mlsanityData to 14 Oct 2026

Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering

arXiv 1812.05252 ↗First posted 13 Dec 2018cs.CV eess.IVcited by 114

Not on the map. Why?

Cited by 22 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Learning effective fusion of multi-modality features is at the heart of visual question answering. We propose a novel method of dynamically fusing multi-modal features with intra- and inter-modality information flow, which alternatively pass dynamic information between and across the visual and language modalities. It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering. We also show that the proposed dynamic intra-modality attention flow conditioned on the other modality can dynamically modulate the intra-modality attention of the target modality, which is vital for multimodality feature fusion. Experimental evaluations on the VQA 2.0 dataset show that the proposed method achieves state-of-the-art VQA performance. Extensive ablation studies are carried out for the comprehensive analysis of the proposed method.

Key facts. Cited by 114 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 33; 2022: 34; 2023: 24; 2024: 11; 2025: 7; 2026: 5.

114 papers.

Sort:

By area:

  1. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,919
  2. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  3. 2023A Survey on Multimodal Large Language Modelscited by 909
  4. 2023LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attentioncited by 781
  5. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  6. 2023A Comprehensive Overview of Large Language Modelscited by 648
  7. 2023LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Modelcited by 602
  8. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 431
  9. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  10. 2022Multimodal Learning with Transformers: A Surveycited by 400
  11. 2023Chameleon: Plug-and-Play Compositional Reasoning with Large Language Modelscited by 356
  12. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
38 more
  1. 2021IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoningcited by 267
  2. 2022Learning to Answer Questions in Dynamic Audio-Visual Scenarioscited by 191
  3. 2021Fast Convergence of DETR with Spatially Modulated Co-Attentioncited by 176
  4. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 165
  5. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  6. 2022A Survey of Deep Learning for Mathematical Reasoningcited by 124
  7. 2021Causal Attention for Vision-Language Taskscited by 111
  8. 2022ConvMAE: Masked Convolution Meets Masked Autoencoderscited by 105
  9. 2022Exploiting Unlabeled Data with Vision and Language Models for Object Detectioncited by 97
  10. 2023DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignmentcited by 90
  11. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 89
  12. 2021Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Modelscited by 75
  13. 2023T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answeringcited by 60
  14. 2023Read-only Prompt Optimization for Vision-Language Few-shot Learningcited by 58
  15. 2021A Simple Long-Tailed Recognition Baseline via Vision-Language Modelcited by 49
  16. 2023HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attentioncited by 44
  17. 2021VT-CLIP: Enhancing Vision-Language Models with Visual-guided Textscited by 42
  18. 2023Transformers in Speech Processing: A Surveycited by 39
  19. 2021Container: Context Aggregation Networkcited by 37
  20. 2021Dual-stream Network for Visual Recognitioncited by 33
  21. 2022Multi-Attention Network for Compressed Video Referring Object Segmentationcited by 28
  22. 2024OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusioncited by 28
  23. 2023Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applicationscited by 27
  24. 2022Progressive Learning for Image Retrieval with Hybrid-Modality Queriescited by 26
  25. 2021Coarse-to-Fine Reasoning for Visual Question Answeringcited by 25
  26. 2023Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modalscited by 24
  27. 2023Robust Visual Question Answering: Datasets, Methods, and Future Challengescited by 23
  28. 2022Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semanticscited by 22
  29. 2022Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Taskscited by 21
  30. 2021Oriented Object Detection with Transformercited by 20
  31. 2021VisQA: X-raying Vision and Language Reasoning in Transformerscited by 19
  32. 2022V-Doc : Visual questions answers with Documentscited by 19
  33. 2025Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learningcited by 19
  34. 2022Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problemcited by 18
  35. 2021Scheduled Sampling in Vision-Language Pretraining with Decoupled Encoder-Decoder Networkcited by 17
  36. 2021LPF: A Language-Prior Feedback Objective Function for De-biased Visual Question Answeringcited by 17
  37. 2021How Transferable are Reasoning Patterns in VQA?cited by 16
  38. 2021Auto-Parsing Network for Image Captioning and Visual Question Answeringcited by 16

50 most cited of 114 All 114 (JSON)