Research map / Vision-language and multimodal / Human and embodied modeling
Neural image captioning
Generate descriptive, controllable, and personalized captions from images.
72 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Human and embodied modeling, keyword cluster “retrieval · scene · captioning”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
17 papers in 2023–24 and 2 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 3.2% to 0.3%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Robust Scene Text Recognition With Automatic Rectification (CVPR 2016 · 710 citations)
- 2017 · A Hierarchical Approach for Generating Descriptive Image Paragraphs (CVPR 2017 · 386 citations)
- 2018 · Convolutional Image Captioning (CVPR 2018 · 432 citations)
- 2019 · Unsupervised Image Captioning (CVPR 2019 · 231 citations)
- 2020 · BERTScore: Evaluating Text Generation with BERT (ICLR 2020 · 2,397 citations)
- 2021 · Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network (AAAI 2021 · 183 citations)
- 2022 · Quantifying Societal Bias Amplification in Image Captioning (CVPR 2022 · 47 citations)
- 2023 · TrOCR: Transformer-Based Optical Character Recognition with Pre-trained Models (AAAI 2023 · 488 citations)
- 2024 · Image Captioning with Multi-Context Synthetic Data (AAAI 2024 · 20 citations)
- 2025 · Whitened CLIP as a Likelihood Surrogate of Images and Captions (ICML 2025 · 0 citations)
- 2026 · Imagine How To Change: Explicit Procedure Modeling for Change Captioning (ICLR 2026 · 0 citations)
Earliest papers here
- Robust Scene Text Recognition With Automatic Rectification (CVPR 2016 · 710 citations)
- Review Networks for Caption Generation (NeurIPS 2016 · 84 citations)
- Event-Specific Image Importance (CVPR 2016 · 40 citations)
What has been tried
69 papers here report 748 measured changes (a component added, removed or swapped, compared with a baseline): helped 71%, no clear effect 7%, hurt 18%, mixed 4%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Replace uni-context-only training with selected captions and summarized multi-context image-text pairs | MSCOCO · BLEU@4 | 26.9 -> 29.9 | Helped | Image Captioning with Multi-Context Synthetic Data (AAAI 2024 · 20 citations) |
| add soft guidance to image plugging | MMS · ROUGE-1 | 49.88 -> 50.39 | Helped | DIUSum: Dynamic Image Utilization for Multimodal Summarization (AAAI 2024 · 9 citations) |
| Use CLIP ViT-B/32 instead of CLIP ViT-L/14 | MS-COCO validation · Normality test scores | No clear effect | Whitened CLIP as a Likelihood Surrogate of Images and Captions (ICML 2025 · 0 citations) |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 24 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Scene graph generation (126 papers)
- Language-grounded scene text and structure (124 papers)
- Multimodal retrieval-augmented modeling (85 papers)
- Composed and text-based image retrieval (78 papers)
- Concept-guided image captioning (69 papers)
Elsewhere in the topic
- Vision-language pretraining (182 papers)
- Medical vision-language models (130 papers)
- fMRI visual decoding (106 papers)
- Human-like visual cognition in VLMs (97 papers)
- Multimodal and affective interaction modeling (87 papers)
- Language-grounded visual concept learning (83 papers)
- Layout-aware document understanding (73 papers)
- Human perception modeling (71 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).