MVCE-Net: Multi-View Region Feature and Caption Enhancement Co-Attention Network for Visual Question Answering
Source abstract
Abstract
Visual question answering (VQA) requires a deep understanding of images and their corresponding textual questions to answer questions about images more accurately. However, existing models tend to ignore the implicit knowledg... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Multimodal Machine Learning Applications · Advanced Image and Video Retrieval Techniques · Domain Adaptation and Few-Shot Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (34)
Show source-provided references
1. Vqa: Visual question answering
2. Deep modular co-attention networks for visual question answering
3. Dynamic fusion with intra-and inter-modality attention flow for visual question answering
4. Bottom-up and top-down attention for image captioning and visual question answering
5. J. Li, D. Li, C. Xiong and S. Hoi, “Blip bootstrapping language-image pretraining for unified vision-language understanding and generation,” arXiv preprint arXiv:2201.12086, 2022.
6. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework
7. Deep residual learning for image recognition
8. Faster r-CNN: Towards real-time object detection with region proposal networks
9. In defense of grid features for visual question answering
10. Mask-refined R-CNN: A network for refining object details in instance segmentation
11. Object detection based on multi-layer convolution feature fusion and online hard example mining10.1109/ACCESS.2018.2815149 ↗
12. Making the v in vqa matter: Elevating the role of image understanding in visual question answering
13. Gqa: A new dataset for real-world visual reasoning and compositional question answering
14. Hierarchical relational attention for video question answering
15. Stacked self-attention networks for visual question answering
16. Imagenet: A large-scale hierarchical image database
17. Visual genome: Connecting language and vision using crowdsourced dense image annotations10.1007/s11263-016-0981-7 ↗
18. L. H. Li, M. Yatskar, D. Yin, C. -J. Hsieh and K. -W. Chang, “Visualbert: A simple and performant baseline for vision and language,” arXiv preprint arXiv:2201.12086, 2019.
19. Unified vision language pre-training for image captioning and VQA
20. GloVe: Global vectors for word representation
21. Aggregated residual transformations for deep neural networks
22. Multimodal deep fusion for image question answering10.1016/j.knosys.2020.106639 ↗
23. Sparse co-attention visual question answering networks based on thresholds10.1007/s10489-022-03559-4 ↗
24. CAAN: Context-aware attention network for visual question answering10.1016/j.patcog.2022.108980 ↗
25. Spca-net: A based on spatial position relationship co-attention network for visual question answering10.1007/s00371-022-02524-z ↗
26. Movie: Revisiting modulated convolutions for visual counting and beyond
27. Language-conditioned graph networks for relational reasoning
28. Interpretable visual reasoning via induced symbolic space
29. Multiple context learning networks for visual question answering
30. Uniter: Universal image-text representation learning
31. Oscar: Object-semantics aligned pre-training for vision-language tasks
32. Large-scale adversarial training for vision-and-language representation learning
33. Seeing out of the box: End-to-end pre-training for vision-language representation learning
34. Rosita: Enhancing vision-and-language semantic alignments via cross and intra-modal knowledge integration