# Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Source: [Meta Spatio-Temporal Debiasing for Video Scene Graph Generation](<https://www.sota2.com/research/paper/68fa6d1c1e209131cea37cb0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:26:36.450Z

Authors: Li Xu, Haoxuan Qu, Jason Kuen, Jiuxiang Gu, Jun Liu

Published: 2022-07-23T07:06:06.000Z

## Abstract

Video scene graph generation (VidSGG) aims to parse the video content into scene graphs, which involves modeling the spatio-temporal contextual information in the video. However, due to the long-tailed training data in datasets, the generalization performance of existing VidSGG models can be affected by the spatio-temporal conditional bias problem. In this work, from the perspective of meta-learning, we propose a novel Meta Video Scene Graph Generation (MVSGG) framework to address such a bias problem. Specifically, to handle various types of spatio-temporal conditional biases, our framework first constructs a support set and a group of query sets from the training data, where the data distribution of each query set is different from that of the support set w.r.t. a type of conditional bias. Then, by performing a novel meta training and testing process to optimize the model to obtain good testing performance on these query sets after training on the support set, our framework can effectively guide the model to learn to well generalize against biases. Extensive experiments demonstrate the efficacy of our proposed framework.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Relation Detection on VidVRD v1.0 (test)](<https://www.sota2.com/research/sota/relation-detection-on-vidvrd-v1-0-test.md>): Relation Detection; VidVRD v1.0 (test); R@50: 12.62.

- [Relation Tagging on VidVRD v1.0 (test)](<https://www.sota2.com/research/sota/relation-tagging-on-vidvrd-v1-0-test.md>): Relation Tagging; VidVRD v1.0 (test); P@5: 44.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.11441>)

[PDF](<https://arxiv.org/pdf/2207.11441.pdf>)