# CapDet: Unifying Dense Captioning and Open-World Detection Pretraining

arXiv: https://arxiv.org/abs/2303.02489 · HTML: https://mlsanity.com/paper/2303.02489/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 45 of its 56 references that are in the map.
- First posted on arXiv 4 Mar 2023.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 45)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale](https://mlsanity.com/paper/1811.00982/) (2018)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)

## Built on by (most cited first, 26 of 26)

- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models](https://mlsanity.com/paper/2501.18954/) (2025)
- [DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection](https://mlsanity.com/paper/2404.09216/) (2024)
- [Multi-modal Queried Object Detection in the Wild](https://mlsanity.com/paper/2305.18980/) (2023)
- [Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions](https://mlsanity.com/paper/2406.07502/) (2024)
- [YOLOE: Real-Time Seeing Anything](https://mlsanity.com/paper/2503.07465/) (2025)
- [Segment and Caption Anything](https://mlsanity.com/paper/2312.00869/) (2023)
- [Generative Region-Language Pretraining for Open-Ended Object Detection](https://mlsanity.com/paper/2403.10191/) (2024)
- [OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion](https://mlsanity.com/paper/2407.07844/) (2024)
- [WeDetect: Fast Open-Vocabulary Object Detection as Retrieval](https://mlsanity.com/paper/2512.12309/) (2025)
- [ControlCap: Controllable Region-level Captioning](https://mlsanity.com/paper/2401.17910/) (2024)
- [Dense Video Object Captioning from Disjoint Supervision](https://mlsanity.com/paper/2306.11729/) (2023)
- [A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes](https://mlsanity.com/paper/2403.07469/) (2024)
- [Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation](https://mlsanity.com/paper/2504.09480/) (2025)
- [VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion](https://mlsanity.com/paper/2505.18986/) (2025)
- [PunchBench: Benchmarking MLLMs in Multimodal Punchline Comprehension](https://mlsanity.com/paper/2412.11906/) (2024)
- [OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning](https://mlsanity.com/paper/2404.03657/) (2024)
- [RTGen: Generating Region-Text Pairs for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2405.19854/) (2024)
- [DynRefer: Delving into Region-level Multimodal Tasks via Dynamic Resolution](https://mlsanity.com/paper/2405.16071/) (2024)
- [It's Just Another Day: Unique Video Captioning by Discriminative Prompting](https://mlsanity.com/paper/2410.11702/) (2024)
- [Prompt-Free Universal Region Proposal Network](https://mlsanity.com/paper/2603.17554/) (2026)
- [From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition](https://mlsanity.com/paper/2406.08358/) (2024)
- [Sustainable Self-evolution Adversarial Training](https://mlsanity.com/paper/2412.02270/) (2024)
- [RTGen: Real-Time Generative Detection Transformer](https://mlsanity.com/paper/2502.20622/) (2025)
- [Dynamic Relation Inference via Verb Embeddings](https://mlsanity.com/paper/2503.13021/) (2025)
- [VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection](https://mlsanity.com/paper/2605.03456/) (2026)

## Abstract (arXiv)

Benefiting from large-scale vision-language pre-training on image-text pairs, open-world detection methods have shown superior generalization ability under the zero-shot or few-shot detection settings. However, a pre-defined category space is still required during the inference stage of existing methods and only the objects belonging to that space will be predicted. To introduce a "real" open-world detector, in this paper, we propose a novel method named CapDet to either predict under a given category list or directly generate the category of predicted bounding boxes. Specifically, we unify the open-world detection and dense caption tasks into a single yet effective framework by introducing an additional dense captioning head to generate the region-grounded captions. Besides, adding the captioning task will in turn benefit the generalization of detection performance since the captioning dataset covers more concepts. Experiment results show that by unifying the dense caption task, our CapDet has obtained significant performance improvements (e.g., +2.1% mAP on LVIS rare classes) over the baseline method on LVIS (1203 classes). Besides, our CapDet also achieves state-of-the-art performance on dense captioning tasks, e.g., 15.44% mAP on VG V1.2 and 13.98% on the VG-COCO dataset.