Search Results for author:
Found 7 papers, 4 papers with code
Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders
As a result, our model can extract effectively both static appearance and dynamic motion spontaneously, leading to superior spatiotemporal representation learning capability.
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
Specifically, we propose two tasks to learn the appearance and speed consistency, respectively.
RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
We study unsupervised video representation learning that seeks to learn both motion and appearance features from unlabeled video only, which can be reused for downstream tasks such as action recognition.
Ranked #11 on
Self-Supervised Action Recognition
on UCF101
Location-aware Graph Convolutional Networks for Video Question Answering
In this work, we propose to represent the contents in the video as a location-aware graph by incorporating the location information of an object into the graph construction.
Foley Music: Learning to Generate Music from Videos
In this paper, we introduce Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments.
Generating Visually Aligned Sound from Videos
During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features.
Music Gesture for Visual Sound Separation
Recent deep learning approaches have achieved impressive performance on visual sound separation tasks.
