L Xu, Q Tang, J Lv, B Zheng, X Zeng, W Li - Neurocomputing, 2023 - Elsevier
Image captioning, also called report generation in medical field, aims to describe visual content of images in human language, which requires to model semantic relationship …
Y Xiao, L Wu, J Guo, J Li, M Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and …
Z Fei, X Yan, S Wang, Q Tian - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Both accuracy and efficiency are crucial for image captioning in real-world scenarios. Although Transformer-based models have gained significant improved captioning …
Z Fei - proceedings of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
Recently, attention-based image captioning models, which are expected to ground correct image regions for proper word generations, have achieved remarkable performance …
Y Zhou, Y Zhang, Z Hu, M Wang - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Current state-of-the-art image captioning models adopt autoregressive decoders, ie they generate each word by conditioning on previously generated words, which leads to heavy …
Most image captioning models are autoregressive, ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference …
Z Fei, M Fan, L Zhu, J Huang, X Wei… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
It is well believed that the higher uncertainty in a word of the caption, the more inter- correlated context information is required to determine it. However, current image captioning …
Z Fei, M Fan, C Yu, D Li, J Huang - arXiv preprint arXiv:2404.04478, 2024 - arxiv.org
Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for …
Z Fei - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Current deep learning-based image captioning systems have been proven to store practical knowledge with their parameters and achieve competitive performances in the public …