Wentong-DST / self-critical
PyTorch implementation of paper: "Self-critical Sequence Training for Image Captioning"
☆22Updated last year
Related projects ⓘ
Alternatives and complementary repositories for self-critical
- Unpaired Image Captioning☆35Updated 3 years ago
- Code for "Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations" (NeurIPS 2019)☆64Updated 4 years ago
- Code for CVPR'19 "Recursive Visual Attention in Visual Dialog"☆65Updated last year
- An image-oriented evaluation tool for image captioning systems (EMNLP-IJCNLP 2019)☆34Updated 4 years ago
- Compact Trilinear Interaction for Visual Question Answering (ICCV 2019)☆38Updated 2 years ago
- ☆62Updated 2 years ago
- Scene Graph Parsing as Dependency Parsing☆41Updated 5 years ago
- Code release for Context-Aware Visual Policy Network for Sequence-Level Image Captioning (MM 2018) and Context-Aware Visual Policy Networ…☆47Updated 5 years ago
- [EMNLP 2018] Training for Diversity in Image Paragraph Captioning☆90Updated 5 years ago
- Code for Discriminability objective for training descriptive captions(CVPR 2018)☆110Updated 5 years ago
- Implementation of Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space☆58Updated 6 years ago
- Contrastive Learning for Image Captioning☆51Updated 6 years ago
- python codes for CIDEr - Consensus-based Image Caption Evaluation☆32Updated 5 years ago
- Information Maximizing Visual Question Generation☆66Updated last year
- Code for "bootstrap, review, decode: using out-of-domain textual data to improve image captioning"☆20Updated 7 years ago
- PyTorch code for Reasoning Visual Dialogs with Structural and Partial Observations☆42Updated 3 years ago
- This project is out of date, I don't remember the details inside...☆85Updated 6 years ago
- Stack-Captioning: Coarse-to-Fine Learning for Image Captioning☆63Updated 6 years ago
- A PyTorch implementation of Dual Attention Network☆30Updated 2 years ago
- ☆22Updated 6 years ago
- Pre-trained V+L Data Preparation☆45Updated 4 years ago
- This is the implementation of self-CIDEr and LSA-based diversity metrics (only for python 2.7).☆36Updated 2 years ago
- Code for the CoNLL 2019 paper "Compositional Generalization in Image Captioning" by Mitja Nikolaus, Mostafa Abdou, Matthew Lamm, Rahul Ar…☆26Updated 4 years ago
- Torch Implementation of Speaker-Listener-Reinforcer for Referring Expression Generation and Comprehension☆33Updated 6 years ago
- Code for NeurIPS 2019 paper ``Self-Critical Reasoning for Robust Visual Question Answering''☆39Updated 5 years ago
- Counterfactual Samples Synthesizing for Robust VQA☆76Updated 2 years ago
- Code for paper "Adaptively Aligned Image Captioning via Adaptive Attention Time". NeurIPS 2019☆49Updated 4 years ago
- ✨ Official PyTorch Implementation for EMNLP'19 Paper, "Dual Attention Networks for Visual Reference Resolution in Visual Dialog"☆45Updated last year
- ☆10Updated 6 years ago
- Semantic Propositional Image Caption Evaluation☆137Updated last year