mlsanityData to 14 Oct 2026

Visual Commonsense R-CNN

arXiv 2002.12204 ↗First posted 27 Feb 2020cs.CVcited by 106

Not on the map. Why?

Abstract (arXiv)

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN.

Key facts. Cited by 106 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 25; 2022: 20; 2023: 21; 2024: 17; 2025: 20; 2026: 3.

106 papers.

Sort:

By area:

  1. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  2. 2021Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identificationcited by 114
  3. 2021Causal Attention for Vision-Language Taskscited by 111
  4. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  5. 2021Interventional Video Grounding with Dual Contrastive Learningcited by 94
  6. 2023Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Imagescited by 91
  7. 2021Deconfounded Video Moment Retrieval with Causal Interventioncited by 84
  8. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  9. 2021Let there be a clock on the beach: Reducing Object Hallucination in Image Captioningcited by 76
  10. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
  11. 2023Equivariant Similarity for Vision-Language Foundation Modelscited by 52
  12. 2022Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigationcited by 51
38 more
  1. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  2. 2023Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatmentcited by 47
  3. 2021Human Trajectory Prediction via Counterfactual Analysiscited by 42
  4. 2022Gender and Racial Bias in Visual Question Answering Datasetscited by 39
  5. 2023Context De-confounded Emotion Recognitioncited by 34
  6. 2024Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlookcited by 33
  7. 2024Auto-Encoding Morph-Tokens for Multimodal LLMcited by 30
  8. 2024Towards Multimodal Sentiment Analysis Debiasing via Bias Purificationcited by 27
  9. 2022ComCLIP: Training-Free Compositional Image and Text Matchingcited by 26
  10. 2022Causal Reasoning Meets Visual Representation Learning: A Prospective Studycited by 24
  11. 2024Robust Emotion Recognition in Context Debiasingcited by 24
  12. 2023Causal Reinforcement Learning: A Surveycited by 23
  13. 2021Learning Domain Invariant Representations for Generalizable Person Re-Identificationcited by 22
  14. 2021CIDEr-R: Robust Consensus-based Image Description Evaluationcited by 22
  15. 2023Long-Tailed Partial Label Learning via Dynamic Rebalancingcited by 22
  16. 2023Disentangled Contrastive Collaborative Filteringcited by 22
  17. 2025Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoningcited by 20
  18. 2022Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identificationcited by 18
  19. 2022Selective Query-guided Debiasing for Video Corpus Moment Retrievalcited by 18
  20. 2023Causal Unsupervised Semantic Segmentationcited by 18
  21. 2021Disentangled Motif-aware Graph Learning for Phrase Groundingcited by 17
  22. 2021Deconfounded Visual Groundingcited by 16
  23. 2023Visual Causal Scene Refinement for Video Question Answeringcited by 16
  24. 2024Visual Knowledge in the Big Model Era: Retrospect and Prospectcited by 16
  25. 2021Class-Balanced Active Learning for Image Classificationcited by 15
  26. 2021Improving Weakly-supervised Object Localization via Causal Interventioncited by 14
  27. 2021Causal Incremental Graph Convolution for Recommender System Retrainingcited by 14
  28. 2021Weakly-Supervised Video Object Grounding via Causal Interventioncited by 13
  29. 2022Interventional Multi-Instance Learning with Deconfounded Instance-Level Predictioncited by 13
  30. 2023Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inferencecited by 13
  31. 2022Beyond Object Recognition: A New Benchmark towards Object Concept Learningcited by 11
  32. 2024De-confounded Data-free Knowledge Distillation for Handling Distribution Shiftscited by 11
  33. 2024Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Trainingcited by 11
  34. 2021Confounder Identification-free Causal Visual Feature Learningcited by 10
  35. 2021DROID: Driver-centric Risk Object Identificationcited by 9
  36. 2021Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Interventioncited by 9
  37. 2022Graph Reasoning Transformer for Image Parsingcited by 9
  38. 2022Causal Inference via Style Transfer for Out-of-distribution Generalisationcited by 8

50 most cited of 106 All 106 (JSON)