Competence-based multimodal curriculum learning for medical report generation
Medical report generation task, which targets to produce long and coherent descriptions of
medical images, has attracted growing research interests recently. Different from the general …
medical images, has attracted growing research interests recently. Different from the general …
Clova: A closed-loop visual assistant with tool usage and update
Utilizing large language models (LLMs) to compose off-the-shelf visual tools represents a
promising avenue of research for developing robust visual assistants capable of addressing …
promising avenue of research for developing robust visual assistants capable of addressing …
From easy to hard: Learning language-guided curriculum for visual question answering on remote sensing data
Visual question answering (VQA) for remote sensing scene has great potential in intelligent
human–computer interaction system. Although VQA in computer vision has been widely …
human–computer interaction system. Although VQA in computer vision has been widely …
[PDF][PDF] Building public trust in Islamic school through adaptive curriculum
This study aims to investigate an adaptive curriculum serving as a medium to build public
trust at Islamic Elementary School (SDI) Tompokersan Lumajang, East Java. It is qualitative …
trust at Islamic Elementary School (SDI) Tompokersan Lumajang, East Java. It is qualitative …
Re-attention for visual question answering
A simultaneous understanding of questions and images is crucial in Visual Question
Answering (VQA). While the existing models have achieved satisfactory performance by …
Answering (VQA). While the existing models have achieved satisfactory performance by …
Closed loop neural-symbolic learning via integrating neural perception, grammar parsing, and symbolic reasoning
The goal of neural-symbolic computation is to integrate the connectionist and symbolist
paradigms. Prior methods learn the neural-symbolic models using reinforcement learning …
paradigms. Prior methods learn the neural-symbolic models using reinforcement learning …
Learning by fixing: Solving math word problems with weak supervision
Previous neural solvers of math word problems (MWPs) are learned with full supervision
and fail to generate diverse solutions. In this paper, we address this issue by introducing a …
and fail to generate diverse solutions. In this paper, we address this issue by introducing a …
Comphy: Compositional physical reasoning of objects and events from videos
Objects' motions in nature are governed by complex interactions and their properties. While
some properties, such as shape and material, can be identified via the object's visual …
some properties, such as shape and material, can be identified via the object's visual …
CLCL: Non-compositional expression detection with contrastive learning and curriculum learning
Non-compositional expressions present a substantial challenge for natural language
processing (NLP) systems, necessitating more intricate processing compared to general …
processing (NLP) systems, necessitating more intricate processing compared to general …
Suppressing biased samples for robust VQA
Most existing visual question answering (VQA) models strongly rely on language bias to
answer questions, ie, they always tend to fit question-answer pairs on the train split and …
answer questions, ie, they always tend to fit question-answer pairs on the train split and …