A vision explainability method for image captioning using transformer decoder attention maps
Open Access
Abstract
No abstract availableKeywords
This publication has 7 references indexed in Scilit:
- Stochastic Models for Autonomous Systems and RoboticsSpectrum of Operational Research, 2026
- Estimation of Automatic License Plate Recognition Using Deep Learning AlgorithmsSpectrum of Decision Making and Applications, 2024
- Style-Enhanced Transformer for Image Captioning in Construction ScenesEntropy, 2024
- Transformer-based visual object tracking via fine–coarse concatenated attention and cross concatenated MLPPattern Recognition, 2023
- Automatic image captioning system based on augmentation and ranking mechanismSignal, Image and Video Processing, 2023
- Image Captioning Encoder–Decoder Models Using CNN-RNN Architectures: A Comparative StudyCircuits, Systems, and Signal Processing, 2022
- ACORT: A compact object relation transformer for parameter efficient image captioningNeurocomputing, 2022