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.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
unclear 1representative citing papers
Bayesian softmax-gated mixture-of-experts models achieve posterior contraction for density estimation and parameter recovery using Voronoi losses, plus two strategies for choosing the number of experts.
A new Ms-MoE-IFactFormer neural operator uses time-step routing and scale-specific experts to achieve stable fine-time-step long-horizon predictions of homogeneous isotropic turbulence and channel flow.
EMoE trains MoE models so they maintain performance when the number of activated experts changes at inference, expanding the usable range to 2-3 times the training k with higher peak results.
Token-Superposition Training combines multiple tokens into bags for multi-hot cross-entropy pre-training followed by a recovery phase, yielding up to 2.5x reduction in training time at 10B scale under equal-loss conditions.
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.
-
On Bayesian Softmax-Gated Mixture-of-Experts Models
Bayesian softmax-gated mixture-of-experts models achieve posterior contraction for density estimation and parameter recovery using Voronoi losses, plus two strategies for choosing the number of experts.
-
Stable Fine-Time-Step Long-Horizon Turbulence Prediction with a Multi-Stepsize Mixture-of-Experts Neural Operator
A new Ms-MoE-IFactFormer neural operator uses time-step routing and scale-specific experts to achieve stable fine-time-step long-horizon predictions of homogeneous isotropic turbulence and channel flow.
-
Elastic MoE: Unlocking the Inference-Time Scalability of Mixture-of-Experts
EMoE trains MoE models so they maintain performance when the number of activated experts changes at inference, expanding the usable range to 2-3 times the training k with higher peak results.
-
Efficient Pre-Training with Token Superposition
Token-Superposition Training combines multiple tokens into bags for multi-hot cross-entropy pre-training followed by a recovery phase, yielding up to 2.5x reduction in training time at 10B scale under equal-loss conditions.