A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Fully Convolutional CaptionNet: Siamese Difference Captioning Attention Model
2019
IEEE Access
INDEX TERMS Image captioning, deep learning, Siamese network, recurrent neural network, convolutional neural network, attention, fully convolutional networks. ...
Our extensive experiments indicate that the FCC model outperforms other learning models on the benchmark Spot-the-Diff datasets by generating succinct and meaningful textual differences in images. ...
Overall, our Fully Convolutional CaptionNet model presents improved features over other models and our updated contributions are as follows: • We propose a novel end-to-end encoder-decoder model that employs ...
doi:10.1109/access.2019.2957513
fatcat:4t7nsc62tze5hjq56rmvhruzsm
Features to Text: A Comprehensive Survey of Deep Learning on Semantic Segmentation and Image Captioning
2021
Complexity
With the emergence of deep learning, computer vision has witnessed extensive advancement and has seen immense applications in multiple domains. ...
Also, the semantic information capturing of objects and their attributes is presented in relation to their annotation generation. ...
Furthermore, the Siamese Difference Captioning Model (SDCM) also combined techniques from deep Siamese convolutional neural network, soft attention mechanism, word embedding, and bidirectional long short-term ...
doi:10.1155/2021/5538927
fatcat:4yae4kjqdne6vaqus5plna4mwm
Vision Transformers in Medical Computer Vision – A Contemplative Retrospection
[article]
2022
arXiv
pre-print
Moreover, to get more insight and deeper understanding, self-attention mechanism of transformers is also explained briefly. ...
Recent escalation in the field of computer vision underpins a huddle of algorithms with the magnificent potential to unravel the information contained within images. ...
Existing techniques, on the other hand, are more concerned with end-to-end automatic classification using computers than with human-computer interaction. Hence, Chen et al. ...
arXiv:2203.15269v1
fatcat:wecjpoikbvfz5cygytqpktoxdq