Research map / Vision-language and multimodal / Visual question answering
Federated Learning for Vision-and-Language Grounding Problems
Fenglin Liu, Xian Wu, Shen Ge, Wei Fan, Yuexian Zou
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 |
|---|---|---|---|
| horizontal federated learning with MSCOCO | NBT · Flickr30k | CIDEr: 60.2 →68.4 | Improved |
| horizontal federated learning with Flickr30k | NBT · MSCOCO | CIDEr: 110.7 →115.2 | Improved |
| vertical federated learning with captioning (MSCOCO+NBT) | BAN · VQA v2.0 test-std | accuracy: 69.8% to 70.6% | Improved |
| add aligning module (ablation) | Spatial / BUTD baseline · VQA v2.0 test-dev | accuracy: 67.3 -> 68.1 | Improved |
| add integrating module (ablation) | Spatial baseline · MSCOCO | CIDEr: 109.8 -> 113.1 | Improved |
| combine aligning and integrating modules (ablation) | Spatial · MSCOCO | CIDEr: 113.1 -> 114.2 | Improved |
| add vertical federated learning to full aimNet (ablation) | Spatial · MSCOCO | CIDEr: 114.2 -> 116.1 | Improved |
| federated transfer learning with VQA | Spatial · Flickr30k | CIDEr: 57.1 -> 61.2 | Improved |
Closest papers by meaning
- Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations (NeurIPS 2019 · similarity 0.90)
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge (TPAMI 2017 · similarity 0.88)
- Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning (ICLR 2026 · similarity 0.87)
- Cycle-Consistency Learning for Captioning and Grounding (AAAI 2024 · similarity 0.87)
- Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning (AAAI 2026 · similarity 0.87)
- Global and Local Prompts Cooperation via Optimal Transport for Federated Learning (CVPR 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.
