# Diverse Image Captioning with Context-Object Split Latent Spaces

arXiv: https://arxiv.org/abs/2011.00966 · HTML: https://mlsanity.com/paper/2011.00966/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2020.

## Built on by (most cited first, 22 of 22)

- [From Show to Tell: A Survey on Deep Learning-based Image Captioning](https://mlsanity.com/paper/2107.06912/) (2021)
- [Make-A-Story: Visual Memory Conditioned Consistent Story Generation](https://mlsanity.com/paper/2211.13319/) (2022)
- [ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues](https://mlsanity.com/paper/2201.06696/) (2022)
- [SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text](https://mlsanity.com/paper/2204.11964/) (2022)
- [IC3: Image Captioning by Committee Consensus](https://mlsanity.com/paper/2302.01328/) (2023)
- [Causal Hidden Markov Model for Time Series Disease Forecasting](https://mlsanity.com/paper/2103.16391/) (2021)
- [Learning Multimodal Data Augmentation in Feature Space](https://mlsanity.com/paper/2212.14453/) (2022)
- [Variational Topic Inference for Chest X-Ray Report Generation](https://mlsanity.com/paper/2107.07314/) (2021)
- [Look, Remember and Reason: Grounded reasoning in videos with language models](https://mlsanity.com/paper/2306.17778/) (2023)
- [Learning Distinct and Representative Styles for Image Captioning](https://mlsanity.com/paper/2209.08231/) (2022)
- [Parts of Speech-Grounded Subspaces in Vision-Language Models](https://mlsanity.com/paper/2305.14053/) (2023)
- [On Distinctive Image Captioning via Comparing and Reweighting](https://mlsanity.com/paper/2204.03938/) (2022)
- [Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval](https://mlsanity.com/paper/2207.14428/) (2022)
- [Set Prediction Guided by Semantic Concepts for Diverse Video Captioning](https://mlsanity.com/paper/2312.15720/) (2023)
- [Diverse Image Captioning with Grounded Style](https://mlsanity.com/paper/2205.01813/) (2022)
- [RONA: Pragmatically Diverse Image Captioning with Coherence Relations](https://mlsanity.com/paper/2503.10997/) (2025)
- [IRONIC: Coherence-Aware Reasoning Chains for Multi-Modal Sarcasm Detection](https://mlsanity.com/paper/2505.16258/) (2025)
- [Multiple Choice Learning of Low-Rank Adapters for Language Modeling](https://mlsanity.com/paper/2507.10419/) (2025)
- [Personalized Image Descriptions from Attention Sequences](https://mlsanity.com/paper/2512.06662/) (2025)
- [Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis](https://mlsanity.com/paper/2408.04909/) (2024)
- [Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition](https://mlsanity.com/paper/2110.04042/) (2021)
- [Group-based Distinctive Image Captioning with Memory Difference Encoding and Attention](https://mlsanity.com/paper/2504.02496/) (2025)

## Abstract (arXiv)

Diverse image captioning models aim to learn one-to-many mappings that are innate to cross-domain datasets, such as of images and texts. Current methods for this task are based on generative latent variable models, e.g. VAEs with structured latent spaces. Yet, the amount of multimodality captured by prior work is limited to that of the paired training data -- the true diversity of the underlying generative process is not fully captured. To address this limitation, we leverage the contextual descriptions in the dataset that explain similar contexts in different visual scenes. To this end, we introduce a novel factorization of the latent space, termed context-object split, to model diversity in contextual descriptions across images and texts within the dataset. Our framework not only enables diverse captioning through context-based pseudo supervision, but extends this to images with novel objects and without paired captions in the training data. We evaluate our COS-CVAE approach on the standard COCO dataset and on the held-out COCO dataset consisting of images with novel objects, showing significant gains in accuracy and diversity.