HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation
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 …
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
Abstract Panoptic Scene Graph Generation (PSG) aims to generate a comprehensive graph-
structure representation based on panoptic segmentation masks. Despite remarkable …
structure representation based on panoptic segmentation masks. Despite remarkable …
Class correlation correction for unbiased scene graph generation
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 …
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 …
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 …
features and the long-tail problem. Recently, various unbiased strategies have been …
Prior Knowledge-driven Dynamic Scene Graph Generation with Causal Inference
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 …
level scene graphs for the given video. It suffers from two kinds of spurious correlation …
Robust hierarchical scene graph generation
The ability to quickly understand scenes from visual observations via structured
representations, known as Scene Graph Generation (SGG), is a crucial component of …
representations, known as Scene Graph Generation (SGG), is a crucial component of …
Adaptive Feature Learning for Unbiased Scene Graph Generation
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 …
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 …
challenge of head-biased prediction caused by the long-tail distribution of predicates …
Domain-Wise Invariant Learning for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction
of their corresponding relationships (predicates). However, the presence of biased predicate …
of their corresponding relationships (predicates). However, the presence of biased predicate …