Papers with Visual Genome dataset

7 papers
Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps (C18-1)

Copied to clipboard

Challenge: Existing literature on visual question answering (VQA) focuses on English, but there are no datasets for other languages.
Approach: They propose a cross-lingual method to make use of English annotation to improve Japanese VQA . they use attention maps generated from English questions to improve the task .
Outcome: The proposed method performs better than using a monolingual corpus in Japanese than using monolingual ones.
Learning Functional Distributional Semantics with Visual Data (2022.acl-long)

Copied to clipboard

Challenge: Functional Distributional Semantics models the meaning of a word as a binary classifier rather than a numerical vector.
Approach: They propose a method to train a Functional Distributional Semantics model with grounded visual data.
Outcome: The proposed model outperforms previous work on learning semantics from Visual Genome on four external evaluation datasets.
RelCLIP: Adapting Language-Image Pretraining for Visual Relationship Detection via Relational Contrastive Learning (2022.emnlp-main)

Copied to clipboard

Challenge: Existing visual relationship detection models only use numeric ids of relation labels for training, but ignore semantic correlation between labels.
Approach: They propose a visual Relationship prediction framework that transfers natural language knowledge from Contrastive Language-Image Pre-training models to enhance the relationship prediction.
Outcome: The proposed framework improves visual relationship prediction by matching semantic correlations with relation triplets.
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 .
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.
HaVQA: A Dataset for Visual Question Answering and Multimodal Research in Hausa Language (2023.findings-acl)

Copied to clipboard

Challenge: Existing models for visual question answering are limited to the English language.
Approach: They present a multimodal dataset for visual question answering tasks in the Hausa language.
Outcome: The proposed dataset provides 12,044 gold standard English-Hausa parallel sentences that are semantically identical to the corresponding visual information.
Learning to Relate from Captions and Bounding Boxes (P19-1)

Copied to clipboard

Challenge: Existing methods for classifying images without supervision are limited.
Approach: They propose a top-down attention mechanism to align entities in captions to objects in the image and leverage the syntactic structure of captions for alignment.
Outcome: The proposed model achieves a recall@50 of 15% and recall@100 of 25% on the relationships present in the image and predicts relations that are not present in captions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations