition is an important task for video understanding with broad applications. However, developing an effective action recognition solution often requires extensive engineering efforts in building and testing different combinations of the modules and their hyperparameters. In this demo, we present AutoVideo, a Python system for automated video action recognition. AutoVideo is featured for 1) highly modular and extendable infrastructure following the standard pipeline language, 2) an exhaustive list of primitives for pipeline construction, 3) data-driven tuners to save the efforts of pipeline tuning, and 4) easy-to-use Graphical User Interface (GUI). AutoVideo is released under MIT license at https://github.com/datamllab/autovideo","doi":"10.24963/ijcai.2022/862","url":"https://ijcai.org/proceedings/2022/862","pdf":"https://ijcai.org/proceedings/2022/0862.pdf","markdown":"https://ijcai.org/proceedings/2022/862.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/862","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Demo Track","track":"Demo Track","number":862,"pages":{"first":5952,"last":5955},"keywords":["Machine Learning: Automated Machine Learning","Computer Vision: Video analysis and understanding"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987205","length_sec":89,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985348","length_sec":131,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bergstra et al., 2013] James Bergstra, Dan Yamins, David D Cox, et al. Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms. In Proceedings of the 12th Python in science conference, volume 13, page 20. Citeseer, 2013.","title":"Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms","authors":"James Bergstra, Dan Yamins, David D Cox","year":"2013","venue":"Proceedings of the 12th Python in science conference","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Carreira and Zisserman, 2017] Joao Carreira and Andrew Zisserman. Quo vadis, action recognition? a new model and the kinetics dataset. In CVPR, pages 6299-6308, 2017.","title":"Quo vadis, action recognition? a new model and the kinetics dataset","authors":"Joao Carreira, Andrew Zisserman","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Demšar et al., 2004] Janez Demšar, Blaž Zupan, Gregor Leban, and Tomaz Curk. Orange: From experimental ma- chine learning to interactive data mining. In PKDD, pages 537-539. Springer, 2004.","title":"Orange: From experimental machine learning to interactive data mining","authors":"Janez Demšar, Blaž Zupan, Gregor Leban, Tomaz Curk","year":"2004","venue":"PKDD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gao et al., 2018] Yongbin Gao, Xuehao Xiang, Naixue Xiong, Bo Huang, Hyo Jong Lee, Rad Alrifai, Xiaoyan Jiang, and Zhijun Fang. Human action monitoring for healthcare based on deep learning. Ieee Access, 6:52277- 52285, 2018.","title":"Human action monitoring for healthcare based on deep learning","authors":"Gao","year":"2018","venue":"Ieee Access","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Herath et al., 2017] Samitha Herath, Mehrtash Harandi, and Fatih Porikli. Going deeper into action recognition: A sur- vey. Image and vision computing, 60:4-21, 2017.","title":"Going deeper into action recognition: A survey","authors":"Samitha Herath, Mehrtash Harandi, Fatih Porikli","year":"2017","venue":"Image and vision computing","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hou et al., 2019] Rui Hou, Chen Chen, Rahul Sukthankar, and Mubarak Shah. An efficient 3d cnn for action/object segmentation in video. arXiv preprint arXiv:1907.08895, 2019.","title":"An efficient 3d cnn for action/object segmentation in video","authors":"Rui Hou, Chen Chen, Rahul Sukthankar, Mubarak Shah","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Lai et al., 2021a] Kwei-Herng Lai, Daochen Zha, Guanchu Wang, Junjie Xu, Yue Zhao, Devesh Kumar, Yile Chen, Purav Zumkhawaka, Minyang Wan, Diego Martinez, et al. Tods: An automated time series outlier detection system. In AAAI, volume 35, pages 16060-16062, 2021.","title":"Tods: An automated time series outlier detection system","authors":"Lai","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lai et al., 2021b] Kwei-Herng Lai, Daochen Zha, Junjie Xu, Yue Zhao, Guanchu Wang, and Xia Hu. Revisiting time series outlier detection: Definitions and benchmarks. In NeurIPS, 2021.","title":"Revisiting time series outlier detection: Definitions and benchmarks","authors":"Lai","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Li et al., 2020] Yuening Li, Daochen Zha, Praveen Venu- gopal, Na Zou, and Xia Hu. Pyodds: An end-to-end out- lier detection system with automated machine learning. In WWW, pages 153-157, 2020.","title":"Pyodds: An end-to-end outlier detection system with automated machine learning","authors":"Li","year":"2020","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Meng et al., 2007] Hongying Meng, Nick Pears, and Chris Bailey. A human action recognition system for embedded computer vision application. In CVPR, pages 1-6. IEEE, 2007.","title":"A human action recognition system for embedded computer vision application","authors":"Hongying Meng, Nick Pears, Chris Bailey","year":"2007","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Milutinovic et al., 2020] Mitar Milutinovic, Brandon Schoenfeld, Diego Martinez-Garcia, Saswati Ray, Sujen Shah, and David Yan. On evaluation of automl systems. In ICML Workshop, 2020.","title":"On evaluation of automl systems","authors":"Mitar Milutinovic, Brandon Schoenfeld, Diego Martinez-Garcia, Saswati Ray, Sujen Shah, David Yan","year":"2020","venue":"ICML Workshop","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Moritz et al., 2018] Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. Ray: A distributed framework for emerging {AI} applications. In OSDI, pages 561-577, 2018.","title":"Ray: A distributed framework for emerging {AI} applications","authors":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan","year":"2018","venue":"OSDI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Piergiovanni et al., 2019] AJ Piergiovanni, Anelia An- gelova, Alexander Toshev, and Michael S Ryoo. Evolving space-time neural architectures for videos. In ICCV, pages 1793-1802, 2019.","title":"Evolving space-time neural architectures for videos","authors":"Piergiovanni","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Poppe, 2010] Ronald Poppe. A survey on vision-based hu- man action recognition. Image and vision computing, 28(6):976-990, 2010.","title":"A survey on vision-based human action recognition","authors":"Ronald Poppe","year":"2010","venue":"Image and vision computing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ryoo et al., 2019] Michael S Ryoo, AJ Piergiovanni, Mingxing Tan, and Anelia Angelova. Assemblenet: Searching for multi-stream neural connectivity in video ar- chitectures. arXiv preprint arXiv:1905.13209, 2019.","title":"Assemblenet: Searching for multi-stream neural connectivity in video architectures","authors":"Michael S Ryoo, Mingxing Piergiovanni, Anelia Tan, Angelova","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Team, 2021] PytorchVideo Team. Pytorchvideo. https: //github.com/facebookresearch/pytorchvideo, 2021. Ac- cessed: 2022-05-22.","title":"PytorchVideo Team. Pytorchvideo","authors":null,"year":"2021","venue":null,"doi":null,"url":"-cessed:2022-05-22","internal_url":null},{"position":17,"raw":"[Tran et al., 2015] Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. Learning spa- tiotemporal features with 3d convolutional networks. In ICCV, pages 4489-4497, 2015.","title":"Learning spatiotemporal features with 3d convolutional networks","authors":"Du Tran, Lubomir Bourdev, Rob Fergus, Lorenzo Torresani, Manohar Paluri","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2016] Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, and Luc Van Gool. Temporal segment networks: Towards good practices for deep action recognition. In ECCV, pages 20- 36. Springer, 2016.","title":"Temporal segment networks: Towards good practices for deep action recognition","authors":"Limin Wang, Yuanjun Xiong, Zhe Wang, Yu Qiao, Dahua Lin, Xiaoou Tang, Luc Van Gool","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang et al., 2022] Guanchu Wang, Zaid Pervaiz Bhat, Zhi- meng Jiang, Yi-Wei Chen, Daochen Zha, Alfredo Costilla Reyes, Afshin Niktash, Gorkem Ulkar, Erman Okman, and Xia Hu. Bed: A real-time object detection system for edge devices. arXiv preprint arXiv:2202.07503, 2022.","title":"Bed: A real-time object detection system for edge devices","authors":"Wang","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yue Zhao, 2019] Dahua Lin Yue Zhao, Yuanjun Xiong. Mmaction. https://github.com/open-mmlab/mmaction, 2019. Accessed: 2022-05-22.","title":"Mmaction","authors":"Dahua Lin, Yue Zhao, Yuanjun Xiong","year":"2019","venue":null,"doi":null,"url":"https://github.com/open-mmlab/mmaction","internal_url":null},{"position":21,"raw":"[Zha et al., 2019] Daochen Zha, Kwei-Herng Lai, Kaixiong Zhou, and Xia Hu. Experience replay optimization. In IJCAI, pages 4243-4249, 2019.","title":"Experience replay optimization","authors":"Zha","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/589"},{"position":22,"raw":"[Zha et al., 2020] Daochen Zha, Kwei-Herng Lai, Mingyang Wan, and Xia Hu. Meta-aad: Active anomaly detection with deep reinforcement learning. In ICDM, pages 771- 780. IEEE, 2020.","title":"Meta-aad: Active anomaly detection with deep reinforcement learning","authors":"Zha","year":"2020","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zha et al., 2021a] Daochen Zha, Kwei-Herng Lai, Songyi Huang, Yuanpu Cao, Keerthana Reddy, Juan Vargas, Alex Nguyen, Ruzhe Wei, Junyu Guo, and Xia Hu. Rlcard: a platform for reinforcement learning in card games. In IJ- CAI, pages 5264-5266, 2021.","title":"Rlcard: a platform for reinforcement learning in card games","authors":"Zha","year":"2021","venue":"IJ-CAI","doi":null,"url":null,"internal_url":"/proceedings/2020/764"},{"position":24,"raw":"[Zha et al., 2021b] Daochen Zha, Wenye Ma, Lei Yuan, Xia Hu, and Ji Liu. Rank the episodes: A simple approach for exploration in procedurally-generated environments. In ICLR, 2021.","title":"Rank the episodes: A simple approach for exploration in procedurally-generated environments","authors":"Zha","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zha et al., 2021c] Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, and Ji Liu. Douzero: Mastering doudizhu with self-play deep reinforcement learning. In ICML, pages 12333-12344. PMLR, 2021.","title":"Douzero: Mastering doudizhu with self-play deep reinforcement learning","authors":"Zha","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zolfaghari et al., 2018] Mohammadreza Zolfaghari, Ka- maljeet Singh, and Thomas Brox. Eco: Efficient convolu- tional network for online video understanding. In ECCV, pages 695-712, 2018.","title":"Eco: Efficient convolutional network for online video understanding","authors":"Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox","year":"2018","venue":"ECCV","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}