This is the official implementation of the ICMR24 paper "UBiSS: A Unified Framework for Bimodal Semantic Summarization of Videos"

The official code of "CSTA: CNN-based Spatiotemporal Attention for Video Summarization"

Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"

DSNet: A Flexible Detect-to-Summarize Network for Video Summarization

Official code and dataset link for ''VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles''

Implementation of the paper "wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations" in Pytorch.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Source code for the paper "Unsupervised Video Summarization via Multi-source Features" published at ICMR 2021

Pytorch implementation for "Video Joint Modelling Based on Hierarchical Transformer for Co-summarization"

A PyTorch reimplementation of FCSN in paper "Video Summarization Using Fully Convolutional Sequence Networks"

The official implementation of 'Align and Attend: Multimodal Summarization with Dual Contrastive Losses' (CVPR 2023)

A computing solution based on deep learning that allows the efficient generation of keyshot type spotlights from videos.

Deep learning model for supervised video summarization called Multi Source Visual Attention (MSVA)