T
Tasweer Ahmad
Researcher at South China University of Technology
Publications - 18
Citations - 432
Tasweer Ahmad is an academic researcher from South China University of Technology. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 7, co-authored 14 publications receiving 234 citations. Previous affiliations of Tasweer Ahmad include Government College University.
Papers
More filters
Journal ArticleDOI
A New CNN-Based Method for Multi-Directional Car License Plate Detection
TL;DR: A CNN-based MD-YOLO framework for multi-directional car license plate detection that can elegantly manage rotational problems in real-time scenarios and outperforms over other existing state-of-the-art methods in terms of better accuracy and lower computational cost.
Journal ArticleDOI
A Review on Human Actions Recognition Using Vision Based Techniques
TL;DR: A detailed review of the latest vision based techniques consists of: 1. Methods, 2. Systems, 3. Quantitative evaluation, and 4. merits and demerits.
Journal ArticleDOI
Action Recognition Using Attention-Joints Graph Convolutional Neural Networks
TL;DR: The proposed methodology has been evaluated on single image Stanford 40-Actions dataset, as well as on temporal skeleton-based action recognition PKU-MDD and NTU-RGBD datasets, and shows that this framework outperforms existing state-of-the-art methods.
Journal ArticleDOI
Using Discrete Cosine Transform Based Features for Human Action Recognition
TL;DR: A discrete cosine transform based features have been exploited for action recognition and K-Nearest Neighbor (K-NN) classifier is used for classification.
Journal ArticleDOI
Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive Survey
TL;DR: A comprehensive overview of recent GCN techniques for action recognition is presented, a taxonomy for the categorization of GCN Techniques is proposed, a detailed study of the benchmark datasets is carried out, relevant resources and opensource codes are enlisted, and an outline for future research directions and trends is provided.