# Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs

arXiv: https://arxiv.org/abs/2003.00387 · HTML: https://mlsanity.com/paper/2003.00387/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 30 of 87)

- [VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning](https://mlsanity.com/paper/2102.10407/) (2021)
- [Interactive and Explainable Region-guided Radiology Report Generation](https://mlsanity.com/paper/2304.08295/) (2023)
- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [A Comprehensive Survey of Scene Graphs: Generation and Application](https://mlsanity.com/paper/2104.01111/) (2021)
- [Panoptic Scene Graph Generation](https://mlsanity.com/paper/2207.11247/) (2022)
- [Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning](https://mlsanity.com/paper/2110.01705/) (2021)
- [Tailor: Generating and Perturbing Text with Semantic Controls](https://mlsanity.com/paper/2107.07150/) (2021)
- [Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation](https://mlsanity.com/paper/2203.09811/) (2022)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs](https://mlsanity.com/paper/2311.01015/) (2023)
- [Deep Learning Approaches on Image Captioning: A Review](https://mlsanity.com/paper/2201.12944/) (2022)
- [Panoptic Scene Graph Generation with Semantics-Prototype Learning](https://mlsanity.com/paper/2307.15567/) (2023)
- [Human-like Controllable Image Captioning with Verb-specific Semantic Roles](https://mlsanity.com/paper/2103.12204/) (2021)
- [Human-Object Interaction Detection via Disentangled Transformer](https://mlsanity.com/paper/2204.09290/) (2022)
- [From Easy to Hard: Learning Language-guided Curriculum for Visual Question Answering on Remote Sensing Data](https://mlsanity.com/paper/2205.03147/) (2022)
- [ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing](https://mlsanity.com/paper/2303.02437/) (2023)
- [Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention](https://mlsanity.com/paper/2311.10988/) (2023)
- [Towards Accurate Text-based Image Captioning with Content Diversity Exploration](https://mlsanity.com/paper/2105.03236/) (2021)
- [Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation](https://mlsanity.com/paper/2206.01988/) (2022)
- [Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning](https://mlsanity.com/paper/2103.05187/) (2021)
- [HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation](https://mlsanity.com/paper/2303.15994/) (2023)
- [O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning](https://mlsanity.com/paper/2108.02359/) (2021)
- [Pair then Relation: Pair-Net for Panoptic Scene Graph Generation](https://mlsanity.com/paper/2307.08699/) (2023)
- [Auto-Parsing Network for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/2108.10568/) (2021)
- [OpenPSG: Open-set Panoptic Scene Graph Generation via Large Multimodal Models](https://mlsanity.com/paper/2407.11213/) (2024)
- [Controllable Image Captioning via Prompting](https://mlsanity.com/paper/2212.01803/) (2022)
- [Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling](https://mlsanity.com/paper/2308.05081/) (2023)
- [SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding](https://mlsanity.com/paper/2407.03200/) (2024)
- [Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrieval](https://mlsanity.com/paper/2111.09276/) (2021)

## Abstract (arXiv)

Humans are able to describe image contents with coarse to fine details as they wish. However, most image captioning models are intention-agnostic which can not generate diverse descriptions according to different user intentions initiatively. In this work, we propose the Abstract Scene Graph (ASG) structure to represent user intention in fine-grained level and control what and how detailed the generated description should be. The ASG is a directed graph consisting of three types of abstract nodes (object, attribute, relationship) grounded in the image without any concrete semantic labels. Thus it is easy to obtain either manually or automatically. From the ASG, we propose a novel ASG2Caption model, which is able to recognise user intentions and semantics in the graph, and therefore generate desired captions according to the graph structure. Our model achieves better controllability conditioning on ASGs than carefully designed baselines on both VisualGenome and MSCOCO datasets. It also significantly improves the caption diversity via automatically sampling diverse ASGs as control signals.