Research map / Architectures and efficiency / RNNs and normalization
AMVH: Asymmetric Multi-Valued Hashing
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use a real-valued query embedding instead of a binary query code (ablation) | AMVH · ESP-GAME | MAP: +14.53% | Helped |
| use a multi-integer-valued database embedding instead of the binary database embedding (ablation) | AMVHreal · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | Helped |
| use binary query codes instead of real-valued query embeddings (ablation) | AMVH · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | Hurt |
| increase the sparsity parameter l from 1 toward 10 (ablation) | AMVHmul · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | Helped |
| increase dictionary size M (ablation) | AMVHreal · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | Helped |
| vary dictionary size M while using multi-integer-valued embeddings (ablation) | AMVHmul · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | No clear effect |
| use real-valued query embeddings and binary database codes (ablation) | AMVH · ESP-GAME, MIR-FLICKR, and NUS-WIDE | MAP | Helped |
| use multi-integer-valued database embeddings (ablation) | AMVH · NUS-WIDE | MAP: +12.41% | Helped |
| use multi-integer-valued database embeddings (ablation) | AMVH · ESP-GAME | top-K precision: +11.53% | Helped |
| use multi-integer-valued database embeddings (ablation) | AMVH · NUS-WIDE | top-K precision: +18.50% | Helped |
Closest papers by meaning
- SADIH: Semantic-Aware DIscrete Hashing (AAAI 2019 · similarity 0.90)
- Statistical Model-driven Similarity Hashing: Bridging Modalities for Efficient Unsupervised Retrieval (AAAI 2025 · similarity 0.88)
- Fast Online Hashing with Multi-Label Projection (AAAI 2023 · similarity 0.87)
- Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion (AAAI 2024 · similarity 0.87)
- Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis (AAAI 2025 · similarity 0.86)
- Generalized Debiased Semi-Supervised Hashing for Large-Scale Image Retrieval (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.