Tag: contrastive learning

Researchers at Shanghai Jiao Tong University have built a multimodal knowledge graph that aligns historical Chinese architectural texts, field photographs ...

Researchers at the Beijing Institute of Technology show that adding expert-vetted relational graphic structure to AI models enables retrieval of ...

Researchers at Hanyang University have developed TACCO, a contrastive learning method that explicitly identifies and suppresses out-of-distribution actions to stabilize ...

Researchers in India show that training only a 2.4-million-parameter projection module on top of frozen CLIP encoders lifts fashion image-to-text ...

Researchers at Shanghai Maritime University have developed RPCV, a deep clustering method that uses transformer-based cross-view attention and entropy-constrained prototype ...

Researchers have developed CHIME, a framework that mitigates and measures hallucinations in zero-shot dense retrieval, showing that which hallucinations are ...

Researchers in India have built a four-part neural system that uses contrastive learning, graph refinement, and reinforcement learning to find ...

Researchers have developed DPAS-Net, a deep learning framework that maintains remarkably accurate multi-view clustering even when up to 90 percent ...

A new framework pairs momentum contrastive learning with the GATv2 graph attention network to detect rare, legally entangled financial credit ...

Researchers at Shanghai Maritime University have developed STTF, a self-supervised framework that fuses road network topology with multi-granularity temporal information ...