Code for the paper "Visual Sentiment Analysis for Review Images with Item-Oriented and User-Oriented CNN", ACM MM'17

PyTorch port of models for Visual Sentiment Analysis pre-trained on the T4SA dataset.

Evaluating multiple novel approaches for adjective use in image captioning.

HCMUS Selab at Mediaeval 21: Visual Sentiment Analysis

Code to reproduce "The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal Distillation". This project trains visual models for Sentiment Analysis in the Twitter domain using a cross-modal student-teacher approach.

Code for paper "OSANet: Object Semantic Attention Network for Visual Sentiment Analysis"

Code as a part of Research Topic on Sentiment Extraction from Images using Latent Textual Features and Joint Embeddings Approach

"TinyEmo: Scaling down Emotional Reasoning via Metric Projection" ACMCV 2024

MLLMsent is a research framework for investigating sentiment reasoning in MultiModal Large Language Models (MLLMs). It provides end-to-end tools for sentiment analysis from visual content, focusing on how images communicate sentiment through complex, scene-level semantics.

Code of the paper "Design and Deployment of an Image Polarity Detector with Visual Attention" by Ragusa et al.