mlsanityData to 7 Oct 2026

DenseCap: Fully Convolutional Localization Networks for Dense Captioning

arXiv 1511.07571 ↗First posted 24 Nov 2015cs.CV cs.LGcited by 176

Not on the map. Why?

Abstract (arXiv)

We introduce the dense captioning task, which requires a computer vision system to both localize and describe salient regions in images in natural language. The dense captioning task generalizes object detection when the descriptions consist of a single word, and Image Captioning when one predicted region covers the full image. To address the localization and description task jointly we propose a Fully Convolutional Localization Network (FCLN) architecture that processes an image with a single, efficient forward pass, requires no external regions proposals, and can be trained end-to-end with a single round of optimization. The architecture is composed of a Convolutional Network, a novel dense localization layer, and Recurrent Neural Network language model that generates the label sequences. We evaluate our network on the Visual Genome dataset, which comprises 94,000 images and 4,100,000 region-grounded captions. We observe both speed and accuracy improvements over baselines based on current state of the art approaches in both generation and retrieval settings.

Key facts. Cited by 176 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 50; 2022: 23; 2023: 39; 2024: 35; 2025: 22; 2026: 7.

176 papers.

Sort:

By area:

  1. 2021Unifying Vision-and-Language Tasks via Text Generationcited by 411
  2. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  3. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 300
  4. 2021VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioningcited by 190
  5. 2023Dense Text-to-Image Generation with Attention Modulationcited by 162
  6. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
  7. 2021From Show to Tell: A Survey on Deep Learning-based Image Captioningcited by 137
  8. 2021Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Cloudscited by 128
  9. 2022DRAMA: Joint Risk Localization and Captioning in Drivingcited by 125
  10. 2022GRiT: A Generative Region-to-text Transformer for Object Understandingcited by 119
  11. 2023Caption Anything: Interactive Image Description with Diverse Multimodal Controlscited by 98
  12. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
38 more
  1. 2022Language Models Can See: Plugging Visual Controls in Text Generationcited by 89
  2. 2023Expressive Text-to-Image Generation with Rich Textcited by 89
  3. 2022Make-A-Story: Visual Memory Conditioned Consistent Story Generationcited by 76
  4. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 74
  5. 2022X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioningcited by 70
  6. 2024FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusioncited by 67
  7. 2023Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoningcited by 63
  8. 2023SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentariescited by 57
  9. 2021D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Groundingcited by 52
  10. 2021Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualizationcited by 51
  11. 2024DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detectioncited by 48
  12. 2023FaithScore: Fine-grained Evaluations of Hallucinations in Large Vision-Language Modelscited by 44
  13. 2022Deep Learning Approaches on Image Captioning: A Reviewcited by 43
  14. 2024Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptionscited by 43
  15. 2021Visual Goal-Step Inference using wikiHowcited by 42
  16. 2022Spatiality-guided Transformer for 3D Dense Captioning on Point Cloudscited by 40
  17. 2022The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoningcited by 38
  18. 2021ContIG: Self-supervised Multimodal Contrastive Learning for Medical Imaging with Geneticscited by 35
  19. 2024LocCa: Visual Pretraining with Location-aware Captionerscited by 35
  20. 2023FuseCap: Leveraging Large Language Models for Enriched Fused Image Captionscited by 33
  21. 2021INVIGORATE: Interactive Visual Grounding and Grasping in Cluttercited by 32
  22. 2023Helping Hands: An Object-Aware Ego-Centric Video Recognition Modelcited by 31
  23. 2023Segment and Caption Anythingcited by 30
  24. 2024Generative Region-Language Pretraining for Open-Ended Object Detectioncited by 29
  25. 2021Multimodal Entity Linking for Tweetscited by 28
  26. 2021Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioningcited by 27
  27. 2021Survey: Transformer based Video-Language Pre-trainingcited by 27
  28. 2021MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioningcited by 27
  29. 2021CityFlow-NL: Tracking and Retrieval of Vehicles at City Scale by Natural Language Descriptionscited by 26
  30. 2023CapDet: Unifying Dense Captioning and Open-World Detection Pretrainingcited by 26
  31. 2024Robin3D: Improving 3D Large Language Model via Robust Instruction Tuningcited by 26
  32. 2024FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularitycited by 26
  33. 2021Towards Accurate Text-based Image Captioning with Content Diversity Explorationcited by 25
  34. 2021Image Captioning for Effective Use of Language Models in Knowledge-Based Visual Question Answeringcited by 25
  35. 2022Is an Object-Centric Video Representation Beneficial for Transfer?cited by 24
  36. 2021ReFormer: The Relational Transformer for Image Captioningcited by 23
  37. 2023Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generationcited by 23
  38. 2021CIDEr-R: Robust Consensus-based Image Description Evaluationcited by 22

50 most cited of 176 All 176 (JSON)