M. Zeeshan Zia

Information Technology University — Pakistan

Engineering · Physical Sciences

15h-index1.0kcitations29works3.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Robotics and Sensor-Based Localization(15), Advanced Neural Network Applications(10), Human Pose and Action Recognition(10), Advanced Vision and Imaging(9), Advanced Image and Video Retrieval Techniques(7)

Publications29 total

Multiview Commonsense Reasoning Using LLMs for Understanding Crime Drama Series
Lecture notes in computer science·2026
Towards trustworthy AI-driven leukemia diagnosis: A hybrid Hierarchical Federated Learning and explainable AI framework
Informatics in Medicine Unlocked·2025· 9 citedOpen Access
Learning by Aligning 2D Skeleton Sequences and Multi-modality Fusion
Lecture notes in computer science·2024· 2 cited
AI-mediated Job Status Tracking in AR as a No-Code service
2022 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)·2022· 2 cited
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 48 cited
Learning by Aligning Videos in Time
2021· 1 citedOpen Access
Unsupervised Activity Segmentation by Joint Representation Learning and Online Clustering.
arXiv (Cornell University)·2021· 5 citedOpen Access
Towards Anomaly Detection in Dashcam Videos
2020Open Access
Weakly-supervised action localization based on seed superpixels
Multimedia Tools and Applications·2020· 5 cited
Domain-Specific Priors and Meta Learning for Few-Shot First-Person\n Action Recognition
arXiv (Cornell University)·2019· 30 citedOpen Access
Deep Supervision with Intermediate Concepts
IEEE Transactions on Pattern Analysis and Machine Intelligence·2018· 85 citedOpen Access
Deep Supervision with Intermediate Concepts
arXiv (Cornell University)·2018· 4 citedOpen Access
Single- and two-person action recognition based on silhouette shape and optical point descriptors
Signal Image and Video Processing·2018· 17 cited
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Lecture notes in computer science·2018· 2 citedOpen Access
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
2017· 91 cited
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
arXiv (Cornell University)·2016· 9 citedOpen Access
Integrating Algorithmic Parameters into Benchmarking and Design Space Exploration in 3D Scene Understanding
2016· 44 citedOpen Access
Monocular reconstruction of vehicles: Combining SLAM with shape priors
2016· 40 cited
Towards Scene Understanding with Detailed 3D Object Representations
International Journal of Computer Vision·2014· 86 citedOpen Access
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects
2014· 92 cited
page 1 of 2Next →

Frequent Co-authors

Quoc-Huy Tran(11), Michael Stark(6), Konrad Schindler(6), Manmohan Chandraker(5), Andrey Konin(5), Gregory D. Hager(4), Sateesh Kumar(4), Sanjay Haresh(4), Luigi Nardi(3), Bruno Bodin(3), Paul H. J. Kelly(3), Chi Li(3), Bernt Schiele(2), John Mawer(2), Andy Nisbet(2), Andrew J. Davison(2), Mikel Luján(2), Michael O’Boyle(2), Xiang Yu(2), Awais Ahmed(2)