Visual data such as images and videos contain a rich source of structured semantic labels as well as a wide range of interacting components. Visual content could be assigned with fine-grained labels describing major components, coarse-grained labels depicting high level abstractions, or a set of labels revealing attributes. Such categorization over different, interacting layers of labels evinces the potential for a graph-based encoding of label information. In this paper, we exploit this rich structure for performing graph-based inference in label space for a number of tasks: multi-label image and video classification and action detection in untrimmed videos. We consider the use of the Bidirectional Inference Neural Network (BINN) and Structured Inference Neural Network (SINN) for performing graph-based inference in label space and propose a Long Short-Term Memory (LSTM) based extension for exploiting activity progression on untrimmed videos. The methods were evaluated on (i) the Animal with Attributes (AwA), Scene Understanding (SUN) and NUS-WIDE datasets for multi-label image classification, (ii) the first two releases of the YouTube-8M large scale dataset for multi-label video classification, and (iii) the THUMOS'14 and MultiTHUMOS video datasets for action detection. Our results demonstrate the effectiveness of structured label inference in these challenging tasks, achieving significant improvements against baselines.
Structured Set Matching Networks for One-Shot Part Labeling
Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Semantic Machines(语义机器公司);University of Washington(华盛顿大学)
图表通常描述复杂的现象,并作为视觉和文本推理的良好测试平台。然而,使用自然图像理解方法来理解图需要大量的图训练数据集,这是非常难以获得的。相反,这可以作为标记图、图像或两者之间的匹配问题来解决。这个问题是非常具有挑战性的,因为缺乏显着的颜色和纹理呈现局部线索模糊,需要全局推理。我们考虑一次性部分标记的问题:在目标图像中标记对象的多个部分,仅给出该类别的单个源图像。对于这个集合到集合的匹配问题,我们引入了结构化集合匹配网络(SSMN),这是一种结合了卷积神经网络的结构化预测模型。使用全局归一化来训练SSMN,以最大化对应元素之间的局部匹配分数和所有匹配元素之间的全局一致性分数,同时还强制执行两个集合之间的匹配约束。SSMN在三个标签传输场景中的表现明显优于几个强大的基线:在200多个类别的新图表数据集上评估的图表到图表;在Pascal Part Dataset之上构建的数据集上评估的图像到图像;以及在这些数据集之间传输标签时评估的图像到图表。
Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling
Hefei University of Technology(合肥工业大学);Shanghai AI Laboratory(上海人工智能实验室);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);Anhui Zhonghuitong Technology Co., Ltd.(安徽中汇通科技有限公司)
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels
Xidian University(西安电子科技大学);Hangzhou Zhuoxi Institute of Brain and Intelligence(杭州卓兮脑与智能研究院);Tsinghua University(清华大学);BNRist(北京国家信息科学与技术研究中心);the University of Sheffield(谢菲尔德大学)
The University of Western Australia(西澳大利亚大学);Murdoch University(莫道克大学);Sun Yat-sen University(中山大学);The Hong Kong University of Science and Technology(香港科技大学)
Deep Attentional Structured Representation Learning for Visual Recognition
EPFL(洛桑联邦理工学院)
结构化表示,如Bags of Words,VLAD和Fisher Vectors,已被证明在处理复杂的视觉识别任务方面非常有效。因此,它们最近已被纳入深度架构中。然而,虽然有效,但由此产生的深度结构化表示学习策略通常会从整个图像中聚合局部特征,忽略了这样一个事实,即在复杂的识别任务中,某些区域提供比其他区域更多的区分信息。在本文中,我们引入了一个注意结构化的表示学习框架,它在聚合过程中引入了图像特定的注意力机制。我们的框架学习以端到端的方式联合预测图像类标签和注意力地图,并且除了目标标签之外没有任何其他监督。正如我们的实验所证明的那样,这始终优于注意力较少的结构化表示学习,并在标准场景识别和细粒度分类基准上产生最先进的结果。
AeroRAG: Structured Multimodal Retrieval-Augmented LLM for Fine-Grained Aerial Visual Reasoning
Research Center for Space Computing System, Zhejiang Lab, Hangzhou(杭州浙大实验室空间计算系统研究中心);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou(中国科学院大学杭州高等研究院);School of Cyber Science and Engineering, Zhengzhou University(郑州大学计算机科学与工程学院);School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院)
Reinforced Label Denoising for Weakly-Supervised Audio-Visual Video Parsing
Shandong University(山东大学);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Shandong Computer Science Center (National Supercomputer Center in Jinan)(山东省计算中心(国家超级计算济南中心))
Learning deep structured network for weakly supervised change detection
Data61-CSIRO(澳大利亚联邦科学与工业研究组织数据61);Australian National University(澳大利亚国立大学);ShanghaiTech University(上海科技大学);The University of Western Australia(西澳大学);Murdoch University(莫道克大学)
Modular Diffusion Models for Structured Visual Recognition
Department of Computer Science, University of British Columbia(不列颠哥伦比亚大学计算机科学系);Vector Institute for AI(向量人工智能研究所);CompVis, Ludwig Maximilian University of Munich(慕尼黑路德维希·马克西米利安大学计算机视觉实验室);Munich Center for Machine Learning(慕尼黑机器学习中心);CIFAR AI Chair(CIFAR人工智能教席)
Temporal Evidence Routing with Structured Visual Evidence for TimeLogicQA
Southeast University(东南大学);National University of Singapore(新加坡国立大学);Independent Researcher(独立研究员);Opus AI Research(Opus AI研究院);University of Science and Technology of China(中国科学技术大学)
Dynamic Visual-semantic Alignment for Zero-shot Learning with Ambiguous Labels
College of Computer Science and Technology(计算机科学与技术学院);School of Computer Science(计算机科学学院);Key Laboratory of Computing Power Network and Information Security, Ministry of Education(教育部计算能力网络与信息安全重点实验室);Shandong Computer Science Center(山东计算机科学中心);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东科学院))
VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling
School of Computer Science, Wuhan University, Wuhan, Hubei, China(中国湖北省武汉市武汉大学计算机学院);School of Information Engineering, Hubei University for Nationalities, Enshi, Hubei, China(中国湖北省恩施市湖北民族学院信息工程学院)
ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
South China University of Technology(华南理工大学);Guangdong Engineering Center for Large Model and GenAI Technology(广东省大模型与生成式人工智能技术工程中心);State Key Laboratory of Subtropical Building and Urban Science(亚热带建筑科学国家重点实验室);Ministry of Education Key Laboratory of Big Data and Intelligent Robot(教育部大数据与智能机器人重点实验室);Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information(广东省计算智能与网络信息重点实验室);Singapore Management University(新加坡国立大学)
University of Amsterdam(阿姆斯特丹大学);Priberam Labs(Priberam实验室);Institute of Systems and Robotics(系统与机器人研究所);LUMLIS (Lisbon ELLIS Unit)(LUMLIS(里斯本ELLIS单元));Unbabel(Unbabel公司)