Video Background Music Generation with Controllable Music Transformer (ACM MM 2021 Best Paper Award)

深度学习经典、新论文逐段精读

Official implementation of compound word transformer (AAAI'21)

Official implementation of VAANet for Emotion Recognition (AAAI2020)

Command-line program to download videos from YouTube.com and other video sites

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

PyTorch Implementation of FastSpeech 2 : Fast and High-Quality End-to-End Text to Speech

The release of the HoK400 and CFM400 datasets.

These scripts generate the "color fingerprint" of a movie by clustering the dominant colors through time.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Starter code for working with the YouTube-8M dataset.

PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

A Machine Learning Approach of Emotional Model

Deep learning library featuring a higher-level API for TensorFlow.

This repository presents UR-FUNNY dataset: first dataset for multimodal humor detection

PyTorch implementation of ECCV 2020 paper "Foley Music: Learning to Generate Music from Videos "

Code and dataset of "MEmoR: A Dataset for Multimodal Emotion Reasoning in Videos" in MM'20.

code for Confidence-aware Non-repetitive Multimodal Transformers for TextCaps (AAAI 2021)

Tools for movie and video research

Deep Learning Tutorial notes and code. See the wiki for more info.

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Code for "A Graph-Based Framework to Bridge Movies and Synopses", ICCV2019

Next Generation of ShadowsocksX

DeepMind's Tacotron-2 Tensorflow implementation

Multimodal Sarcasm Detection Dataset