Showing cs.MMShow all
3 papers · 1 filter
cs.MM2026
Hierarchical Semantic Correlation-Aware Masked Autoencoder for Unsupervised Audio-Visual Representation Learning
Donghuo Zeng, Hao Niu, Masato Taya
Learning aligned multimodal embeddings from weakly paired, label-free corpora is challenging: pipelines often provide only pre-extracted features, clips contain multiple events, an…
cs.MM2026
Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs
Donghuo Zeng, Hao Niu, Yanan Wang +1
Learning robust audio-visual embeddings requires bringing genuinely related audio and visual signals together while filtering out incidental co-occurrences - background noise, unre…
cs.MM2025
Comparing Contrastive and Triplet Loss: Variance Analysis and Optimization Behavior
Donghuo Zeng
Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a the…