Create and release your Profile on Zintellect – Postdoctoral applicants must create an account and complete a profile in the on-line application system. Please note: your resume/CV may not exceed 3 pages.
Complete your application – Enter the rest of the information required for the IC Postdoc Program Research Opportunity. The application itself contains detailed instructions for each one of these components: availability, citizenship, transcripts, dissertation abstract, publication and presentation plan, and information about your Research Advisor co-applicant.
Additional information about the IC Postdoctoral Research Fellowship Program is available on the program website located at: https://orise.orau.gov/icpostdoc/index.html.
If you have questions, send an email to ICPostdoc@orau.org. Please include the reference code for this opportunity in your email.
Research Topic Description, including Problem Statement:
Facial recognition technology has been a longstanding challenge in the field of computer vision, with existing applications struggling to achieve accuracy in diverse real-world scenarios. Despite recent advances, there remains a need for further research to overcome the limitations of current methods and improve their robustness, particularly in situations where faces are partially occluded, poorly lit, or exhibit varying expressions.
This research topic investigates the use of new models, such as vision transformers, for facial recognition, with a focus on developing techniques to accurately evaluate the confidence of matches and interpret the embedding space. A key limitation of current systems is that they do not scale into downstream use cases as their inaccuracies compound, limiting their applicability. The research might also explore the combination of multiple modalities, such as audio and face recognition, and the incorporation of video data to enhance the accuracy of systems. Finally, the project would examine the potential applications of the developed techniques for other embedding searches, such as sentence embeddings.
Proposals are likely to approach this Topic from an applied vision transformers (ViT) perspective. A literature review with respect to facial recognition and recently emerging associated fields could inform experimental work, e.g. AI/ML enhanced ViT, may be relevant.
Relevance to the Intelligence Community:
Facial recognition technology plays a critical role in various NIC applications, including identity verification and counter-surveillance. Advancements in this field may:
The proposed research aims to push the boundaries of what is currently possible, which can potentially lead to breakthroughs in operational effectiveness, legal compliance and efficiency. Furthermore, the exploration of multimodal fusion and video analysis may expand the scope of applicable scenarios, providing valuable insights and tools for the NIC.
Zhonglin Sun, Georgios Tzimiropoulos (2022) 'Part-based face recognition with vision transformers', arXiv:2212.00057 [cs. CV], https://doi.org/10.48550/arXiv .2212.00057.
Key Words: facial recognition, vision transformers (ViT), machine learning, video sense-making, real time analysis, video multimodal fusion.