Repo for Visual Acoustic Matching, CVPR 2022

ObjectFolder Dataset

Audio-Visual Speech Separation with Cross-Modal Consistency

A first-of-its-kind acoustic simulation platform for audio-visual embodied AI research. It supports training and evaluating multiple tasks and applications.

VisualEchoes Dataset (ECCV 2020)

Reading list for research topics in embodied vision

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

Reading list for research topics in multimodal machine learning

Listen to Look: Action Recognition by Previewing Audio (CVPR 2020)

Scaling and Benchmarking Self-Supervised Visual Representation Learning

Co-Separating Sounds of Visual Objects (ICCV 2019)

2.5D visual sound

2.5D visual sound dataset

Learning to Separate Object Sounds by Watching Unlabeled Video (ECCV 2018)

Im2Flow: Motion Hallucination from Static Images for Action Recognition (CVPR 2018)

On-Demand Learning for Deep Image Restoration (ICCV 2017)

Website of Open Innovation Lab