# Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing

arXiv: https://arxiv.org/abs/2503.00548 · HTML: https://mlsanity.com/paper/2503.00548/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 23 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Neural Motifs: Scene Graph Parsing with Global Context](https://mlsanity.com/paper/1711.06640/) (2017)
- [Unbiased Scene Graph Generation from Biased Training](https://mlsanity.com/paper/2002.11949/) (2020)
- [Learning to Compose Dynamic Tree Structures for Visual Contexts](https://mlsanity.com/paper/1812.01880/) (2018)
- [Action Genome: Actions as Composition of Spatio-temporal Scene Graphs](https://mlsanity.com/paper/1912.06992/) (2019)
- [SGTR: End-to-end Scene Graph Generation with Transformer](https://mlsanity.com/paper/2112.12970/) (2021)
- [RelTR: Relation Transformer for Scene Graph Generation](https://mlsanity.com/paper/2201.11460/) (2022)
- [PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2009.00893/) (2020)
- [Relationformer: A Unified Framework for Image-to-Graph Generation](https://mlsanity.com/paper/2203.10202/) (2022)
- [Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels](https://mlsanity.com/paper/1512.06974/) (2015)
- [Target Adaptive Context Aggregation for Video Scene Graph Generation](https://mlsanity.com/paper/2108.08121/) (2021)
- [Panoptic Video Scene Graph Generation](https://mlsanity.com/paper/2311.17058/) (2023)
- [Unbiased Scene Graph Generation in Videos](https://mlsanity.com/paper/2304.00733/) (2023)
- [4D Panoptic Scene Graph Generation](https://mlsanity.com/paper/2405.10305/) (2024)
- [Social Fabric: Tubelet Compositions for Video Relation Detection](https://mlsanity.com/paper/2108.08363/) (2021)
- [Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2208.03763/) (2022)
- [Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2207.07913/) (2022)

## Built on by (most cited first, 6 of 6)

- [Synthetic Visual Genome 2: Extracting Large-scale Spatio-Temporal Scene Graphs from Videos](https://mlsanity.com/paper/2602.23543/) (2026)
- [UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning](https://mlsanity.com/paper/2509.06165/) (2025)
- [Language-Driven Object-Oriented Two-Stage Method for Scene Graph Anticipation](https://mlsanity.com/paper/2509.05661/) (2025)
- [A Closer Look at Dynamic Scene Graph Generation In the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.15846/) (2025)
- [Click2Graph: Interactive Panoptic Video Scene Graphs from a Single Click](https://mlsanity.com/paper/2511.15948/) (2025)
- [T-STAR: A Large-Scale Benchmark for Spatio-Temporal Panoptic Scene Graph Generation in Satellite Video](https://mlsanity.com/paper/2607.21228/) (2026)

## Abstract (arXiv)

Video Scene Graph Generation (VidSGG) aims to capture dynamic relationships among entities by sequentially analyzing video frames and integrating visual and semantic information. However, VidSGG is challenged by significant biases that skew predictions. To mitigate these biases, we propose a VIsual and Semantic Awareness (VISA) framework for unbiased VidSGG. VISA addresses visual bias through memory-enhanced temporal integration that enhances object representations and concurrently reduces semantic bias by iteratively integrating object features with comprehensive semantic information derived from triplet relationships. This visual-semantics dual debiasing approach results in more unbiased representations of complex scene dynamics. Extensive experiments demonstrate the effectiveness of our method, where VISA outperforms existing unbiased VidSGG approaches by a substantial margin (e.g., +13.1% improvement in mR@20 and mR@50 for the SGCLS task under Semi Constraint).