SymTrack is the first systematic detection-free framework for scene text tracking that constructs benchmarks from video text spotting datasets and reports up to 11.97% AUC gains over prior trackers.
Quasimonotonicity, regularity and duality for nonlinear systems of partial differential equations
7 Pith papers cite this work. Polarity classification is still indexing.
years
2026 7verdicts
UNVERDICTED 7representative citing papers
Gaussian process regression enables implicit multi-camera calibration by learning 2D-to-3D mappings with built-in uncertainty and active learning for efficient data use.
HEaD+ detects object hallucinations early in diffusion generation via cross-attention maps, text, and a Predicted Final Image, raising complete image rates by 6-8% for four-object prompts and reducing time by up to 32%.
MCBP detects boundaries by computing discrete mean curvature from k-nearest neighbor patches on the data manifold, then decomposes data into low-curvature smooth and high-curvature boundary subsets to improve clustering.
A cascade pipeline on 400 AIE tiles evaluates gg→ttg leading-order matrix elements at 1 million per second with parts-per-million accuracy to MadGraph, delivering 34× CPU speedup and 7.7× better energy efficiency at 54.8 W.
ProMoTA integrates process modeling with automated end-to-end traceability generation and analysis for model transformation chains in MDE, demonstrated on a wireless sensor network IoT application.
The paper identifies key unresolved questions in giant planet formation, interiors, and their role in planetary systems.
citing papers explorer
-
Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
SymTrack is the first systematic detection-free framework for scene text tracking that constructs benchmarks from video text spotting datasets and reports up to 11.97% AUC gains over prior trackers.
-
Implicit Multi-Camera System Calibration Using Gaussian Processes
Gaussian process regression enables implicit multi-camera calibration by learning 2D-to-3D mappings with built-in uncertainty and active learning for efficient data use.
-
Hallucination Early Detection in Diffusion Models
HEaD+ detects object hallucinations early in diffusion generation via cross-attention maps, text, and a Predicted Final Image, raising complete image rates by 6-8% for four-object prompts and reducing time by up to 32%.
-
A Mean Curvature Approach to Boundary Detection: Geometric Insights for Unsupervised Learning
MCBP detects boundaries by computing discrete mean curvature from k-nearest neighbor patches on the data manifold, then decomposes data into low-curvature smooth and high-curvature boundary subsets to improve clustering.
-
Cascade Pipeline for Leading-Order Matrix Element Evaluation on AMD Versal AI Engine Arrays
A cascade pipeline on 400 AIE tiles evaluates gg→ttg leading-order matrix elements at 1 million per second with parts-per-million accuracy to MadGraph, delivering 34× CPU speedup and 7.7× better energy efficiency at 54.8 W.
-
ProMoTA: a model-driven framework for end-to-end traceability analysis
ProMoTA integrates process modeling with automated end-to-end traceability generation and analysis for model transformation chains in MDE, demonstrated on a wireless sensor network IoT application.
-
Outstanding Questions in Giant Planet Theory
The paper identifies key unresolved questions in giant planet formation, interiors, and their role in planetary systems.