Research map / Vision-language and multimodal / Visual question answering
Learning to Answer Questions from Image Using Convolutional Neural Network
Lin Ma, Zhengdong Lu, Hang Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the end-to-end CNN with image, question, and multimodal convolution components instead of Neural-Image-QA | Image QA model · DAQUAR-All, single word | accuracy: 19.43 -> 24.49 | Improved |
| Use the end-to-end CNN instead of Neural-Image-QA | Image QA model · DAQUAR-Reduced, single word | accuracy: 34.68 -> 42.76 | Improved |
| Use the end-to-end CNN instead of VSE FULL | Image QA model · COCO-QA | accuracy: 57.84 -> 58.40 | Improved |
| Add multimodal convolution to fuse image and question representations rather than simply concatenate them (ablation) | Proposed CNN · COCO-QA | accuracy: 56.77 -> 58.40 | Improved |
| Add the image representation (ablation) | Proposed CNN · COCO-QA | accuracy: 37.84 -> 58.40 | Improved |
| Preserve natural word order instead of randomly reshuffling question words (ablation) | Proposed CNN · COCO-QA | accuracy: 40.74 versus 58.40 | Improved |
| Use bidirectional 2-VIS+BLSTM instead of VIS+LSTM | VSE · DAQUAR-Reduced, single word | accuracy: 34.41 -> 35.78 | Improved |
Closest papers by meaning
- Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction (CVPR 2016 · similarity 0.92)
- Image Captioning and Visual Question Answering Based on Attributes and External Knowledge (TPAMI 2017 · similarity 0.91)
- An Analysis of Visual Question Answering Algorithms (ICCV 2017 · similarity 0.90)
- Visual Question Answering with Question Representation Update (QRU) (NeurIPS 2016 · similarity 0.90)
- Ask Your Neurons: A Deep Learning Approach to Visual Question Answering (IJCV 2017 · similarity 0.90)
- Hierarchical Question-Image Co-Attention for Visual Question Answering (NeurIPS 2016 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
