Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Jordan Vice"'
Publikováno v:
Remote Sensing, Vol 16, Iss 13, p 2266 (2024)
Semantic scene completion is a crucial outdoor scene understanding task that has direct implications for technologies like autonomous driving and robotics. It compensates for unavoidable occlusions and partial measurements in LiDAR scans, which may o
Externí odkaz:
https://doaj.org/article/f8bc1c8b6dbf4dbe9906f4446ab1b669
Autor:
Masood M. Khan, Jordan Vice
Publikováno v:
IEEE Access, Vol 10, Pp 99686-99701 (2022)
Like other Artificial Intelligence (AI) systems, Machine Learning (ML) applications cannot explain decisions, are marred with training-caused biases, and suffer from algorithmic limitations. Their eXplainable Artificial Intelligence (XAI) capabilitie
Externí odkaz:
https://doaj.org/article/d4acc913294843c7ae43b86b88830b9a
Autor:
Jordan Vice, Masood Mehmood Khan
Publikováno v:
IEEE Access, Vol 10, Pp 36091-36105 (2022)
This paper builds upon the theoretical foundations of the Accountable eXplainable Artificial Intelligence (AXAI) capability framework presented in part one of this paper. We demonstrate incorporation of the AXAI capability in the real time Affective
Externí odkaz:
https://doaj.org/article/18e136b866f649a9a1ff4d84608b267b
Models of seven discrete facial expressions are built on macro-level facial muscle variations for separating distinct affective states. We propose a step-wise Hierarchical Separation and Classification Network (HSCN) that discovers dynamic and contin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c1fe9bb4fdb0e0d7117b499a7f667e2
https://doi.org/10.36227/techrxiv.21951752
https://doi.org/10.36227/techrxiv.21951752
Publikováno v:
2022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ed37f260b75506d7486ead36e20a5b38
https://doi.org/10.1109/eais51927.2022.9787730
https://doi.org/10.1109/eais51927.2022.9787730
Publikováno v:
2022 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6e0cc2769eba2f4497b634398d730a6f
https://doi.org/10.1109/eais51927.2022.9787693
https://doi.org/10.1109/eais51927.2022.9787693
Autor:
Masood Mehmood Khan, Jordan Vice
This paper builds upon the theoretical foundations of the Accountable explainable Artificial Intelligence (AXAI) capability framework presented in part one of this paper. This part demonstrates the incorporation of the AXAI capability in the real tim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c6d8128d10fadee827a3096439c7c1c3
https://doi.org/10.36227/techrxiv.19102094.v1
https://doi.org/10.36227/techrxiv.19102094.v1
Publikováno v:
CogMI
Most affect classification schemes rely on near accurate single-cue models resulting in less than required accuracy under certain peculiar conditions. We investigate how the holism of a multimodal solution could be exploited for affect classification
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97eff5002dc5712c78fd75577ccd3c68
https://doi.org/10.1109/cogmi48466.2019.00020
https://doi.org/10.1109/cogmi48466.2019.00020