Dynamic visual reasoning by learning differentiable physics models from video and language
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
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 …
Class-incremental instance segmentation via multi-teacher networks
Although deep neural networks have achieved amazing results on instance segmentation,
they are still ill-equipped when they are required to learn new tasks incrementally …
they are still ill-equipped when they are required to learn new tasks incrementally …
Semantic-aware modular capsule routing for visual question answering
Visual Question Answering (VQA) is fundamentally compositional in nature, and many
questions are simply answered by decomposing them into modular sub-problems. The …
questions are simply answered by decomposing them into modular sub-problems. The …
General greedy de-bias learning
Neural networks often make predictions relying on the spurious correlations from the
datasets rather than the intrinsic properties of the task of interest, facing with sharp …
datasets rather than the intrinsic properties of the task of interest, facing with sharp …
MSAM: Deep Semantic Interaction Network for Visual Question Answering
F Wang, B Wang, F Xu, J Li, P Liu - International Conference on …, 2023 - Springer
Abstract In Visual Question Answering (VQA) task, extracting semantic information from
multimodalities and effectively utilizing this information for interaction is crucial. Existing VQA …
multimodalities and effectively utilizing this information for interaction is crucial. Existing VQA …
[HTML][HTML] 以图像视频为中心的跨媒体分析与推理
黄庆明， 王树徽， 许倩倩， 李亮， 蒋树强 - 智能系统学报, 2021 - html.rhhz.net
如何跨越从跨媒体数据到跨媒体知识所面临的“异构鸿沟” 和“语义鸿沟”, 对体量巨大的跨媒体
数据进行有效管理与利用, 是发展新一代人工智能亟待突破的瓶颈问题. 针对以图像视频为代表 …
数据进行有效管理与利用, 是发展新一代人工智能亟待突破的瓶颈问题. 针对以图像视频为代表 …