| Challenge: | Visual question answering and image captioning require a shared body of general knowledge connecting language and vision. |
| Approach: | They propose a method that exploits a shared body of general knowledge connecting language and vision by jointly generating captions. |
| Outcome: | The proposed approach obtains state-of-the-art performance on the VQA v2 challenge . it uses human annotated captions to generate question-relevant captions . |
Similar Papers
All You May Need for VQA are Image Captions (2022.naacl-main)
Copied to clipboard
| Challenge: | Visual Question Answering (VQA) has benefited from increasingly sophisticated models, but has not enjoyed the same level of engagement in terms of data creation. |
| Approach: | They propose a method that automatically derives VQA examples at volume by leveraging existing image-caption annotations combined with neural models for textual question generation. |
| Outcome: | The proposed method improves state-of-the-art zero-shot accuracy by double digits and achieves robustness that lacks in the same model trained on human-annotated VQA data. |
Improving Visual Question Answering by Referring to Generated Paragraph Captions (P19-1)
Copied to clipboard
| Challenge: | Empirical results show that paragraph captions help answer more visual questions . |
| Approach: | They propose a visual and textual question answering model which uses paragraph captions as input . they use cross-attention to extract related information, then consensus to fuse the inputs . |
| Outcome: | Empirical results show that paragraph captions help answer more visual questions . the proposed model significantly improves the baseline model . |
Can We Learn Question, Answer, and Distractors All from an Image? A New Task for Multiple-choice Visual Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies focus on generating QADs from image and question, but a novel task is needed to generate meaningful questions, correct answers, and challenging distractors. |
| Approach: | They propose a task to generate QADs from images and encode images together . they use contrastive learning to ensure consistency of QAD generated and tested . |
| Outcome: | Empirical evaluations on the benchmark dataset validate the performance of the proposed task. |
Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to visual question answering represent images using pre-trained CNNs . but they rarely provide any insight, apart from the answer, into the VQA process . |
| Approach: | They propose to break up the end-to-end VQA into two steps: explaining and reasoning . they first extract attributes and generate descriptions as explanations for an image . a reasoning module utilizes these explanations in place of the image to infer an answer . |
| Outcome: | The proposed system achieves comparable performance with baselines, but with added benefits of explanability and the ability to improve with higher quality explanations. |
WeaQA: Weak Supervision via Captions for Visual Question Answering (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for training visual question answering models rely on datasets with human-annotated image-quest-answer triplets. |
| Approach: | They propose a method to train models with synthetic Q-A pairs generated procedurally from captions. |
| Outcome: | The proposed method trains models with synthetic Q-A pairs generated from captions on three VQA benchmarks. |
Modular Visual Question Answering via Code Generation (2023.acl-short)
Copied to clipboard
Sanjay Subramanian, Medhini Narasimhan, Kushal Khangaonkar, Kevin Yang, Arsha Nagrani, Cordelia Schmid, Andy Zeng, Trevor Darrell, Dan Klein
| Challenge: | a framework for visual question answering is based on modular code generation . the scope of reasoning needed for visual questions is vast, and requires many skills . |
| Approach: | They propose a framework that formulates visual question answering as modular code generation. |
| Outcome: | The proposed framework improves accuracy on COVR and GQA datasets by 3% and 2% compared to the few-shot baseline that does not employ code generation. |
Augmenting Image Question Answering Dataset by Exploiting Image Captions (L18-1)
Copied to clipboard
| Challenge: | Image question answering requires large amounts of human-annotated data to achieve optimal performance. |
| Approach: | They propose a framework to augment training data by generating additional examples from unannotated pairs of an image and captions. |
| Outcome: | The proposed framework augments training data by generating additional examples from unannotated pairs of an image and captions. |
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to visual question answering (VQA) are not suitable for real-world applications. |
| Approach: | They propose a supervised multi-modal domain adaptation method for visual question answering in images that exploits supervised domain adaptation. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the benchmark VQA 2.0 and VizWiz datasets. |
QACE: Asking Questions to Evaluate an Image Caption (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing metric for image captioning evaluation is based on n-gram similarity metrics but these fail to capture semantic errors in captions. |
| Approach: | They propose a new metric based on Question Answering for Caption Evaluation to evaluate image captioning based upon Question Generation and Question Answers systems. |
| Outcome: | The proposed metric is multi-modal, reference-less and explainable. |
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tasks to generate question-answer pairs from visual images are under-explored. |
| Approach: | They propose a task that targets question-answer pair generation from visual images. |
| Outcome: | The proposed model can generate diverse or consistent QAPs on two benchmarks. |