gicheonkang / gst-visdial
Official PyTorch Implementation for CVPR'23 Paper, "The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training"
β18Updated 10 months ago
Related projects β
Alternatives and complementary repositories for gst-visdial
- π PyTorch Implementation for EMNLP'21 Findings "Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer"β13Updated last year
- β18Updated 5 months ago
- Official repository for the A-OKVQA datasetβ63Updated 6 months ago
- Pytorch code for Language Models with Image Descriptors are Strong Few-Shot Video-Language Learnersβ112Updated 2 years ago
- Coarse-to-Fine Reasoning for Visual Question Answering (CVPRW'22)β43Updated 2 years ago
- β63Updated 5 years ago
- Source code for EMNLP 2022 paper βPEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Modelsββ47Updated 2 years ago
- Repo for paper: "Paxion: Patching Action Knowledge in Video-Language Foundation Models" Neurips 23 Spotlightβ35Updated last year
- Code for the ICCV'21 paper "Context-aware Scene Graph Generation with Seq2Seq Transformers"β44Updated 2 years ago
- β13Updated 2 years ago
- Official Repository for CVPR 2022 paper "REX: Reasoning-aware and Grounded Explanation"β18Updated 11 months ago
- ICCV 2023 (Oral) Open-domain Visual Entity Recognition Towards Recognizing Millions of Wikipedia Entitiesβ32Updated 2 months ago
- A collections of papers about VQA-CP datasets and their resultsβ37Updated 2 years ago
- The SVO-Probes Dataset for Verb Understandingβ31Updated 2 years ago
- Video Graph Transformer for Video Question Answering (ECCV'22)β44Updated last year
- β79Updated 2 years ago
- Official repo for CVPR 2022 (Oral) paper: Revisiting the "Video" in Video-Language Understanding. Contains code for the Atemporal Probe (β¦β48Updated 5 months ago
- VQACL: A Novel Visual Question Answering Continual Learning Setting (CVPR'23)β31Updated 7 months ago
- NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)β129Updated 3 months ago
- β40Updated last year
- [CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. Theβ¦β51Updated 3 months ago
- β79Updated 2 years ago
- This repo contains code for Invariant Grounding for Video Question Answeringβ26Updated last year
- β15Updated 2 years ago
- Code for 'Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality', EMNLP 2022β30Updated last year
- Code, data, models for the Sherlock corpusβ55Updated last year
- [EMNLP 2020] What is More Likely to Happen Next? Video-and-Language Future Event Predictionβ48Updated 2 years ago
- β11Updated 10 months ago
- Implementation for the paper "Reliable Visual Question Answering Abstain Rather Than Answer Incorrectly" (ECCV 2022: https//arxiv.org/absβ¦β32Updated last year
- Counterfactual Samples Synthesizing for Robust VQAβ76Updated last year