# Length-Controllable Image Captioning

arXiv: https://arxiv.org/abs/2007.09580 · HTML: https://mlsanity.com/paper/2007.09580/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 30 of 36)

- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [Caption Anything: Interactive Image Description with Diverse Multimodal Controls](https://mlsanity.com/paper/2305.02677/) (2023)
- [Human-like Controllable Image Captioning with Verb-specific Semantic Roles](https://mlsanity.com/paper/2103.12204/) (2021)
- [Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation](https://mlsanity.com/paper/2108.01682/) (2021)
- [ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing](https://mlsanity.com/paper/2303.02437/) (2023)
- [Towards Accurate Text-based Image Captioning with Content Diversity Exploration](https://mlsanity.com/paper/2105.03236/) (2021)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [Emergent Visual-Semantic Hierarchies in Image-Text Representations](https://mlsanity.com/paper/2407.08521/) (2024)
- [Controllable Image Captioning via Prompting](https://mlsanity.com/paper/2212.01803/) (2022)
- [Learning Distinct and Representative Styles for Image Captioning](https://mlsanity.com/paper/2209.08231/) (2022)
- [Learning Combinatorial Prompts for Universal Controllable Image Captioning](https://mlsanity.com/paper/2303.06338/) (2023)
- [Parallel and High-Fidelity Text-to-Lip Generation](https://mlsanity.com/paper/2107.06831/) (2021)
- [Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning](https://mlsanity.com/paper/2309.04965/) (2023)
- [FlexCap: Describe Anything in Images in Controllable Detail](https://mlsanity.com/paper/2403.12026/) (2024)
- [Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation](https://mlsanity.com/paper/2210.11109/) (2022)
- [Counterfactual Maximum Likelihood Estimation for Training Deep Networks](https://mlsanity.com/paper/2106.03831/) (2021)
- [CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning](https://mlsanity.com/paper/2507.01409/) (2025)
- [AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning](https://mlsanity.com/paper/2507.12841/) (2025)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)
- [CLID: Controlled-Length Image Descriptions with Limited Data](https://mlsanity.com/paper/2211.14835/) (2022)
- [Textual Inversion and Self-supervised Refinement for Radiology Report Generation](https://mlsanity.com/paper/2405.20607/) (2024)
- [Detailed Object Description with Controllable Dimensions](https://mlsanity.com/paper/2411.19106/) (2024)
- [SGDiff: Scene Graph Guided Diffusion Model for Image Collaborative SegCaptioning](https://mlsanity.com/paper/2512.01975/) (2025)
- [Self-Annotated Training for Controllable Image Captioning](https://mlsanity.com/paper/2110.08446/) (2021)
- [CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation](https://mlsanity.com/paper/2407.11393/) (2024)
- [Fine-grained length controllable video captioning with ordinal embeddings](https://mlsanity.com/paper/2408.15447/) (2024)
- [Goal-driven text descriptions for images](https://mlsanity.com/paper/2108.12575/) (2021)
- [A Picture is Worth a Thousand Words: A Unified System for Diverse Captions and Rich Images Generation](https://mlsanity.com/paper/2110.09756/) (2021)
- [DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism](https://mlsanity.com/paper/2311.14920/) (2023)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)

## Abstract (arXiv)

The last decade has witnessed remarkable progress in the image captioning task; however, most existing methods cannot control their captions, e.g., choosing to describe the image either roughly or in detail. In this paper, we propose to use a simple length level embedding to endow them with this ability. Moreover, due to their autoregressive nature, the computational complexity of existing models increases linearly as the length of the generated captions grows. Thus, we further devise a non-autoregressive image captioning approach that can generate captions in a length-irrelevant complexity. We verify the merit of the proposed length level embedding on three models: two state-of-the-art (SOTA) autoregressive models with different types of decoder, as well as our proposed non-autoregressive model, to show its generalization ability. In the experiments, our length-controllable image captioning models not only achieve SOTA performance on the challenging MS COCO dataset but also generate length-controllable and diverse image captions. Specifically, our non-autoregressive model outperforms the autoregressive baselines in terms of controllability and diversity, and also significantly improves the decoding efficiency for long captions. Our code and models are released at textcolormagentatexttthttps://github.com/bearcatt/LaBERT.