A
Asish Bera
Researcher at Edge Hill University
Publications - 21
Citations - 162
Asish Bera is an academic researcher from Edge Hill University. The author has contributed to research in topics: Biometrics & Convolutional neural network. The author has an hindex of 4, co-authored 18 publications receiving 53 citations. Previous affiliations of Asish Bera include VLSI Technology & Haldia Institute of Technology.
Papers
More filters
Posted Content
Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
TL;DR: This work proposes a novel context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients, and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding-box and/or distinguishable part annotations.
Journal ArticleDOI
Attend and Guide (AG-Net): A Keypoints-driven Attention-based Deep Network for Image Recognition
TL;DR: Zhang et al. as discussed by the authors proposed an end-to-end CNN model, which learns meaningful features linking fine-grained changes using a keypoints-based attention mechanism for visual recognition in still images.
Proceedings Article
Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification
TL;DR: Zhang et al. as mentioned in this paper proposed a context-aware attentional pooling (CAP) that effectively captures subtle changes via sub-pixel gradients and learns to attend informative integral regions and their importance in discriminating different subcategories without requiring the bounding box and/or distinguishable part annotations.
Journal ArticleDOI
Human Identification Using Selected Features From Finger Geometric Profiles
TL;DR: A finger biometric system at an unconstrained environment at the preprocessing stage that decomposes the main hand contour into finger-level shape representation and the rank-based forward–backward greedy algorithm is followed to select relevant features and to enhance classification accuracy.
Journal ArticleDOI
Attend and Guide (AG-Net): A Keypoints-Driven Attention-Based Deep Network for Image Recognition
TL;DR: Zhang et al. as mentioned in this paper proposed an end-to-end CNN model, which learns meaningful features linking fine-grained changes using a keypoints-based attention mechanism.