Abstract Automatic Visual Captioning (AVC) generates syntactically and semantically correct
sentences by describing important objects, attributes, and their relationships with each other …

Few-shot learning is a challenging task, which aims to learn a classifier for novel classes
with few examples. Pre-training based meta-learning methods effectively tackle the problem …

The focus of this survey is on the analysis of two modalities of multimodal deep learning:
image and text. Unlike classic reviews of deep learning where monomodal image classifiers …

Emotion recognition in user-generated videos plays an important role in human-centered
computing. Existing methods mainly employ traditional two-stage shallow pipeline, ie …

Image captioning, aiming at generating natural sentences to describe image contents, has
received significant attention with remarkable improvements in recent advances. The …

Emotion cause analysis has elicited wide interest in both academia and industry, and aims
to identify the reasons behind certain emotions expressed in text. Most of the current studies …

Existing methods on visual emotion analysis mainly focus on coarse-grained emotion
classification, ie assigning an image with a dominant discrete emotion category. However …

Studies of image captioning are shifting towards a trend of a fully end-to-end paradigm by
leveraging powerful visual pre-trained models and transformer-based generation …

Image captioning using encoder–decoder-based approach where CNN is used as the
Encoder and sequence generator like RNN as Decoder has proven to be very effective …

Fine-grained image captioning is gaining traction in multimedia, merging vision-to-language
tasks, with attribute selection now recognized as pivotal in improving performance. While …