mlsanityData to 7 Oct 2026

Dynamic Memory Networks for Visual and Textual Question Answering

arXiv 1603.01417 ↗First posted 4 Mar 2016cs.NE cs.CL cs.CVcited by 62

Not on the map. Why?

Abstract (arXiv)

Neural network architectures with memory and attention mechanisms exhibit certain reasoning capabilities required for question answering. One such architecture, the dynamic memory network (DMN), obtained high accuracy on a variety of language tasks. However, it was not shown whether the architecture achieves strong results for question answering when supporting facts are not marked during training or whether it could be applied to other modalities such as images. Based on an analysis of the DMN, we propose several improvements to its memory and input modules. Together with these changes we introduce a novel input module for images in order to be able to answer visual questions. Our new DMN+ model improves the state of the art on both the Visual Question Answering dataset and the babi-10k text question-answering dataset without supporting fact supervision.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 19; 2023: 16; 2024: 6; 2025: 2.

62 papers.

Sort:

By area:

  1. 2021Pre-Trained Models: Past, Present and Futurecited by 319
  2. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  3. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  4. 2024Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Surveycited by 74
  5. 2021Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answeringcited by 56
  6. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  7. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  8. 2021Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generationcited by 47
  9. 2022Memory-Guided Semantic Learning Network for Temporal Sentence Groundingcited by 46
  10. 2021DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answeringcited by 35
  11. 2021Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Groundingcited by 31
  12. 2022Learning to Answer Visual Questions from Web Videoscited by 30
38 more
  1. 2023Multi-modal Machine Learning in Engineering Design: A Review and Future Directionscited by 27
  2. 2023MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detectioncited by 26
  3. 2023From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunitiescited by 24
  4. 2022Vision+X: A Survey on Multimodal Learning in the Light of Datacited by 22
  5. 2022Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformerscited by 18
  6. 2023Foundation Model is Efficient Multimodal Multitask Model Selectorcited by 16
  7. 2022Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisationcited by 15
  8. 2021Cognitive Visual Commonsense Reasoning Using Dynamic Working Memorycited by 14
  9. 2022VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challengescited by 14
  10. 2021Interpretable Visual Understanding with Cognitive Attention Networkcited by 12
  11. 2023Simple Baselines for Interactive Video Retrieval with Questions and Answerscited by 12
  12. 2024A Survey on Integrated Sensing, Communication, and Computationcited by 12
  13. 2022Endowing Language Models with Multimodal Knowledge Graph Representationscited by 11
  14. 2023Multimodal Graph Transformer for Multimodal Question Answeringcited by 10
  15. 2023Answer Mining from a Pool of Images: Towards Retrieval-Based Visual Question Answeringcited by 10
  16. 2023S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learningcited by 10
  17. 2023Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questionscited by 9
  18. 2025Hadamard product in deep learning: Introduction, Advances and Challengescited by 9
  19. 2021Neural Attention Models in Deep Learning: Survey and Taxonomycited by 8
  20. 2022Guiding Visual Question Answering with Attention Priorscited by 7
  21. 2022From Pixels to Objects: Cubic Visual Attention for Visual Question Answeringcited by 7
  22. 2021A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environmentcited by 6
  23. 2021Zero-Shot Open-Book Question Answeringcited by 6
  24. 2023Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Ordercited by 6
  25. 2021A Neural Question Answering System for Basic Questions about Subroutinescited by 5
  26. 2021Saying the Unseen: Video Descriptions via Dialog Agentscited by 5
  27. 2023Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQAcited by 5
  28. 2021A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysiscited by 4
  29. 2021End-to-End Egospheric Spatial Memorycited by 3
  30. 2022Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequencescited by 3
  31. 2021Towards Solving Multimodal Comprehensioncited by 2
  32. 2022MGA-VQA: Multi-Granularity Alignment for Visual Question Answeringcited by 2
  33. 2023A Brain-inspired Memory Transformation based Differentiable Neural Computer for Reasoning-based Question Answeringcited by 2
  34. 2023A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Informationcited by 2
  35. 2023Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answeringcited by 2
  36. 2023Multi-Clue Reasoning with Memory Augmentation for Knowledge-based Visual Question Answeringcited by 2
  37. 2024Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospectscited by 2
  38. 2021PEN4Rec: Preference Evolution Networks for Session-based Recommendationcited by 1

50 most cited of 62 All 62 (JSON)