Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational Structured Semantic Inference for Diverse Image Captioning
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 syntactic diversity modeling to lexical-only variant (ablation) | VSSI-cap · MSCOCO accuracy | CIDEr: 87.3 -> 89.4 | Helped |
| add lexical diversity modeling to syntax-only variant (ablation) | VSSI-cap · MSCOCO accuracy | CIDEr: 88.8 -> 89.4 | Helped |
| add syntactic diversity modeling to lexical-only variant (ablation) | VSSI-cap · MSCOCO diversity n=5 | mBleu: 68.7 -> 62.4 | Helped |
| add lexical diversity modeling to syntax-only variant (ablation) | VSSI-cap · MSCOCO diversity n=5 | mBleu: 63.0 -> 62.4 | Helped |
| add syntactic modeling to lexical-only variant (ablation) | VSSI-cap · MSCOCO diversity n=5 | div2: 45.6 -> 47.2 | Helped |
| add lexical modeling to syntax-only variant (ablation) | VSSI-cap · MSCOCO diversity n=5 | Unique sentences: 82.4 -> 83.0 | Helped |
| add syntactic modeling to lexical-only variant (ablation) | VSSI-cap · MSCOCO diversity n=5 | div1: 34.3 -> 33.9 | No clear effect |
| replace AG-CVAE object-guided CVAE with VarMI-tree structured inferer | CVAE captioner · MSCOCO accuracy | CIDEr: 85.7 -> 89.4 | Helped |
Closest papers by meaning
- Modeling Caption Diversity in Contrastive Vision-Language Pretraining (ICML 2024 · similarity 0.89)
- Top-Down Semantic Refinement for Image Captioning (AAAI 2026 · similarity 0.89)
- FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity (CVPR 2025 · similarity 0.88)
- Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning (CVPR 2025 · similarity 0.88)
- Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning (NeurIPS 2025 · similarity 0.88)
- CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness (NeurIPS 2025 · 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.