HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation

C Zhang, S Stepputtis, J Campbell… - Proceedings of the …, 2024 - openaccess.thecvf.com
Being able to understand visual scenes is a precursor for many downstream tasks including
autonomous driving robotics and other vision-based approaches. A common approach …

From easy to hard: Learning curricular shape-aware features for robust panoptic scene graph generation

H Shi, L Li, J **ao, Y Zhuang, L Chen - International Journal of Computer …, 2024 - Springer
Abstract Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-
structure representation based on panoptic segmentation masks. Despite remarkable …

Class correlation correction for unbiased scene graph generation

M Zhao, Y Kong, L Zhang, B Yin - Pattern Recognition, 2024 - Elsevier
The long-tail distribution in the scene graph generation (SGG) task has spurred immense
interest in unbiased SGG. However, current state-of-the-art debiasing techniques extract …

Texture-Aware Causal Feature Extraction Network for Multimodal Remote Sensing Data Classification

Z Xu, W Jiang, J Geng - IEEE Transactions on Geoscience and …, 2024 - ieeexplore.ieee.org
The pixel-level classification of multimodal remote sensing (RS) images plays a crucial role
in the intelligent interpretation of RS data. However, existing methods that mainly focus on …

Landmark: Language-guided representation enhancement framework for scene graph generation

X Chang, T Wang, S Cai, C Sun - Applied Intelligence, 2023 - Springer
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual
features and the long-tail problem. Recently, various unbiased strategies have been …

Prior Knowledge-driven Dynamic Scene Graph Generation with Causal Inference

J Lu, L Chen, Y Song, S Lin, C Wang… - Proceedings of the 31st …, 2023 - dl.acm.org
The task of dynamic scene graph generation (DSGG) aims at constructing a set of frame-
level scene graphs for the given video. It suffers from two kinds of spurious correlation …

Robust hierarchical scene graph generation

C Zhang, S Stepputtis, J Campbell… - … 2023 Workshop: New …, 2023 - openreview.net
The ability to quickly understand scenes from visual observations via structured
representations, known as Scene Graph Generation (SGG), is a crucial component of …

Adaptive Feature Learning for Unbiased Scene Graph Generation

J Yang, C Wang, L Yang, Y Jiang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Scene Graph Generation (SGG) aims to detect all objects and identify their pairwise
relationships in the scene. Recently, tremendous progress has been made in exploring …

Head-Tail Cooperative Learning Network for Unbiased Scene Graph Generation

L Wang, Z Yuan, Y Lu, B Chen - arxiv preprint arxiv:2308.12048, 2023 - arxiv.org
Scene Graph Generation (SGG) as a critical task in image understanding, facing the
challenge of head-biased prediction caused by the long-tail distribution of predicates …

Domain-Wise Invariant Learning for Panoptic Scene Graph Generation

L Li, Y Qin, W Ji, Y Zhou… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction
of their corresponding relationships (predicates). However, the presence of biased predicate …