Research map / Vision-language and multimodal / Cross-modal learning
Attention-aware Deep Adversarial Hashing for Cross-Modal Retrieval
Xi Zhang, Hanjiang Lai, Jiashi Feng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add HashGAN attention-aware adversarial hashing instead of DCMH | DCMH · IAPR TC-12 text->image 16 bits | MAP: 0.5185 -> 0.5358 | Improved |
| add HashGAN instead of DCMH | DCMH · IAPR TC-12 image->text 16 bits | MAP: 0.4526 -> 0.5293 | Improved |
| add HashGAN instead of DCMH | DCMH · MIR-Flickr 25k text->image 32 bits | MAP: 0.7900 -> 0.8062 | Improved |
| add HashGAN instead of DCMH | DCMH · MIR-Flickr 25k image->text 64 bits | MAP: 0.7485 -> 0.7720 | Improved |
| add HashGAN instead of DCMH | DCMH · NUS-WIDE text->image 64 bits | MAP: 0.6571 -> 0.6939 | Improved |
| add HashGAN instead of DCMH | DCMH · NUS-WIDE image->text 32 bits | MAP: 0.6031 -> 0.6258 | Improved |
| use VGG instead of smaller CNN-F image network (ablation) | HashGAN · IAPR TC-12 text->image 16 bits | MAP: 0.5267 -> 0.5358 | Improved |
| use VGG instead of smaller CNN-F image network (ablation) | HashGAN · IAPR TC-12 text->image 64 bits | MAP: 0.5538 -> 0.5648 | Improved |
| use VGG instead of smaller CNN-F image network (ablation) | HashGAN · IAPR TC-12 image->text 32 bits | MAP: 0.5168 -> 0.5283 | Improved |
| use VGG instead of smaller CNN-F image network (ablation) | HashGAN · IAPR TC-12 image->text 64 bits | MAP: 0.5208 -> 0.5439 | Improved |
| increase hash code length from 16 to 64 bits | HashGAN · MIR-Flickr 25k text->image | MAP: 0.7922 -> 0.8074 | Improved |
| increase hash code length from 16 to 64 bits | HashGAN · NUS-WIDE image->text | MAP: 0.6300 -> 0.6468 | Improved |
Closest papers by meaning
- Unsupervised Generative Adversarial Cross-Modal Hashing (AAAI 2018 · similarity 0.93)
- Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval (CVPR 2018 · similarity 0.92)
- Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval (AAAI 2019 · similarity 0.92)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.91)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.90)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.88)
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.
