ili3p / vqa-soft
Accompanying code for "A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models" CVPR 2017 VQA workshop paper.
☆15Updated 7 years ago
Related projects ⓘ
Alternatives and complementary repositories for vqa-soft
- Code release for Hu et al. Modeling Relationships in Referential Expressions with Compositional Modular Networks. in CVPR, 2017☆67Updated 6 years ago
- Torch implementation for Stacked Attention Networks☆24Updated 7 years ago
- ☆34Updated 5 years ago
- Project Uncovering Temporal Context for Video Question and Answering☆15Updated 8 years ago
- ☆32Updated 5 years ago
- Multimodal Compact Bilinear Pooling for Torch7☆68Updated 7 years ago
- image caption with semantic attention☆12Updated 7 years ago
- Repository for our ICLR 2018 paper: memoryGAN☆47Updated 6 years ago
- Hadamard Product for Low-rank Bilinear Pooling☆71Updated 7 years ago
- For visual commonsense model☆34Updated 5 years ago
- Structured Attentions for Visual Question Answering☆47Updated 6 years ago
- The implementation of Text-guided Attention Model for Image Captioning☆22Updated 7 years ago
- Localize objects in images using referring expressions☆37Updated 8 years ago
- ☆29Updated 7 years ago
- Code release for Hu et al. Natural Language Object Retrieval, in CVPR, 2016☆113Updated 8 years ago
- An unofficial PyTorch implementation of the HAN and AdaHAN models presented in the "Learning Visual Question Answering by Bootstrapping H…☆54Updated 6 years ago
- This package provides simple functions to verify and evaluate WebVision dataset.☆16Updated 6 years ago
- Referring expression comprehension on ReferIt(RefClef)☆10Updated 7 years ago
- Code to replicate "Generating Visual Explanations"☆47Updated 4 years ago
- Code for paper "Image Caption Generation with Text-Conditional Semantic Attention"☆61Updated 7 years ago
- Implements an MLP for VQA☆8Updated 8 years ago
- Multimodal Residual Learning for Visual QA (NIPS 2016)☆39Updated 7 years ago
- Torch implementation of orthoreg.☆15Updated 3 years ago
- Faster-RCNN based on Densecap(deprecated)☆85Updated 8 years ago
- Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Parsing"☆12Updated 4 years ago
- A simple but well-performing "single-hop" visual attention model for the GQA dataset☆20Updated 5 years ago
- A more memory efficient Torch implementation of "Densely Connected Convolutional Networks".☆30Updated 7 years ago
- VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation☆22Updated 7 years ago