research
∙
08/24/2023
SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data
We propose Subject-Conditional Relation Detection SCoRD, where condition...
share
research
∙
06/30/2022
Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations
We propose a margin-based loss for vision-language model pretraining tha...
research
∙
04/05/2022
OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
Dataset bias and spurious correlations can significantly impair generali...
research
∙
06/17/2021
Learning to Predict Visual Attributes in the Wild
Visual attributes constitute a large portion of information contained in...
research
∙
04/01/2021
An Investigation of Critical Issues in Bias Mitigation Techniques
A critical problem in deep learning is that systems learn inappropriate ...
research
∙
04/28/2020
Do We Need Fully Connected Output Layers in Convolutional Networks?
Traditionally, deep convolutional neural networks consist of a series of...
research
∙
04/12/2020
A negative case analysis of visual grounding methods for VQA
Existing Visual Question Answering (VQA) methods tend to exploit dataset...
research
∙
10/06/2019
REMIND Your Neural Network to Prevent Catastrophic Forgetting
In lifelong machine learning, a robotic agent must be incrementally upda...
research
∙
08/05/2019
Answering Questions about Data Visualizations using Efficient Bimodal Fusion
Chart question answering (CQA) is a newly proposed visual question answe...
research
∙
04/19/2019
Challenges and Prospects in Vision and Language Research
Language grounded image understanding tasks have often been proposed as ...
research
∙
03/01/2019
Answer Them All! Toward Universal Visual Question Answering Models
Visual Question Answering (VQA) research is split into two camps: the fi...
research
∙
10/29/2018
TallyQA: Answering Complex Counting Questions
Most counting questions in visual question answering (VQA) datasets are ...
research
∙
01/24/2018
DVQA: Understanding Data Visualizations via Question Answering
Bar charts are an effective way for humans to convey information to each...
research
∙
03/28/2017
An Analysis of Visual Question Answering Algorithms
In visual question answering (VQA), an algorithm must answer text-based ...
research
∙
10/05/2016