Generate image from music emotion. Starting from retrieve music information, predicting the valence and arousal values and eventually generate image with similar emotion.

Deepfake Detection Solution using Multimodal Approach.

Multimodal Agentic GenAI Workflow – Seamlessly blends retrieval and generation for intelligent storytelling

Multi-speaker diarization from video using SyncNet’s cross-modal embedding space to match multiple face tracks to corresponding audio tracks.

Experiments around using Multi-Modal Casual Attention with Multi-Grouped Query Attention

App to cheer you up with some awesome quotes when depressed using deep learning

Multimodal deep learning package that uses both categorical and text-based features in a single deep architecture for regression and binary classification use cases.

Deeplearning utils for multimodal research

Code and Models for Binding Text, Images, Graphs, and Audio for Music Representation Learning

Streamlit app for demonstrating multi-modal(vision+language) modelling in Pytorch.

Multi-Modal Representational Learning for Social Media Popularity Prediction

Enhanced fork of MISA integrating the MMLatch feedback mechanism for multimodal sentiment analysis.

Implementation of InstructPix2Pix from scratch

[IROS 2023] GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation

Mixed vision-language Attention Model that gets better by making mistakes

Preprocessing and feature extraction for raw voice data of DAIC-WOZ

Kedro pipelines for preprocessing text and tabular data for multi-modal ML in TensorFlow.

This repo contains the official PyTorch implementation of vLMIG: Improving Visual Commonsense in Language Models via Multiple Image Generation

Unofficial implementation for Sigmoid Loss for Language Image Pre-Training