Automatic chart understanding: a review
Automated chart analysis has vast potential to improve the accessibility of charts for a wider
audience, eg, people with visual impairments or other disabilities, by generating captions for …
audience, eg, people with visual impairments or other disabilities, by generating captions for …
Hair: Hierarchical visual-semantic relational reasoning for video question answering
Relational reasoning is at the heart of video question answering. However, existing
approaches suffer from several common limitations:(1) they only focus on either object-level …
approaches suffer from several common limitations:(1) they only focus on either object-level …
Test-time model adaptation for visual question answering with debiased self-supervisions
Visual question answering (VQA) is a prevalent task in real-world, and plays an essential
role in helping the blind understand the physical world. However, due to the real-world …
role in helping the blind understand the physical world. However, due to the real-world …
Vlab: Enhancing video language pre-training by feature adapting and blending
Large-scale image-text contrastive pre-training models, such as CLIP, have been
demonstrated to effectively learn high-quality multimodal representations. However, there is …
demonstrated to effectively learn high-quality multimodal representations. However, there is …
Encoder–decoder cycle for visual question answering based on perception-action cycle
In this study, we propose a novel encoder–decoder cycle (EDC) framework inspired by the
human learning process called the perception-action cycle to tackle challenging problems …
human learning process called the perception-action cycle to tackle challenging problems …
Causal inference with knowledge distilling and curriculum learning for unbiased VQA
Y Pan, Z Li, L Zhang, J Tang - ACM Transactions on Multimedia …, 2022 - dl.acm.org
Recently, many Visual Question Answering (VQA) models rely on the correlations between
questions and answers yet neglect those between the visual information and the textual …
questions and answers yet neglect those between the visual information and the textual …
Hgan: Hierarchical graph alignment network for image-text retrieval
Image-text retrieval (ITR) is a challenging task in the field of multimodal information
processing due to the semantic gap between different modalities. In recent years …
processing due to the semantic gap between different modalities. In recent years …
Resolving zero-shot and fact-based visual question answering via enhanced fact retrieval
Practical applications with visual question answering (VQA) systems are challenging, and
recent research has aimed at investigating this important field. Many issues related to real …
recent research has aimed at investigating this important field. Many issues related to real …
Explicit cross-modal representation learning for visual commonsense reasoning
Given a question about an image, Visual Commonsense Reasoning (VCR) needs to provide
not only a correct answer, but also a rationale to justify the answer. VCR is a challenging …
not only a correct answer, but also a rationale to justify the answer. VCR is a challenging …
Positional attention guided transformer-like architecture for visual question answering
A Mao, Z Yang, K Lin, J Xuan… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Transformer architectures have recently been introduced into the field of visual question
answering (VQA), due to their powerful capabilities of information extraction and fusion …
answering (VQA), due to their powerful capabilities of information extraction and fusion …