pith. sign in

arxiv: 2402.01703 · v6 · submitted 2024-01-24 · 💻 cs.CY · cs.AI· cs.LG· eess.AS

Community-Informed AI Models for Police Accountability

Benjamin A.T. Graham , Lauren Brown , Georgios Chochlakis , Morteza Dehghani , Raquel Delerme , Brittany Friedman , Ellie Graeden , Preni Golazizian
show 8 more authors
Rajat Hebbar Parsa Hejabi Aditya Kommineni Mayag\"uez Salinas Michael Sierra-Ar\'evalo Jackson Trager Nicholas Weller Shrikanth Narayanan
This is my paper

Pith reviewed 2026-05-24 05:07 UTC · model grok-4.3

classification 💻 cs.CY cs.AIcs.LGeess.AS
keywords community-informed AIpolice accountabilitybody-worn camerasmultidisciplinary teamsdemocratic governancesocial scientiststraffic stopsLos Angeles Police Department
0
0 comments X

The pith

AI models for police accountability must incorporate the preferences and perspectives of the communities they serve.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that AI analyzing government-public interactions, such as body-worn camera videos of police traffic stops, can only advance democratic accountability if it embeds the views of the governed. It describes a community-informed method for building multi-perspective AI tools, developed through work on Los Angeles Police Department footage. Social scientists on the development teams serve as the bridge that folds diverse stakeholder input into the models. The approach treats this integration as necessary for the tools to support rather than undermine public legitimacy.

Core claim

This article proposes a community-informed approach to developing multi-perspective AI tools for government accountability, illustrated by an inductive research project building tools to analyze body-worn camera footage of traffic stops conducted by the Los Angeles Police Department, with emphasis on the role of social scientists in integrating perspectives of diverse stakeholders.

What carries the argument

The community-informed approach, in which social scientists on multidisciplinary teams integrate the perspectives of diverse stakeholders into the development of AI tools for police and government accountability.

If this is right

  • AI tools for reviewing police interactions will produce outputs that better match community standards of accountability.
  • Analysis of body-worn camera footage will become scalable while remaining aligned with public expectations of transparency.
  • Government AI projects in accountability domains will routinely require social scientists to translate stakeholder input into model design.
  • Democratic legitimacy of automated oversight systems will depend on explicit mechanisms for community perspective inclusion.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same integration process could apply to AI systems used in other government functions that affect citizens directly.
  • It offers a design-time route to addressing bias concerns instead of relying solely on post-training adjustments.
  • Testing the method in additional cities or interaction types would reveal whether the role of social scientists generalizes.

Load-bearing premise

Social scientists on multidisciplinary teams can successfully integrate the perspectives of diverse stakeholders into AI tool development without compromising model performance or introducing new biases.

What would settle it

A controlled comparison in which community members rate the accountability judgments of a standard AI model against those of a community-informed model and find no difference or preference for the non-informed version.

read the original abstract

Face-to-face interactions between police officers and the public affect both individual well-being and democratic legitimacy. Many government-public interactions are captured on video, including interactions between police officers and drivers captured on bodyworn cameras (BWCs). New advances in AI technology enable these interactions to be analyzed at scale, opening promising avenues for improving government transparency and accountability. However, for AI to serve democratic governance effectively, models must be designed to include the preferences and perspectives of the governed. This article proposes a community-informed, approach to developing multi-perspective AI tools for government accountability. We illustrate our approach by describing the research project through which the approach was inductively developed: an effort to build AI tools to analyze BWC footage of traffic stops conducted by the Los Angeles Police Department. We focus on the role of social scientists as members of multidisciplinary teams responsible for integrating the perspectives of diverse stakeholders into the development of AI tools in the domain of police -- and government -- accountability.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

0 major / 3 minor

Summary. The manuscript proposes a community-informed, inductive approach to developing multi-perspective AI tools for analyzing body-worn camera (BWC) footage to support police and government accountability. It illustrates the approach via a description of its development in a project focused on traffic stops by the Los Angeles Police Department, with emphasis on the integrative role of social scientists within multidisciplinary teams.

Significance. The normative argument that AI models for democratic governance must incorporate the perspectives of the governed is clearly articulated and grounded in an existing project. The inductive, project-based illustration supplies a practical template that could inform future work on stakeholder-inclusive AI design in public-sector applications.

minor comments (3)
  1. [Abstract] Abstract: the phrase 'multi-perspective AI tools' is introduced without a concise definition or example of what counts as a distinct 'perspective' (e.g., officer, driver, community observer), which would aid readers new to the framework.
  2. [Project description section] The manuscript would benefit from one or two concrete, anonymized examples of how a specific community input altered model requirements, annotation guidelines, or evaluation criteria during the LAPD project; the current high-level description leaves the integration mechanism somewhat abstract.
  3. [Introduction or related-work section] A short discussion of how the approach differs from or builds upon existing participatory-AI or value-sensitive-design literature would help situate the contribution.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive assessment of our manuscript, the recognition of its normative argument and practical template, and the recommendation for minor revision. No specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity; position paper with no derivations or fitted claims

full rationale

The manuscript is a high-level position paper and project description advocating a community-informed methodology for AI tool development in police accountability. It contains no equations, parameters, quantitative predictions, or derivation chains. The central claim is presented as a normative design principle rather than an empirically derived result. No self-citations function as load-bearing uniqueness theorems, and the inductive development process is described without reducing any output to fitted inputs or self-referential definitions. The paper is self-contained as a methodological illustration.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper is a conceptual and methodological proposal; no quantitative free parameters, mathematical axioms, or new invented entities are introduced in the abstract.

axioms (1)
  • domain assumption Community perspectives can be effectively elicited and integrated into AI model design by social scientists without loss of technical validity.
    Invoked in the description of the multidisciplinary team role and the inductive development of the approach.

pith-pipeline@v0.9.0 · 5769 in / 1076 out tokens · 21441 ms · 2026-05-24T05:07:08.123347+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages · 1 internal anchor

  1. [1]

    In: Fodor, P., Montali, M., Calvanese, D., Roman, D

    Akhtar, Sohail, Valerio Basile, and Viviana Patti. “A New Measure of Polarization in the Annotation of Hate Speech.” In AI*IA 2019 – Advances in Artificial Intelligence, edited by Mario Alviano, Gianluigi Greco, and Francesco Scarcello, 588–603. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2019. https://doi.org/10.1007/978-3...

    work page doi:10.1007/978-3-030- 2019

  2. [2]

    Modeling Annotator Perspective and Polarized Opinions to Improve Hate Speech Detection

    Akhtar, Sohail, Valerio Basile, and Viviana Patti. “Modeling Annotator Perspective and Polarized Opinions to Improve Hate Speech Detection.” Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 8 (October 1, 2020): 151–54. https://doi.org/10.1609/hcomp.v8i1.7473

    work page doi:10.1609/hcomp.v8i1.7473 2020

  3. [3]

    Interacting with Cancer Patients: The Significance of Physicians’ Communication Behavior

    Arora, Neeraj K. “Interacting with Cancer Patients: The Significance of Physicians’ Communication Behavior.” Social Science & Medicine 57, no. 5 (September 1, 2003): 791–806. https://doi.org/10.1016/S0277-9536(02)00449-5

    work page doi:10.1016/s0277-9536(02)00449-5 2003

  4. [4]

    The Role of Officer Race and Gender in Police-Civilian Interactions in Chicago

    Ba, Bocar A., Dean Knox, Jonathan Mummolo, and Roman Rivera. “The Role of Officer Race and Gender in Police-Civilian Interactions in Chicago.” Science 371, no. 6530 (February 12, 2021): 696–702

    work page 2021

  5. [5]

    Refusal in Data Ethics: Re-Imagining the Code Beneath the Code of Computation in the Carceral State

    Barabas Barabas, Chelsea. “Refusal in Data Ethics: Re-Imagining the Code Beneath the Code of Computation in the Carceral State.” SSRN Scholarly Paper. Rochester, NY, April 27, 2022. https://doi.org/10.2139/ssrn.4094977. 8

    work page doi:10.2139/ssrn.4094977 2022

  6. [6]

    Studying up: Reorienting the Study of Algorithmic Fairness around Issues of Power

    Barabas, Chelsea, Colin Doyle, JB Rubinovitz, and Karthik Dinakar. “Studying up: Reorienting the Study of Algorithmic Fairness around Issues of Power.” In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 167–76. FAccT ’20. New York, NY, USA: Association for Computing Machinery, 2020

    work page 2020

  7. [7]

    Emotional Expressions Reconsidered: Challenges to Inferring Emotion From Human Facial Movements

    Barrett, Lisa Feldman, Ralph Adolphs, Stacy Marsella, Aleix M. Martinez, and Seth D. Pollak. “Emotional Expressions Reconsidered: Challenges to Inferring Emotion From Human Facial Movements.” Psychological Science in the Public Interest: A Journal of the American Psychological Society 20, no. 1 (July 2019): 1–68. https://doi.org/10.1177/1529100619832930

    work page doi:10.1177/1529100619832930 2019

  8. [8]

    Benjamin, Ruha. 2019. Race After Technology: Abolitionist Tools for the New Jim Code. New York: Polity Press

    work page 2019

  9. [9]

    Ticketing and Turnout: The Participatory Consequences of Low-Level Police Contact

    Ben-Menachem, Jonathan, and Kevin T. Morris. “Ticketing and Turnout: The Participatory Consequences of Low-Level Police Contact.” American Political Science Review 117, no. 3 (August 2023): 822–34. https://doi.org/10.1017/S0003055422001265

    work page doi:10.1017/s0003055422001265 2023

  10. [10]

    The Conditional Legitimacy of Behavior Change Advice in Primary Care

    Bergen, Clara. “The Conditional Legitimacy of Behavior Change Advice in Primary Care.” Social Science & Medicine 255 (June 1, 2020): 112985. https://doi.org/10.1016/j.socscimed.2020.112985

    work page doi:10.1016/j.socscimed.2020.112985 2020

  11. [11]

    Legitimacy, Communication, and Leadership in the Turnaround Game

    Brandts, Jordi, David J. Cooper, and Roberto A. Weber. “Legitimacy, Communication, and Leadership in the Turnaround Game.” Management Science 61, no. 11 (November 2015): 2627–

    work page 2015

  12. [12]

    https://doi.org/10.1287/mnsc.2014.2021

    work page doi:10.1287/mnsc.2014.2021 2014

  13. [13]

    How (Not) to Write a Privacy Law,

    Cohen, Julie. “How (Not) to Write a Privacy Law,” 2023. http://knightcolumbia.org/content/how- not-to-write-a-privacy-law

    work page 2023

  14. [14]

    Pulled Over: How Police Stops Define Race and Citizenship

    Epp, Charles R., Steven Maynard-Moody, and Donald Haider-Markel. Pulled Over: How Police Stops Define Race and Citizenship. University of Chicago Press, 2014

    work page 2014

  15. [15]

    Developing Speech Processing Pipelines for Police Accountability

    Field, Anjalie, Prateek Verma, Nay San, Jennifer L. Eberhardt, and Dan Jurafsky. “Developing Speech Processing Pipelines for Police Accountability.” arXiv, June 9, 2023. https://doi.org/10.48550/arXiv.2306.06086

    work page doi:10.48550/arxiv.2306.06086 2023

  16. [16]

    Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task 9 Learning

    Fornaciari, Tommaso, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, and Massimo Poesio. “Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task 9 Learning.” In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2591–97. Associatio...

    work page 2021

  17. [17]

    Aggressive Policing and the Mental Health of Young Urban Men

    Geller, Amanda, Jeffrey Fagan, Tom Tyler, and Bruce G. Link. “Aggressive Policing and the Mental Health of Young Urban Men.” American Journal of Public Health 104, no. 12 (December 2014): 2321–27. https://doi.org/10.2105/AJPH.2014.302046

    work page doi:10.2105/ajph.2014.302046 2014

  18. [18]

    Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data

    Gianfrancesco, Milena A., Suzanne Tamang, Jinoos Yazdany, and Gabriela Schmajuk. “Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data.” JAMA Internal Medicine 178, no. 11 (November 1, 2018): 1544–47 https://doi.org/10.1001/jamainternmed.2018.3763

    work page doi:10.1001/jamainternmed.2018.3763 2018

  19. [19]

    Combatting Police Discrimination in the Age of Big Data

    Goel, Sharad, Maya Perelman, Ravi Shroff, and David Alan Sklansky. “Combatting Police Discrimination in the Age of Big Data.” New Criminal Law Review 20, no. 2 (May 1, 2017): 181–232. https://doi.org/10.1525/nclr.2017.20.2.181

    work page doi:10.1525/nclr.2017.20.2.181 2017

  20. [20]

    Ego4D: Around the World in 3,000 Hours of Egocentric Video,

    Grauman, Kristen, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, et al. “Ego4D: Around the World in 3,000 Hours of Egocentric Video,” 18995–12, 2022. https://openaccess.thecvf.com/content/CVPR2022/html/Grauman_Ego4D_Around_the_World_in _3000_Hours_of_Egocentric_Video_CVPR_2022_paper.html

    work page 2022

  21. [21]

    Deep Multiple Instance Learning for Foreground Speech Localization in Ambient Audio from Wearable Devices

    Hebbar, Rajat, Pavlos Papadopoulos, Ramon Reyes, Alexander F. Danvers, Angelina J. Polsinelli, Suzanne A. Moseley, David A. Sbarra, Matthias R. Mehl, and Shrikanth Narayanan. “Deep Multiple Instance Learning for Foreground Speech Localization in Ambient Audio from Wearable Devices.” EURASIP Journal on Audio, Speech, and Music Processing 2021, no. 1 (Febru...

    work page doi:10.1186/s13636-020-00194-0 2021

  22. [22]

    Perceptions of Social Behavior: Evidence of Differing Expectations for Interpersonal and Intergroup Interaction

    Hoyle, Rick H., Robin L. Pinkley, and Chester A. Insko. “Perceptions of Social Behavior: Evidence of Differing Expectations for Interpersonal and Intergroup Interaction.” Personality and Social Psychology Bulletin 15, no. 3 (September 1, 1989): 365–76. https://doi.org/10.1177/0146167289153007

    work page doi:10.1177/0146167289153007 1989

  23. [23]

    Penal Code § 630-638.55

    Invasion of Privacy Act (1967), Cal. Penal Code § 630-638.55. 10

    work page 1967

  24. [24]

    What If Ground Truth Is Subjective? Personalized Deep Neural Hate Speech Detection

    Kanclerz, Kamil, Marcin Gruza, Konrad Karanowski, Julita Bielaniewicz, Piotr Milkowski, Jan Kocon, and Przemyslaw Kazienko. “What If Ground Truth Is Subjective? Personalized Deep Neural Hate Speech Detection.” In Proceedings of the 1st Workshop on Perspectivist Approaches to NLP @LREC2022, edited by Gavin Abercrombie, Valerio Basile, Sara Tonelli, Verena ...

    work page 2022

  25. [25]

    Administrative Records Mask Racially Biased Policing

    Knox, Dean, Will Lowe, and Jonathan Mummolo. “Administrative Records Mask Racially Biased Policing.” American Political Science Review 114, no. 3 (August 2020): 619–37. https://doi.org/10.1017/S0003055420000039

    work page doi:10.1017/s0003055420000039 2020

  26. [26]

    Aggressive Policing and the Educational Performance of Minority Youth

    Legewie, Joscha, and Jeffrey Fagan. “Aggressive Policing and the Educational Performance of Minority Youth.” American Sociological Review 84, no. 2 (April 1, 2019): 220–47. https://doi.org/10.1177/0003122419826020

    work page doi:10.1177/0003122419826020 2019

  27. [27]

    Implementing a Body- Worn Camera Program: Recommendations and Lessons Learned,

    Miller, Lindsay, Jessica Toliver, and Police Executive Research Forum. “Implementing a Body- Worn Camera Program: Recommendations and Lessons Learned,” September 12, 2014. https://policycommons.net/artifacts/3333634/implementing-a-body-worn-camera- program/4132482/

    work page arXiv 2014

  28. [28]

    Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations

    Mostafazadeh Davani, Aida, Mark Díaz, and Vinodkumar Prabhakaran. “Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations.” Edited by Brian Roark and Ani Nenkova. Transactions of the Association for Computational Linguistics 10 (2022): 92–110. https://doi.org/10.1162/tacl_a_00449

    work page doi:10.1162/tacl_a_00449 2022

  29. [29]

    Policy – Limitation on the Use of Pretextual Stops – Established

    Office of the Chief of Police. 2022. Special Order No. 3. “Policy – Limitation on the Use of Pretextual Stops – Established.” Available at: https://lapdonlinestrgeacc.blob.core.usgovcloudapi.net/lapdonlinemedia/2022/03/3_9_22_SO_No ._3_Policy_Limitation_on_Use_of_Pretextual_Stops_Established.pdf

    work page 2022

  30. [30]

    Human Uncertainty Makes Classification More Robust,

    Peterson, Joshua C., Ruairidh M. Battleday, Thomas L. Griffiths, and Olga Russakovsky. “Human Uncertainty Makes Classification More Robust,” 9617–26, 2019. https://openaccess.thecvf.com/content_ICCV_2019/html/Peterson_Human_Uncertainty_Makes_ Classification_More_Robust_ICCV_2019_paper.html

    work page 2019

  31. [31]

    Truth as White Property: Solidifying White Epistemology and Owning Racial Knowledge

    Pham, Vincent N. “Truth as White Property: Solidifying White Epistemology and Owning Racial Knowledge.” Communication and Critical/Cultural Studies 20, no. 2 (April 3, 2023): 288–305. https://doi.org/10.1080/14791420.2023.2199831. 11

    work page doi:10.1080/14791420.2023.2199831 2023

  32. [32]

    A Large-Scale Analysis of Racial Disparities in Police Stops across the United States

    Pierson, Emma, Camelia Simoiu, Jan Overgoor, Sam Corbett-Davies, Daniel Jenson, Amy Shoemaker, Vignesh Ramachandran, et al. “A Large-Scale Analysis of Racial Disparities in Police Stops across the United States.” Nature Human Behaviour 4, no. 7 (July 2020): 736–45. https://doi.org/10.1038/s41562-020-0858-1

    work page doi:10.1038/s41562-020-0858-1 2020

  33. [33]

    Linguistically Debatable or Just Plain Wrong?

    Plank, Barbara, Dirk Hovy, and Anders Søgaard. “Linguistically Debatable or Just Plain Wrong?” In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), edited by Kristina Toutanova and Hua Wu, 507–11. Baltimore, Maryland: Association for Computational Linguistics, 2014. https://doi.org/10.3115/v1...

    work page doi:10.3115/v1/p14- 2014

  34. [34]

    On Releasing Annotator-Level Labels and Information in Datasets

    Prabhakaran, Vinodkumar, Aida Mostafazadeh Davani, and Mark Díaz. “On Releasing Annotator-Level Labels and Information in Datasets.” arXiv, October 11, 2021. https://doi.org/10.48550/arXiv.2110.05699

    work page doi:10.48550/arxiv.2110.05699 2021

  35. [35]

    Robust Speech Recognition via Large-Scale Weak Supervision

    Radford, Alec, Jong Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. “Robust Speech Recognition via Large-Scale Weak Supervision.” arXiv, December 6,

    work page

  36. [36]

    https://doi.org/10.48550/arXiv.2212.04356

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2212.04356

  37. [37]

    Differing Perceptions: How Students of Color and White Students Perceive Campus Climate for Underrepresented Groups

    Rankin, Susan R, and Robert Dean Reason. “Differing Perceptions: How Students of Color and White Students Perceive Campus Climate for Underrepresented Groups.” Journal of College Student Development 46, no. 1 (2005): 43–61

    work page 2005

  38. [38]

    Escalated Police Stops of Black Men Are Linguistically and Psychologically Distinct in Their Earliest Moments

    Rho, Eugenia H., Maggie Harrington, Yuyang Zhong, Reid Pryzant, Nicholas P. Camp, Dan Jurafsky, and Jennifer L. Eberhardt. “Escalated Police Stops of Black Men Are Linguistically and Psychologically Distinct in Their Earliest Moments.” Proceedings of the National Academy of Sciences 120, no. 23 (June 6, 2023): e2216162120. https://doi.org/10.1073/pnas.2216162120

    work page doi:10.1073/pnas.2216162120 2023

  39. [39]

    Police Body-Worn Camera Footage Access Map - RCFP

    The Reporters Committee for Freedom of the Press. “Police Body-Worn Camera Footage Access Map - RCFP.” Accessed October 31, 2023. https://www.rcfp.org/resources/bodycams/

    work page 2023

  40. [40]

    Detecting Racial Bias in Algorithms and Machine Learning

    Turner Lee, Nicol. “Detecting Racial Bias in Algorithms and Machine Learning.” Journal of Information, Communication and Ethics in Society 16, no. 3 (January 1, 2018): 252–60. https://doi.org/10.1108/JICES-06-2018-0056. 12

    work page doi:10.1108/jices-06-2018-0056 2018

  41. [41]

    Law Enforcement: DOJ Can Improve Publication of Use of Force Data and Oversight of Excessive Force Allegations | U.S. GAO,

    U.S. Government Accountability Office. “Law Enforcement: DOJ Can Improve Publication of Use of Force Data and Oversight of Excessive Force Allegations | U.S. GAO,” December 7,

    work page

  42. [42]

    https://www.gao.gov/products/gao-22-104456

    work page

  43. [43]

    Language from Police Body Camera Footage Shows Racial Disparities in Officer Respect

    Voigt, Rob, Nicholas P. Camp, Vinodkumar Prabhakaran, William L. Hamilton, Rebecca C. Hetey, Camilla M. Griffiths, David Jurgens, Dan Jurafsky, and Jennifer L. Eberhardt. “Language from Police Body Camera Footage Shows Racial Disparities in Officer Respect.” Proceedings of the National Academy of Sciences 114, no. 25 (June 20, 2017): 6521–26. https://doi....

    work page doi:10.1073/pnas.1702413114 2017

  44. [44]

    All in One: Exploring Unified Video-Language Pre-Training,

    Wang, Jinpeng, Yixiao Ge, Rui Yan, Yuying Ge, Kevin Qinghong Lin, Satoshi Tsutsui, Xudong Lin, et al. “All in One: Exploring Unified Video-Language Pre-Training,” 6598–6608, 2023. https://openaccess.thecvf.com/content/CVPR2023/html/Wang_All_in_One_Exploring_Unified_ Video-Language_Pre-Training_CVPR_2023_paper.html

    work page 2023

  45. [45]

    Multiview Transformers for Video Recognition,

    Yan, Shen, Xuehan Xiong, Anurag Arnab, Zhichao Lu, Mi Zhang, Chen Sun, and Cordelia Schmid. “Multiview Transformers for Video Recognition,” 3333–43, 2022. https://openaccess.thecvf.com/content/CVPR2022/html/Yan_Multiview_Transformers_for_Vide o_Recognition_CVPR_2022_paper.html

    work page 2022

  46. [46]

    As Body-Worn Cameras Proliferate, States’ Access Restrictions Defeat Their Purpose

    Zansberg, Steve. “As Body-Worn Cameras Proliferate, States’ Access Restrictions Defeat Their Purpose.” Communications Lawyer 32 (2017 2016): 12

    work page 2017

  47. [47]

    The Stanford Open Policing Project

    “The Stanford Open Policing Project.” Accessed November 3, 2023. https://openpolicing.stanford.edu/

    work page 2023

  48. [48]

    1050. Scope of 18 U.S.C § 2511 Prohibitions,

    “1050. Scope of 18 U.S.C § 2511 Prohibitions,” February 19, 2015. https://www.justice.gov/archives/jm/criminal-resource-manual-1050-scope-18-usc-2511- prohibitions

    work page 2015