HERL applies dual-constraint hyperbolic contrastive learning and a prototype head in Poincaré space to improve semantic preservation and hierarchy modeling for incomplete multi-view clustering.
Adam: A method for stochastic optimization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 5roles
method 1polarities
use method 1representative citing papers
GC-ART learns global second-order rational tone curves from soft per-channel histograms via a 643-parameter MLP and applies them pointwise to boost illumination robustness in image classification.
ADAPT-MS achieves 0.66 RMSE unsupervised and 0.60 with 1000 labels on cross-platform MOOC satisfaction prediction by aligning representations and correcting platform biases.
TET-LLM predicts MOOC satisfaction early via temporal event transformers on behavior, LLM embeddings on text, and topic distributions, beating baselines at RMSE 0.82 and AUC 0.77 for 7-day forecasts.
A three-stage CNN compression framework (dynamic cropping + compound shrinking + cascaded dynamic inference) reduces ResNet-50 MACs by 48.8% while improving ImageNet-1K top-1 accuracy by 0.8%.
citing papers explorer
-
Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering
HERL applies dual-constraint hyperbolic contrastive learning and a prototype head in Poincaré space to improve semantic preservation and hierarchy modeling for incomplete multi-view clustering.
-
GC-ART: Global Learnable Second-Order Rational Tone Curves for Illumination Robustness
GC-ART learns global second-order rational tone curves from soft per-channel histograms via a 643-parameter MLP and applies them pointwise to boost illumination robustness in image classification.
-
Cross-Platform Domain Adaptation for Multi-Modal MOOC Learner Satisfaction Prediction
ADAPT-MS achieves 0.66 RMSE unsupervised and 0.60 with 1000 labels on cross-platform MOOC satisfaction prediction by aligning representations and correcting platform biases.
-
Early-Warning Learner Satisfaction Forecasting in MOOCs via Temporal Event Transformers and LLM Text Embeddings
TET-LLM predicts MOOC satisfaction early via temporal event transformers on behavior, LLM embeddings on text, and topic distributions, beating baselines at RMSE 0.82 and AUC 0.77 for 7-day forecasts.
-
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
A three-stage CNN compression framework (dynamic cropping + compound shrinking + cascaded dynamic inference) reduces ResNet-50 MACs by 48.8% while improving ImageNet-1K top-1 accuracy by 0.8%.