Awesome Image Captioning

A curated list of image captioning and related area. :-)

Contributing

Please feel free to send me pull requests or email (chihung.chan@outlook.com) to add links. Markdown format:

- [Paper Name](link) - Author 1 et al, `Conference Year`. [[code]](link)

Change Log

• May 25 An up-to-date paper list about vision-and-language pre-training is available here.

Table of Contents

• Papers
  • Survey
  • Before - 2015 - 2016 - 2017 - 2018 - 2019 - 2020
• Dataset
• Image Captioning Challenge
• Popular Implementations
  • PyTorch
  • TensorFlow
  • Torch
  • Others

Papers

Survey

• A Comprehensive Survey of Deep Learning for Image Captioning - Hossain M et al, arXiv preprint 2018.

  Before

• I2t: Image parsing to text description - Yao B Z et al, P IEEE 2011.
• Im2Text: Describing Images Using 1 Million Captioned Photographs - Ordonez V et al, NIPS 2011. [project web]
• Deep Captioning with Multimodal Recurrent Neural Networks - Mao J et al, arXiv preprint 2014.

2015

CVPR 2015

• Show and Tell: A Neural Image Caption Generator - Vinyals O et al, CVPR 2015. [code] [code]
• Deep Visual-Semantic Alignments for Generating Image Descriptions - Karpathy A et al, CVPR 2015. [project web] [code]
• Mind’s Eye: A Recurrent Visual Representation for Image Caption Generation - Chen X et al, CVPR 2015.
• Long-term Recurrent Convolutional Networks for Visual Recognition and Description - Donahue J et al, CVPR 2015. [code] [project web]

  ICCV 2015

• Guiding the Long-Short Term Memory Model for Image Caption Generation - Jia X et al, ICCV 2015.
• Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images - Mao J et al, ICCV 2015. [code]

  NIPS 2015

• Expressing an Image Stream with a Sequence of Natural Sentences - Park C C et al, NIPS 2015. [code]

  ICML 2015

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention - Xu K et al, ICML 2015. [project] [code] [code]

  arXiv preprint 2015

• Order-Embeddings of Images and Language - Vendrov I et al, arXiv preprint 2015. [code]
• Generating Images from Captions with Attention - Mansimov E et al, arXiv preprint 2015. [code]
• Learning FRAME Models Using CNN Filters for Knowledge Visualization - Lu Y, et al, arXiv preprint 2015. [code]
• Aligning where to see and what to tell: image caption with region-based attention and scene factorization - Jin J et al, arXiv preprint 2015.

2016

CVPR 2016

• Image captioning with semantic attention - You Q et al, CVPR 2016. [code]
• DenseCap: Fully Convolutional Localization Networks for Dense Captioning - Johnson J et al, CVPR 2016. [code]
• What value do explicit high level concepts have in vision to language problems? - Wu Q et al, CVPR 2016.
• Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data - Lisa Anne Hendricks et al, CVPR 2016. [code]
• SPICE: Semantic Propositional Image Caption Evaluation - Anderson P et al, ECCV 2016. [code]

  ACMMM 2016

• Image Captioning with Deep Bidirectional LSTMs - Wang C et al, ACMMM 2016. [code]

  ACL 2016

• Multimodal Pivots for Image Caption Translation - Hitschler J et al, ACL 2016.

  arXiv preprint 2016

• Image Caption Generation with Text-Conditional Semantic Attention - Zhou L et al, arXiv preprint 2016. [code]
• DeepDiary: Automatic Caption Generation for Lifelogging Image Streams - Fan C et al, arXiv preprint 2016.
• Learning to generalize to new compositions in image understanding - Atzmon Y et al, arXiv preprint 2016.
• Generating captions without looking beyond objects - Heuer H et al, arXiv preprint 2016.
• Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning - Chen W et al, arXiv preprint 2016. [code]
• Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering - Liu H et al, arXiv preprint 2016.
• Recurrent Highway Networks with Language CNN for Image Captioning - Gu J et al, arXiv preprint 2016.

2017

CVPR 2017

• Captioning Images with Diverse Objects - Venugopalan S et al, CVPR 2017. [code]
• Top-down Visual Saliency Guided by Captions - Ramanishka V et al, CVPR 2017. [code]
• Self-Critical Sequence Training for Image Captioning - Steven J et al, CVPR 2017. [code]
• Dense Captioning with Joint Inference and Visual Context - Yang L et al, CVPR 2017. [code]
• Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition - Yufei W et al, CVPR 2017. [code]
• A Hierarchical Approach for Generating Descriptive Image Paragraphs - Krause J et al, CVPR 2017. [code]
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward - Ren Z et al, CVPR 2017.
• Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects - Ting Y et al, CVPR 2017.
• Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning - Lu J et al, CVPR 2017. [code]
• Attend to You: Personalized Image Captioning with Context Sequence Memory Networks - CC Park et al, CVPR 2017. [code]
• SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning - Chen L et al, CVPR 2017. [code]
• Bidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-In-The-Blank Image Captioning - Qing S et al, CVPR 2017.

  ICCV 2017

• Areas of Attention for Image Captioning - Pedersoli M et al, ICCV 2017.
• Boosting Image Captioning with Attributes - Yao T et al, ICCV 2017.
• An Empirical Study of Language CNN for Image Captioning - Gu J et al, ICCV 2017.
• Improved Image Captioning via Policy Gradient Optimization of SPIDEr - Liu S et al, ICCV 2017.
• Towards Diverse and Natural Image Descriptions via a Conditional GAN - Dai B et al, ICCV 2017. [code]
• Paying Attention to Descriptions Generated by Image Captioning Models - Tavakoliy H R et al, ICCV 2017.
• Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner - Chen T H et al, ICCV 2017. [code]

  AAAI 2017

• Image Caption with Global-Local Attention - Li L et al, AAAI 2017.
• Reference Based LSTM for Image Captioning - Chen M et al, AAAI 2017.
• Attention Correctness in Neural Image Captioning - Liu C et al, AAAI 2017.
• Text-guided Attention Model for Image Captioning - Mun J et al, AAAI 2017. [code]

  NIPS 2017

• Contrastive Learning for Image Captioning - Dai B et al, NIPS 2017. [code]

  TPAMI 2017

• Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge - Vinyals O et al, TPAMI 2017. [code]

  arXiv preprint 2017

• MAT: A Multimodal Attentive Translator for Image Captioning - Liu C et al, arXiv preprint 2017.
• Actor-Critic Sequence Training for Image Captioning - Zhang L et al, arXiv preprint 2017.
• What is the Role of Recurrent Neural Networks (RNNs) in an Image Caption Generator? - Tanti M et al, arXiv preprint 2017. [code]
• Self-Guiding Multimodal LSTM - when we do not have a perfect training dataset for image captioning - Xian Y et al, arXiv preprint 2017.
• Phrase-based Image Captioning with Hierarchical LSTM Model - Tan Y H et al, arXiv preprint 2017.
• Show-and-Fool: Crafting Adversarial Examples for Neural Image Captioning - Chen H et al, arXiv preprint 2017.

2018

CVPR 2018

• Neural Baby Talk - Lu J et al, CVPR 2018. [code]
• Convolutional Image Captioning - Aneja J et al, CVPR 2018.
• Learning to Evaluate Image Captioning - Cui Y et al, CVPR 2018. [code]
• Discriminability Objective for Training Descriptive Captions - Luo R et al, CVPR 2018. [code]
• SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text - Mathews A et al, CVPR 2018.
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering - Anderson P et al, CVPR 2018. [code]
• GroupCap: Group-Based Image Captioning With Structured Relevance and Diversity Constraints - Chen F et al, CVPR 2018.

  ECCV 2018

• Unpaired Image Captioning by Language Pivoting - Gu J et al, ECCV 2018.
• Recurrent Fusion Network for Image Captioning - Jiang W et al, ECCV 2018.
• Exploring Visual Relationship for Image Captioning - Yao T et al, ECCV 2018.
• Rethinking the Form of Latent States in Image Captioning - Dai B et al, ECCV 2018. [code]
• Boosted Attention: Leveraging Human Attention for Image Captioning - Chen S et al, ECCV 2018.
• "Factual" or "Emotional": Stylized Image Captioning with Adaptive Learning and Attention - Chen T et al, ECCV 2018.

  AAAI 2018

• Learning to Guide Decoding for Image Captioning - Jiang W et al, AAAI 2018.
• Stack-Captioning: Coarse-to-Fine Learning for Image Captioning - Gu J et al, AAAI 2018. [code]
• Temporal-difference Learning with Sampling Baseline for Image Captioning - Chen H et al, AAAI 2018.

  NeurIPS 2018

• Partially-Supervised Image Captioning - Anderson P et al, NeurIPS 2018.
• A Neural Compositional Paradigm for Image Captioning - Dai B et al, NeurIPS 2018.

  NAACL 2018

• Defoiling Foiled Image Captions - Wang J et al, NAACL 2018.
• Punny Captions: Witty Wordplay in Image Descriptions - Chandrasekaran A et al, NAACL 2018. [code]
• Object Counts! Bringing Explicit Detections Back into Image Captioning - Aneja J et al, NAACL 2018.

  ACL 2018

• Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning - Sharma P et al, ACL 2018. [code]
• Attacking visual language grounding with adversarial examples: A case study on neural image captioning - Chen H et al, ACL 2018. [code]

  EMNLP 2018

• simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions - Liu et al, EMNLP 2018. [code]

  arXiv preprint 2018

• Improved Image Captioning with Adversarial Semantic Alignment - Melnyk I et al, arXiv preprint 2018.
• Improving Image Captioning with Conditional Generative Adversarial Nets - Chen C et al, arXiv preprint 2018.
• CNN+CNN: Convolutional Decoders for Image Captioning - Wang Q et al, arXiv preprint 2018.
• Diverse and Controllable Image Captioning with Part-of-Speech Guidance - Deshpande A et al, arXiv preprint 2018.

2019

CVPR 2019

• Unsupervised Image Captioning - Yang F et al, CVPR 2019. [code]
• Engaging Image Captioning Via Personality - Shuster K et al, CVPR 2019.
• Pointing Novel Objects in Image Captioning - Li Y et al, CVPR 2019.
• Auto-Encoding Scene Graphs for Image Captioning - Yang X et al, CVPR 2019.
• Context and Attribute Grounded Dense Captioning - Yin G et al, CVPR 2019.
• Look Back and Predict Forward in Image Captioning - Qin Y et al, CVPR 2019.
• Self-critical n-step Training for Image Captioning - Gao J et al, CVPR 2019.
• Intention Oriented Image Captions with Guiding Objects - Zheng Y et al, CVPR 2019.
• Describing like humans: on diversity in image captioning - Wang Q et al, CVPR 2019.
• Adversarial Semantic Alignment for Improved Image Captions - Dognin P et al, CVPR 2019.
• MSCap: Multi-Style Image Captioning With Unpaired Stylized Text - Gao L et al, CVPR 2019.
• Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech - Aditya D et al, CVPR 2019.
• Good News, Everyone! Context driven entity-aware captioning for news images - Biten A F et al, CVPR 2019. [code]
• CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection - Zhang L et al, CVPR 2019. [code]
• Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning - Kim D et al, CVPR 2019. [code]
• Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions - Cornia M et al, CVPR 2019. [code]
• Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables - Xu Y et al, CVPR 2019.

  AAAI 2019

• Meta Learning for Image Captioning - Li N et al, AAAI 2019.
• Learning Object Context for Dense Captioning - Li X et al, AAAI 2019.
• Hierarchical Attention Network for Image Captioning - Wang W et al, AAAI 2019.
• Deliberate Residual based Attention Network for Image Captioning - Gao L et al, AAAI 2019.
• Improving Image Captioning with Conditional Generative Adversarial Nets - Chen C et al, AAAI 2019.
• Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding - Song L et al, AAAI 2019.

  ACL 2019

• Dense Procedure Captioning in Narrated Instructional Videos - Shi B et al, ACL 2019.
• Informative Image Captioning with External Sources of Information - Zhao S et al, ACL 2019.
• Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning - Fan Z et al, ACL 2019.

  BMVC 2019

• Image Captioning with Unseen Objects - Demirel et al, BMVC 2019.
• Look and Modify: Modification Networks for Image Captioning - Sammani et al, BMVC 2019. [code]
• Show, Infer and Tell: Contextual Inference for Creative Captioning - Khare et al, BMVC 2019. [code]
• SC-RANK: Improving Convolutional Image Captioning with Self-Critical Learning and Ranking Metric-based Reward - Yan et al, BMVC 2019.

  ICCV 2019

• Hierarchy Parsing for Image Captioning - Yao T et al, ICCV 2019.
• Entangled Transformer for Image Captioning - Li G et al, ICCV 2019.
• Attention on Attention for Image Captioning - Huang L et al, ICCV 2019. [code]
• Reflective Decoding Network for Image Captioning - Ke L at al, ICCV 2019.
• Learning to Collocate Neural Modules for Image Captioning - Yang X et al, ICCV 2019.

  NeurIPS 2019

• Image Captioning: Transforming Objects into Words - Herdade S et al, NeurIPS 2019.
• Adaptively Aligned Image Captioning via Adaptive Attention Time - Huang L et al, NeurIPS 2019. [code]
• Variational Structured Semantic Inference for Diverse Image Captioning - Chen F et al, NeurIPS 2019.
• Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations - Liu F et al, NeurIPS 2019. [code]

  IJCAI 2019

• Image Captioning with Compositional Neural Module Networks - Tian J et al, IJCAI 2019.
• Exploring and Distilling Cross-Modal Information for Image Captioning - Liu F et al, IJCAI 2019.
• Swell-and-Shrink: Decomposing Image Captioning by Transformation and Summarization - Wang H et al, IJCAI 2019.
• Hornet: a hierarchical offshoot recurrent network for improving person re-ID via image captioning - Yan S et al, IJCAI 2019.

  EMNLP 2019

• Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach - Kim D J et al, EMNLP 2019.
• TIGEr: Text-to-Image Grounding for Image Caption Evaluation - Jiang M et al, EMNLP 2019.
• REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning - Jiang M et al, EMNLP 2019.
• Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering - Changpinyo S et al, EMNLP 2019.

  CoNLL 2019

• Compositional Generalization in Image Captioning - Nikolaus M et al, CoNLL 2019. [code]

2020

AAAI 2020

• MemCap: Memorizing Style Knowledge for Image Captioning - Zhao et al, AAAI 2020.
• Unified Vision-Language Pre-Training for Image Captioning and VQA - Zhou L et al, AAAI 2020.
• Show, Recall, and Tell: Image Captioning with Recall Mechanism - Wang L et al, AAAI 2020.
• Reinforcing an Image Caption Generator using Off-line Human Feedback - Hongsuck Seo P et al, AAAI 2020.
• Interactive Dual Generative Adversarial Networks for Image Captioning - Liu et al, AAAI 2020.
• Feature Deformation Meta-Networks in Image Captioning of Novel Objects - Cao et al, AAAI 2020.
• Joint Commonsense and Relation Reasoning for Image and Video Captioning - Hou et al, AAAI 2020.
• Learning Long- and Short-Term User Literal-Preference with Multimodal Hierarchical Transformer Network for Personalized Image Caption - Zhang et al, AAAI 2020.

CVPR 2020

• Normalized and Geometry-Aware Self-Attention Network for Image Captioning - Guo L et al, CVPR 2020.
• Object Relational Graph with Teacher-Recommended Learning for Video Captioning - Zhang Z et al, CVPR 2020.
• Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs - Chen S et al, CVPR 2020.
• X-Linear Attention Networks for Image Captioning - Pan et al, CVPR 2020.

ACL 2020

• Improving Image Captioning with Better Use of Caption - Shi Z et al, ACL 2020.
• Cross-modal Coherence Modeling for Caption Generation - Alikhani M et al, ACL 2020.
• [Improving Image Captioning Evaluation by Considering Inter References Variance]() - Yi Y et al, ACL 2020.
• [MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning]() - Lei J et al, ACL 2020.
• Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA - Kim H et al, ACL 2020.

ECCV 2020

• Length-Controllable Image Captioning - Deng C et al, ECCV 2020.
• Captioning Images Taken by People Who Are Blind - Gurari D et al, ECCV 2020.
• Towards Unique and Informative Captioning of Images - Wang Z et al, ECCV 2020.
• Learning Visual Representations with Caption Annotations - Sariyildiz M et al, ECCV 2020.
• Comprehensive Image Captioning via Scene Graph Decomposition - Zhong Y et al, ECCV 2020.
• SODA: Story Oriented Dense Video Captioning Evaluation Framework - Fujita S et al, ECCV 2020.
• TextCaps: a Dataset for Image Captioning with Reading Comprehension - Sidorov O et al, ECCV 2020.
• Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets - Wang J et al, ECCV 2020.
• Learning to Generate Grounded Visual Captions without Localization Supervision - Ma C et al, ECCV 2020.
• Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards - Yang X et al, ECCV 2020.
• Learning Modality Interaction for Temporal Sentence Localization and Event Captioning in Videos - Chen S et al, ECCV 2020.

EMNLP 2020

• CapWAP: Image Captioning with a Purpose - Fisch A et al, EMNLP 2020.
• X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers - Cho J et al, EMNLP 2020.
• Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning - Fang Z et al, EMNLP 2020.
• Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements - Li Y et al, EMNLP 2020.

NeurIPS 2020

• Diverse Image Captioning with Context-Object Split Latent Spaces - Mahajan S et al, NeurIPS 2020.
• RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning - Chiaro R et al, NeurIPS 2020.

Dataset

• nocaps, LANG: English
• MS COCO, LANG: English.
• Flickr 8k, LANG: English.
• Flickr 30k, LANG: English.
• AI Challenger, LANG: Chinese.
• Visual Genome, LANG: English.
• SBUCaptionedPhotoDataset, LANG: English.
• IAPR TC-12, LANG: English, German and Spanish.

Image Captioning Challenge

• Microsoft COCO Image Captioning
• Google AI Blog: Conceptual Captions

Popular Implementations

PyTorch

• ruotianluo/self-critical.pytorch
• ruotianluo/ImageCaptioning.pytorch
• jiasenlu/NeuralBabyTalk

  TensorFlow

• tensorflow/models/im2txt
• DeepRNN/image_captioning

  Torch

• jcjohnson/densecap
• karpathy/neuraltalk2
• jiasenlu/AdaptiveAttention

  Others

• emansim/text2image
• apple2373/chainer-caption
• peteanderson80/bottom-up-attention

Licenses

To the extent possible under law, Zhihong Chen has waived all copyright and related or neighboring rights to this work.