{"type":"ScholarlyArticle","title":"CVAT-BWV: A Web-Based Video Annotation Platform for Police Body-Worn Video","authors":[{"name":"Parsa Hejabi","slug":"parsa-hejabi","given":"Parsa","family":"Hejabi","affiliation":"University of Southern California"},{"name":"Akshay Kiran Padte","slug":"akshay-kiran-padte","given":"Akshay Kiran","family":"Padte","affiliation":"University of Southern California"},{"name":"Preni Golazizian","slug":"preni-golazizian","given":"Preni","family":"Golazizian","affiliation":"University of Southern California"},{"name":"Rajat Hebbar","slug":"rajat-hebbar","given":"Rajat","family":"Hebbar","affiliation":"University of Southern California"},{"name":"Jackson Trager","slug":"jackson-trager","given":"Jackson","family":"Trager","affiliation":"University of Southern California"},{"name":"Georgios Chochlakis","slug":"georgios-chochlakis","given":"Georgios","family":"Chochlakis","affiliation":"University of Southern California"},{"name":"Aditya Kommineni","slug":"aditya-kommineni","given":"Aditya","family":"Kommineni","affiliation":"University of Southern California"},{"name":"Ellie Graeden","slug":"ellie-graeden","given":"Ellie","family":"Graeden","affiliation":"Georgetown University {hejabi , padte ,"},{"name":"Shrikanth Narayanan","slug":"shrikanth-narayanan","given":"Shrikanth","family":"Narayanan","affiliation":"University of Southern California"},{"name":"Benjamin A.T. Graham","slug":"benjamin-a-t-graham","given":"Benjamin A.T.","family":"Graham","affiliation":"University of Southern California"},{"name":"Morteza Dehghani","slug":"morteza-dehghani","given":"Morteza","family":"Dehghani","affiliation":"University of Southern California"}],"abstract":"We introduce an open-source platform for annotating body-worn video (BWV) footage aimed at enhancing transparency and accountability in policing. Despite the widespread adoption of BWVs in police departments, analyzing the vast amount of footage generated has presented significant challenges. This is primarily due to resource constraints, the sensitive nature of the data, which limits widespread access, and consequently, lack of annotations for training machine learning models. Our platform, called CVAT-BWV, offers a secure, locally hosted annotation environment that integrates several AI tools to assist in annotating multimodal data. With features such as automatic speech recognition, speaker diarization, object detection, and face recognition, CVAT-BWV aims to reduce the manual annotation workload, improve annotation quality, and allow for capturing perspectives from a diverse population of annotators. This tool aims to streamline the collection of annotations and the building of models, enhancing the use of BWV data for oversight and learning purposes to uncover insights into police-civilian interactions.","doi":"10.24963/ijcai.2024/1006","url":"https://ijcai.org/proceedings/2024/1006","pdf":"https://ijcai.org/proceedings/2024/1006.pdf","markdown":"https://ijcai.org/proceedings/2024/1006.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/1006","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Demo Track","track":"Demo Track","number":1006,"pages":{"first":8674,"last":8678},"keywords":["AI Ethics, Trust, Fairness: ETF: Societal impact of AI","Computer Vision: CV: Applications","Humans and AI: HAI: Human-AI collaboration","Machine Learning: ML: Applications"],"videos":[],"references":[{"position":1,"raw":"[Bain et al., 2023] Max Bain, Jaesung Huh, Tengda Han, and Andrew Zisserman. WhisperX: Time-Accurate Speech Transcription of Long-Form Audio. In Proc. INTER- SPEECH 2023, pages 4489-4493, 2023.","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","authors":"Bain","year":"2023","venue":"Proc. INTER-SPEECH 2023","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[California Department of Justice, 2024] California Depart- ment of Justice. Racial and identity profiling advi- sory board annual report. https://oag.ca.gov/system/ files/media/ripa-board-report-2024.pdf, 2024. Accessed: 2024-02-05.","title":"California Department of Justice. Racial and identity profiling advisory board annual report","authors":null,"year":"2024","venue":null,"doi":null,"url":"https://oag.ca.gov/system/files/media/ripa-board-report-2024.pdf","internal_url":null},{"position":3,"raw":"[Camp et al., 2021] Nicholas P. Camp, Rob Voigt, Dan Ju- rafsky, and Jennifer L. Eberhardt. The thin blue wave- form: Racial disparities in officer prosody undermine in- stitutional trust in the police. Journal of Personality and Social Psychology, 121(6):1157-1171, December 2021.","title":"The thin blue waveform: Racial disparities in officer prosody undermine institutional trust in the police","authors":"Nicholas P Camp, Rob Voigt, Dan Jurafsky, Jennifer L Eberhardt","year":"2021","venue":"Journal of Personality and Social Psychology","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2020] Jiankang Deng, Jia Guo, Evangelos Ververas, Irene Kotsia, and Stefanos Zafeiriou. Retinaface: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.","title":"Retinaface: Single-shot multi-level face localisation in the wild","authors":"Deng","year":"2020","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Graham et al., 2024] Benjamin AT Graham, Lauren Brown, Georgios Chochlakis, Morteza Dehghani, Raquel Del- erme, Brittany Friedman, Ellie Graeden, Preni Golazizian, Rajat Hebbar, Parsa Hejabi, et al. A multi-perspective machine learning approach to evaluate police-driver inter- action in Los Angeles. arXiv preprint arXiv:2402.01703, 2024.","title":"A multi-perspective machine learning approach to evaluate police-driver interaction in Los Angeles","authors":"A T Benjamin, Lauren Graham, Georgios Brown, Morteza Chochlakis, Raquel Dehghani, Brittany Delerme, Ellie Friedman, Preni Graeden, Rajat Golazizian, Parsa Hebbar, Hejabi","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jocher et al., 2023] Glenn Jocher, Ayush Chaurasia, and Jing Qiu. Ultralytics YOLO, January 2023. [Labelbox, 2024] Labelbox. Labelbox. https://labelbox. com, 2024. [Online; accessed 2024].","title":"Ultralytics YOLO","authors":"Glenn Jocher, Ayush Chaurasia, Jing Qiu","year":"2023","venue":null,"doi":null,"url":"https://labelbox.com,2024","internal_url":null},{"position":7,"raw":"[Marchesoni-Acland and Facciolo, 2023] Franco Marchesoni-Acland and Gabriele Facciolo. Iadet: Simplest human-in-the-loop object detection, 2023.","title":"Franco Marchesoni-Acland and Gabriele Facciolo. Iadet: Simplest human-in-the-loop object detection","authors":"Marchesoni-Acland, Facciolo","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Montani and Honnibal, 2024] Ines Montani and Matthew Honnibal. Prodigy: A modern and scriptable annotation tool for creating training data for machine learning mod- els, 2024.","title":"Prodigy: A modern and scriptable annotation tool for creating training data for machine learning models","authors":"Ines Montani, Matthew Honnibal","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Prabhakaran et al., 2018] Vinodkumar Prabhakaran, Camilla Griffiths, Hang Su, Prateek Verma, Nelson Mor- gan, Jennifer L Eberhardt, and Dan Jurafsky. Detecting institutional dialog acts in police traffic stops. Transac- tions of the Association for Computational Linguistics, 6:467-481, 2018.","title":"Detecting institutional dialog acts in police traffic stops","authors":"Prabhakaran","year":"2018","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Rho et al., 2023] Eugenia H. Rho, Maggie Harrington, Yuyang Zhong, Reid Pryzant, Nicholas P. Camp, Dan Ju- rafsky, and Jennifer L. Eberhardt. Escalated police stops of black men are linguistically and psychologically dis- tinct in their earliest moments. Proceedings of the National Academy of Sciences, 120(23):e2216162120, 2023.","title":"Escalated police stops of black men are linguistically and psychologically distinct in their earliest moments","authors":"Eugenia H Rho, Maggie Harrington, Yuyang Zhong, Reid Pryzant, Nicholas P Camp, Dan Jurafsky, Jennifer L Eberhardt","year":"2023","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Schroff et al., 2015] Florian Schroff, Dmitry Kalenichenko, and James Philbin. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015.","title":"Facenet: A unified embedding for face recognition and clustering","authors":"Schroff","year":"2015","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sekachev et al., 2020] Boris Sekachev, Nikita Manovich, Maxim Zhiltsov, Andrey Zhavoronkov, Dmitry Kalinin, Ben Hoff, TOsmanov, Dmitry Kruchinin, Artyom Zanke- vich, DmitriySidnev, Maksim Markelov, Johannes222, Mathis Chenuet, a andre, telenachos, Aleksandr Melnikov, Jijoong Kim, Liron Ilouz, Nikita Glazov, Priya4607, Rush Tehrani, Seungwon Jeong, Vladimir Skubriev, Sebastian Yonekura, vugia truong, zliang7, lizhming, and Tritin Truong. opencv/cvat: v1.1.0, August 2020.","title":"zliang7, lizhming, and Tritin Truong","authors":"Boris Sekachev, Nikita Manovich, Maxim Zhiltsov, Andrey Zhavoronkov, Dmitry Kalinin, Ben Hoff, Dmitry Tosmanov, Artyom Kruchinin, Zankevich, Maksim Dmitriysidnev, Markelov, Mathis Johannes222, Aleksandr Chenuet, Jijoong Melnikov, Liron Kim, Nikita Ilouz, Glazov, Rush Priya4607, Seungwon Tehrani, Vladimir Jeong, Sebastian Skubriev, Yonekura","year":"2020","venue":"opencv/cvat","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Serengil and Ozpinar, 2020] Sefik Ilkin Serengil and Alper Ozpinar. Lightface: A hybrid deep face recognition frame- work. In 2020 Innovations in Intelligent Systems and Ap- plications Conference (ASYU), pages 23-27. IEEE, 2020.","title":"Sefik Ilkin Serengil and Alper Ozpinar. Lightface: A hybrid deep face recognition framework","authors":"Ozpinar Serengil","year":"2020","venue":"Innovations in Intelligent Systems and Applications Conference (ASYU)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[van der Wal et al., 2021] Douwe van der Wal, Iny Jhun, Is- raa Laklouk, Jeff Nirschl, Lara Richer, Rebecca Rojansky, Talent Theparee, Joshua Wheeler, Jörg Sander, Felix Feng, Osama Mohamad, Silvio Savarese, Richard Socher, and Andre Esteva. Biological data annotation via a human- augmenting AI-based labeling system. NPJ Digit. Med., 4(1):145, October 2021.","title":"Biological data annotation via a humanaugmenting AI-based labeling system","authors":"Wal Van Der","year":"2021","venue":"NPJ Digit. Med","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Voigt et al., 2017] Rob Voigt, Nicholas P. Camp, Vinod- kumar Prabhakaran, William L. Hamilton, Rebecca C. Hetey, Camilla M. Griffiths, David Jurgens, Dan Juraf- sky, and Jennifer L. Eberhardt. Language from police body camera footage shows racial disparities in officer re- spect. Proceedings of the National Academy of Sciences, 114(25):6521-6526, 2017.","title":"Language from police body camera footage shows racial disparities in officer respect","authors":"Rob Voigt, Nicholas P Camp, Vinodkumar Prabhakaran, William L Hamilton, Rebecca C Hetey, Camilla M Griffiths, David Jurgens, Dan Jurafsky, Jennifer L Eberhardt","year":"2017","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Weber and Plank, 2023] Leon Weber and Barbara Plank. ActiveAED: A human in the loop improves annotation er- ror detection. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, pages 8834-8845, Toronto, Canada, July 2023. Association for Computa- tional Linguistics.","title":"ActiveAED: A human in the loop improves annotation error detection","authors":"Plank Weber, Leon Weber, Barbara Plank","year":"2023","venue":"Findings of the Association for Computational Linguistics: ACL 2023","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}