Memory Efficient Temporal Visual Graph Model for Unsupervised Video Domain Adaptation

08/13/2022
by   Xinyue Hu, et al.
0

Existing video domain adaption (DA) methods need to store all temporal combinations of video frames or pair the source and target videos, which are memory cost expensive and can't scale up to long videos. To address these limitations, we propose a memory-efficient graph-based video DA approach as follows. At first our method models each source or target video by a graph: nodes represent video frames and edges represent the temporal or visual similarity relationship between frames. We use a graph attention network to learn the weight of individual frames and simultaneously align the source and target video into a domain-invariant graph feature space. Instead of storing a large number of sub-videos, our method only constructs one graph with a graph attention mechanism for one video, reducing the memory cost substantially. The extensive experiments show that, compared with the state-of-art methods, we achieved superior performance while reducing the memory cost significantly.

READ FULL TEXT
research
07/31/2020

Adversarial Bipartite Graph Learning for Video Domain Adaptation

Domain adaptation techniques, which focus on adapting models between dis...
research
07/23/2021

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

Video semantic segmentation is an essential task for the analysis and un...
research
12/10/2020

DA-HGT: Domain Adaptive Heterogeneous Graph Transformer

Domain adaptation using graph networks is to learn label-discriminative ...
research
07/14/2020

Video Object Segmentation with Episodic Graph Memory Networks

How to make a segmentation model to efficiently adapt to a specific vide...
research
05/26/2019

Temporal Attentive Alignment for Video Domain Adaptation

Although various image-based domain adaptation (DA) techniques have been...
research
03/31/2020

TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

We present a lightweight video motion retargeting approach TransMoMo tha...
research
11/07/2016

Memory-augmented Attention Modelling for Videos

We present a method to improve video description generation by modeling ...

Please sign up or login with your details

Forgot password? Click here to reset