mlsanityData to 7 Oct 2026

VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search

arXiv 2108.02725 ↗First posted 5 Aug 2021cs.CL cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Numerous online stock image libraries offer high quality yet copyright free images for use in marketing campaigns. To assist advertisers in navigating such third party libraries, we study the problem of automatically fetching relevant ad images given the ad text (via a short textual query for images). Motivated by our observations in logged data on ad image search queries (given ad text), we formulate a keyword extraction problem, where a keyword extracted from the ad text (or its augmented version) serves as the ad image query. In this context, we propose VisualTextRank: an unsupervised method to (i) augment input ad text using semantically similar ads, and (ii) extract the image query from the augmented ad text. VisualTextRank builds on prior work on graph based context extraction (biased TextRank in particular) by leveraging both the text and image of similar ads for better keyword extraction, and using advertiser category specific biasing with sentence-BERT embeddings. Using data collected from the Verizon Media Native (Yahoo Gemini) ad platform's stock image search feature for onboarding advertisers, we demonstrate the superiority of VisualTextRank compared to competitive keyword extraction baselines (including an 11% accuracy lift over biased TextRank). For the case when the stock image library is restricted to English queries, we show the effectiveness of VisualTextRank on multilingual ads (translated to English) while leveraging semantically similar English ads. Online tests with a simplified version of VisualTextRank led to a 28.7% increase in the usage of stock image search, and a 41.6% increase in the advertiser onboarding rate in the Verizon Media Native ad platform.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 370 of its 1,819 references that are in the map. First posted on arXiv 5 Aug 2021.

Builds on

370 of 1,819 references.

References · 370

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  9. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  10. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  11. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  12. 2017Graph Attention Networkscited by 8,854
38 more
  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017Mask R-CNNcited by 7,259
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  10. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  11. 2018How Powerful are Graph Neural Networks?cited by 4,355
  12. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  13. 2014Going Deeper with Convolutionscited by 4,231
  14. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  15. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  16. 2013Auto-Encoding Variational Bayescited by 3,980
  17. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  18. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  19. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  20. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  21. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  22. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  23. 2018YOLOv3: An Incremental Improvementcited by 2,652
  24. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  25. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  26. 2018Deep contextualized word representationscited by 2,285
  27. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  28. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
  29. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  30. 2015A large annotated corpus for learning natural language inferencecited by 1,837
  31. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  32. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  33. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  34. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  35. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  36. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  37. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  38. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428

50 most cited of 370 All 370 (JSON)

Built on by

Not cited yet.