Research map / Vision-language and multimodal / Cross-modal learning
Deep Supervised Cross-Modal Retrieval
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 |
|---|---|---|---|
| combine label-space and common-space discrimination losses with modality-invariance loss | DSCMR · Wikipedia | average mAP: +0.018 | Helped |
| combine label-space and common-space discrimination losses with modality-invariance loss | DSCMR · Pascal Sentence | average mAP: +0.038 | Helped |
| combine label-space and common-space discrimination losses with modality-invariance loss | DSCMR · NUS-WIDE-10k | average mAP: +0.020 | Helped |
| combine label-space and common-space discrimination losses with modality-invariance loss | DSCMR · XMediaNet | average mAP: +0.050 | Helped |
| add label-space discrimination loss J1 (ablation) | DSCMR · Pascal Sentence | average mAP: 0.607 -> 0.716 | Helped |
| add label-space discrimination loss J1 (ablation) | DSCMR · NUS-WIDE-10k | average mAP: 0.265 -> 0.613 | Helped |
| add common-space discrimination loss J2 (ablation) | DSCMR · Pascal Sentence | average mAP: 0.715 -> 0.716 | Helped |
| add common-space discrimination loss J2 (ablation) | DSCMR · NUS-WIDE-10k | average mAP: 0.611 -> 0.613 | Helped |
| add modality-invariance loss J3 (ablation) | DSCMR · Pascal Sentence | average mAP: 0.694 -> 0.716 | Helped |
| add modality-invariance loss J3 (ablation) | DSCMR · NUS-WIDE-10k | average mAP: 0.538 -> 0.613 | Helped |
| add common-space discrimination loss J2 and modality-invariance loss J3 to J1-only training (ablation) | DSCMR · Pascal Sentence | average mAP: 0.685 -> 0.716 | Helped |
| add common-space discrimination loss J2 and modality-invariance loss J3 to J1-only training (ablation) | DSCMR · NUS-WIDE-10k | average mAP: 0.524 -> 0.613 | Helped |
Closest papers by meaning
- Online Asymmetric Similarity Learning for Cross-Modal Retrieval (CVPR 2017 · similarity 0.89)
- Learning Cross-Modal Retrieval With Noisy Labels (CVPR 2021 · similarity 0.89)
- DiCA: Disambiguated Contrastive Alignment for Cross-Modal Retrieval with Partial Labels (AAAI 2025 · similarity 0.88)
- Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval (AAAI 2024 · similarity 0.87)
- CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer (AAAI 2024 · similarity 0.87)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.87)
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.