MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

ImageNet-R(endition) and DeepAugment (ICCV 2021)

Code and Splits for the paper "A Fair and Comprehensive Comparison of Multimodal Tweet Sentiment Analysis Methods", In Proceedings of the 2021 Workshop on Multi-Modal Pre-Training for Multimedia Understanding (MMPT ’21), August 21, 2021,Taipei, Taiwan

CLUE code

Implementation for our IJCAI-21 paper --- AdaVQA: Overcoming Language Priors with Adapted Margin Loss.

The official Pytorch implementation of paper "FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification" accepted by MICCAI 2023

A Python toolkit for detecting and mitigating ethical bias in machine learning models. This project provides wrapper classes around IBM's AI Fairness 360 (AIF360) library to make bias detection and mitigation more accessible and easier to implement in machine learning pipelines.

Official code of "Discover the Unknown Biased Attribute of an Image Classifier" (ICCV 2021)

NAACL 2022 paper on Analyzing Modality Robustness in Multimodal Sentiment Analysis

[KDD 2021] Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System

The implementation of CubeMLP