From show to tell: A survey on deep learning-based image captioning
Connecting Vision and Language plays an essential role in Generative Intelligence. For this
reason, large research efforts have been devoted to image captioning, ie describing images …
reason, large research efforts have been devoted to image captioning, ie describing images …
Deep image captioning: A review of methods, trends and future challenges
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 …
content of images in human language, which requires to model semantic relationship …
A survey on non-autoregressive generation for neural machine translation and beyond
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 …
(NMT) to speed up inference, has attracted much attention in both machine learning and …
Deecap: Dynamic early exiting for efficient image captioning
Both accuracy and efficiency are crucial for image captioning in real-world scenarios.
Although Transformer-based models have gained significant improved captioning …
Although Transformer-based models have gained significant improved captioning …
Attention-aligned transformer for image 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 …
image regions for proper word generations, have achieved remarkable performance …
Semi-autoregressive transformer for image captioning
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 …
generate each word by conditioning on previously generated words, which leads to heavy …
Non-autoregressive image captioning with counterfactuals-critical multi-agent learning
Most image captioning models are autoregressive, ie they generate each word by
conditioning on previously generated words, which leads to heavy latency during inference …
conditioning on previously generated words, which leads to heavy latency during inference …
Uncertainty-aware image captioning
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 …
correlated context information is required to determine it. However, current image captioning …
Diffusion-rwkv: Scaling rwkv-like architectures for diffusion models
Transformers have catalyzed advancements in computer vision and natural language
processing (NLP) fields. However, substantial computational complexity poses limitations for …
processing (NLP) fields. However, substantial computational complexity poses limitations for …
Memory-augmented image captioning
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 …
knowledge with their parameters and achieve competitive performances in the public …