Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
In: International Conference on Learning Representations (2017)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
GLeVE introduces graph-guided lesion grounding with anatomical verification and octree refinement to improve text-to-lesion alignment in 3D CT volumes.
Hyp2Former learns hierarchical semantic similarities in hyperbolic space among known categories so that unknown objects remain close to higher-level concepts and can be detected reliably.
citing papers explorer
-
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
-
GLeVE: Graph-Guided Lesion Grounding with Proposal Verification in 3D CT
GLeVE introduces graph-guided lesion grounding with anatomical verification and octree refinement to improve text-to-lesion alignment in 3D CT volumes.
-
Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation
Hyp2Former learns hierarchical semantic similarities in hyperbolic space among known categories so that unknown objects remain close to higher-level concepts and can be detected reliably.