RI:Small:Collaborative Research: Understanding Human-Object Interactions from First-person and Third-person Videos

RI:Small：协作研究：从第一人称和第三人称视频中理解人与物体的交互

• 批准号: 2104404
• 负责人: Michael Ryoo
• 金额: $ 22.84万
• 依托单位: SUNY at Stony Brook
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2022-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2104404&HistoricalAwards=false
• 关键词: RI; Small; Collaborative; Research; Understanding

Ubiquitous cameras, together with ever increasing computing resources, are dramatically changing the nature of visual data and their analysis. Cities are adopting networked camera systems for policing and intelligent resource allocation, and individuals are recording their lives using wearable devices. For these camera systems to become truly smart and useful for people, it is crucial that they understand interesting objects in the scene and detect ongoing activities/events, while jointly considering continuous 24/7 videos from multiple sources. Such object-level and activity-level awareness in hospitals, elderly homes, and public places would provide assistive and quality-of-life technology for disabled and elderly people, provide intelligent surveillance systems to prevent crimes, and allow smart usage of environmental resources. This project will investigate novel computer vision algorithms that combine 1st-person videos (from wearable cameras) and 3rd-person videos (from static environmental cameras) for joint recognition of humans, objects, and their interactions. The key idea is to combine the two views' complementary and unique advantages for joint visual scene understanding. To this end, it will create a new dataset, and develop new algorithms that learn to recognize objects jointly across the views, learn human-object and human-human relationships through the two views, and anonymize the videos to preserve users' privacies. The project will provide new algorithms that have the potential to benefit applications in smart environments, security, and quality-of-life assistive technologies. The project will also perform complementary educational and outreach activities that engage students in research and STEM.This project will develop novel algorithms that learn from joint 1st-person videos (from wearable cameras) and 3rd-person videos (from static environmental cameras) for joint recognition of humans, objects, and their interactions. The 1st-person view is ideal for object recognition, while the 3rd-person view is ideal for human activity recognition. Thus, this project will investigate unique solutions to challenging problems that would otherwise be difficult to overcome when analyzing each viewpoint in isolation. The main research directions will be: (1) creating a benchmark 1st-person and 3rd-person video dataset to investigate this new problem; and developing algorithms that (2) learn to establish object and human correspondences between the two views; (3) learn object-action relationships across the views; and (4) anonymize the visual data for privacy-preserving visual recognition.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

无处不在的相机以及不断增加的计算资源正在极大地改变视觉数据及其分析的性质。城市正在采用网络摄像头系统进行警务和智能资源分配，个人正在使用可穿戴设备记录他们的生活。为了使这些摄像头系统变得真正智能且对人们有用，至关重要的是它们能够理解场景中有趣的物体并检测正在进行的活动/事件，同时共同考虑来自多个来源的连续 24/7 视频。医院、养老院和公共场所的这种对象级和活动级意识将为残疾人和老年人提供辅助和生活质量技术，提供智能监控系统以预防犯罪，并允许智能利用环境资源。 该项目将研究新颖的计算机视觉算法，将第一人称视频（来自可穿戴相机）和第三人称视频（来自静态环境相机）相结合，以联合识别人类、物体及其交互。其关键思想是结合两种视图的互补和独特优势来进行联合视觉场景理解。为此，它将创建一个新的数据集，并开发新的算法，学习跨视图共同识别对象，通过两个视图学习人与对象和人与人的关系，并对视频进行匿名化以保护用户的隐私。该项目将提供新的算法，有可能使智能环境、安全和生活质量辅助技术中的应用受益。该项目还将开展补充教育和外展活动，让学生参与研究和 STEM。该项目将开发新颖的算法，从联合第一人称视频（来自可穿戴相机）和第三人称视频（来自静态环境相机）中学习，以实现联合识别人类、物体及其相互作用。第一人称视图非常适合物体识别，而第三人称视图非常适合人类活动识别。因此，该项目将研究独特的解决方案来解决具有挑战性的问题，否则在单独分析每个观点时很难克服这些问题。主要研究方向是：（1）创建基准第一人称和第三人称视频数据集来研究这个新问题；开发算法：(2) 学习在两种视图之间建立物体和人类的对应关系； (3) 学习跨视图的对象-动作关系； (4) 对视觉数据进行匿名处理，以保护隐私的视觉识别。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，认为值得支持。

项目成果

Neural Neural Textures Make Sim2Real Consistent

神经网络纹理使 Sim2Real 保持一致

• 发表时间: 2022-12
• 期刊: Conference on Robot Learning (CoRL
• 作者: Burgert, Ryan;Shang, Jinghuan;Li, Xiang;Ryoo, Michael S.
• 通讯作者: Ryoo, Michael S.

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space

通过恢复 3D 空间中的标记来学习与视点无关的视觉表示

• DOI: 10.48550/arxiv.2206.11895
• 发表时间: 2022-06-23
• 期刊: ArXiv
• 作者: Jinghuan Shang;Srijan Das;M. Ryoo
• 通讯作者: M. Ryoo

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

自监督学习真的能改善像素强化学习吗？

• DOI: 10.48550/arxiv.2206.05266
• 发表时间: 2022-06-10
• 期刊: ArXiv
• 作者: Xiang Li;Jinghuan Shang;Srijan Das;M. Ryoo
• 通讯作者: M. Ryoo

Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning

用于第三人称模仿学习的自监督解缠表征学习

• DOI: 10.1109/iros51168.2021.9636363
• 发表时间: 2021-08-02
• 期刊: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• 作者: Jinghuan Shang;M. Ryoo
• 通讯作者: M. Ryoo

Recognizing Actions in Videos From Unseen Viewpoints

从看不见的视角识别视频中的动作

• 发表时间: 2021-06
• 期刊: IEEE Conference on Computer Vision and Pattern Recognition
• 作者: Piergiovanni, AJ;Ryoo, Michael S
• 通讯作者: Ryoo, Michael S