OK-VQA

Overview edit

Variants: OK-VQA

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Visual Question Answering (VQA) - Metrics: Accuracy, Exact Match (EM), Recall@5
• Retrieval - Metrics: Recall@5

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning (2024) -
• Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects (2023) -
• Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models (2023) -
• A Simple Baseline for Knowledge-Based Visual Question Answering (2023) -
• Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering (2023) -
• PaLI-X: On Scaling up a Multilingual Vision and Language Model (2023) -
• PaLM-E: An Embodied Multimodal Language Model (2023) -
• Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering (2023) -
• Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis (2023) -
• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models (2023) -
• REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory (2022) -
• PromptCap: Prompt-Guided Task-Aware Image Captioning (2022) -
• VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge (2022) -
• Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training (2022) -
• Retrieval Augmented Visual Question Answering with Outside Knowledge (2022) -
• PaLI: A Jointly-Scaled Multilingual Language-Image Model (2022) -
• LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection (2022) -
• Language Models are General-Purpose Interfaces (2022) -
• REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering (2022) -
• Flamingo: a Visual Language Model for Few-Shot Learning (2022) -