CAPIMAC combines self-repellent random-walk anchors, noise-contrastive training, and Gaussian-kernel padding to improve clustering on incomplete and misaligned multimodal benchmarks.
Large graph construction for scalable semi-supervised learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Consistency-Aware Padding for Incomplete Multi-Modal Alignment Clustering Based on Self-Repellent Greedy Anchor Search
CAPIMAC combines self-repellent random-walk anchors, noise-contrastive training, and Gaussian-kernel padding to improve clustering on incomplete and misaligned multimodal benchmarks.