Research map / Vision-language and multimodal / Human and embodied modeling
End-to-End Convolutional Semantic Embeddings
Read the paperCheck 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 |
|---|---|---|---|
| add the intermediate loss to global semantic learning (ablation) | CSE · Flickr30K | Sentence retrieval R@1: 43.2 -> 44.6 | Helped |
| add the intermediate loss to global semantic learning (ablation) | CSE · Flickr30K | Image retrieval R@1: 35.7 -> 36.9 | Helped |
| add the intermediate loss to global semantic learning (ablation) | CSE · MS-COCO | Sentence retrieval R@1: 51.6 -> 56.3 | Helped |
| add the intermediate loss to global semantic learning (ablation) | CSE · MS-COCO | Image retrieval R@1: 43.4 -> 45.7 | Helped |
| use the local context vector instead of global semantics (ablation) | CSE · Flickr30K | Sentence retrieval R@1: 44.6 -> 36.9 | Hurt |
| use the local context vector instead of global semantics (ablation) | CSE · MS-COCO | Sentence retrieval R@1: 56.3 -> 41.5 | Hurt |
Closest papers by meaning
- Jointly Modeling Embedding and Translation to Bridge Video and Language (CVPR 2016 · similarity 0.90)
- Expressing Objects Just Like Words: Recurrent Visual Embedding for Image-Text Matching (AAAI 2020 · similarity 0.89)
- Learning Semantic Concepts and Order for Image and Sentence Matching (CVPR 2018 · similarity 0.89)
- What Value Do Explicit High Level Concepts Have in Vision to Language Problems? (CVPR 2016 · similarity 0.89)
- VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks (ICLR 2025 · similarity 0.86)
- Unified Generative and Discriminative Training for Multi-modal Large Language Models (NeurIPS 2024 · 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.