SPOT is introduced, a structured prompting framework that augments open-source VLMs with spatial reasoning abilities for scene graph generation with minimal training, and achieves competitive or superior relation prediction compared to large proprietary models.
The Cross-Modal Dual-Path Generator (CM-DPG), a model for robust open-vocabulary SGG that enhances object-level semantic representations through joint visual-textual encoding and improves relational reasoning using complementary visual and geometric cues, is proposed.
Ming-Hao Zou, Qingtian Zeng, Shangkun Liu et al.· 0 citations
Scene graphs provide structured visual knowledge that can enhance multimodal large language models (MLLMs) for tasks like visual question answering and image captioning. However, existing approaches inject scene graphs as deterministic, hard prompts, ignoring the inherent uncertainty in visual perception, leading to ov...
OvDSGG is introduced, the first end-to-end framework for open-vocabulary DSGG, which significantly outperforms open-vocabulary baselines across all metrics, and a rigorous open-vocabulary DSGG benchmark adapted from Action Genome, with disjoint Base/Novel splits for both objects and predicates.
John Helsby, Yi Yang, B. Rosenhahn et al.· 0 citations
This work extends its previous work in scene graph generation to integrate image captioning, incorporating large language models to interpret scene graph structures and produce high-quality captions encompassing complex actions and relationships.
Anfel Amirat, N. Baha, Lamine Benrais· Signal, Image and Video Proc...· 0 citations
OVIP-SG is presented, a unified framework for instance-preserving semantic mapping, functional scene partitioning, and language-guided small, fine-grained object retrieval that outperforms ConceptGraphs under a unified evaluation protocol on Replica.
Tianjing Hao, Hai-Yu Lan, Ang Li et al.· 0 citations
KNA-SG, a framework for constructing open-vocabulary 3D scene graphs from RGB sequences with explicit keyframe–node associations, is proposed and Experimental results show that KNA-SG outperforms existing methods on open-vocabulary 3D semantic segmentation and 3D object grounding tasks.
Yang Xu, Wen-ku Shi, Jing Xing et al.· Technologies· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
