Deep Visual-Semantic Alignments for Generating Image Descriptions

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Unified Framework for Multimodal Domain Adaptation (2018, methodology): “For the source domain, we use the MSCOCO dataset [36] and select training split from [30] which contains 113,287 images, along with one caption each.”
Exploring Hate Speech Detection in Multimodal Publications (2019, methodology): “This approach is applied in tasks such as image captioning [14, 13] and multimodal image retrieval [9, 8].”
Artificial intelligence in radiology (2018, unknown): “Following deep learning advances in the automatic caption generation from photographic images 86 , recent efforts have explored means to diagnose abnormalities in chest radiography scans and automatically annotate them in a textual format 87 .”
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples (2017, background): “variety of NLP tasks ranging from machine translation [5, 6] and automatic response generation [20, 21, 22, 23] to semantic constituency parsing [24], and generation of textual descriptions from visual data [25, 26].”
A Survey on Deep Learning for Multimodal Data Fusion (2020, methodology): “Aiming to address the limitation that current visual recognition systems cannot generate rich descriptions for images at a glance, a multimodal alignment model is presented by bridging the inter-modal relationship between visual and text data (Karpathy & Li, 2017).”