The good practice in the VQA system such as pos-tag attention, structed triplet learning and triplet attention is very general and can be inserted into almost any visual and language task
☆19Jan 23, 2018Updated 8 years ago
Alternatives and similar repositories for STL-VQA
Users that are interested in STL-VQA are comparing it to the libraries listed below
Sorting:
- Project for Dynamic Capsule Attention☆12Dec 7, 2019Updated 6 years ago
- Re-implementation for 'R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering'.☆12Apr 11, 2019Updated 6 years ago
- ☆14May 10, 2021Updated 4 years ago
- Code Release for `Learning Answer Embeddings for Visual Question Answering`. (CVPR 2018)☆13Apr 6, 2019Updated 6 years ago
- VQA baseline with Conditional Batch Normalization☆15Apr 9, 2018Updated 7 years ago
- vqa drived by bottom-up and top-down attention and knowledge☆14Nov 21, 2018Updated 7 years ago
- Unofficial reimplementation of Dynamic Fusion with Intra- and Inter-modality Attention Flow for Visual Question Answering☆18Oct 30, 2019Updated 6 years ago
- Official code for the paper "Contrast and Classify: Training Robust VQA Models" published at ICCV, 2021☆19Jul 27, 2021Updated 4 years ago
- ☆27Oct 7, 2021Updated 4 years ago
- Code for the Grounded Visual Question Answering (GVQA) model from the paper -- Don't Just Assume; Look and Answer: Overcoming Priors for …☆27Mar 10, 2022Updated 3 years ago
- Real-world photo sequence question answering system (MemexQA). CVPR'18 and TPAMI'19☆33Jul 1, 2019Updated 6 years ago
- [ICLR 2019] ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees☆32Jan 16, 2020Updated 6 years ago
- Just little bits.☆10Aug 5, 2025Updated 7 months ago
- Co-attending Regions and Detections for VQA.