Modeling 4D Human-Object Interactions for Event and Object Recognition

By Ping Wei, Yibiao Zhao, Nanning Zheng, Song-Chun Zhu. 2013

125 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis (2016, methodology): “Multiview 3D event [43] and Northwestern-UCLA [40] datasets used more than one Kincect cameras at the same time to collect multi-view representations of the same action, and scale up the number of samples.”
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding (2019, methodology): “The Northwestern-UCLA [20] and the Multiview 3D Event [19] datasets used more than one depth sensors at the same time to collect multi-view representations of the same action, and scale up the number of samples.”
RGB-D-based action recognition datasets: A survey (2016, methodology): “Cluttered background and occlusion: UTKinect, RGBD-HuDaAct, MSRDaily Activity, CAD-120, RGBD-SAR, 3D Online, DMLSmartActions, Multiview 3D Event, LIRIS, and Oﬃce Activity.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “Another approach to construct temporal displacement representations incorporates the object being interacted with in each pose [123].”
PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understanding (2017, methodology): “Multiview 3D event [49] and Northwestern-UCLA [44] datasets start to use multi-view method to capture the 3D videos.”
Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense (2019, background): “In robotics and computer vision, prior work has exploited human-object relations in event, object, and scene modeling, but most work focuses on human-object relation detection in images [5, 30, 25, 21], probabilistic modeling from multiple data sources [45, 33, 13], and snapshots generation or scene”
Learning Perceptual Causality from Video (2013, methodology): “Action recognition, while beyond the scope of this paper, works by detecting spatio-temporal relationships in the video (e.g., detecting computer use through relative positions of skeleton joints and proximity to the computer [Wei et al. 2013]).”
SceneGrok (2014, background): “…new; much prior work has targeted this domain [Gibson 1977; Gupta et al. 2011; Pandey and Alami 2012; Fouhey et al. 2012; Koppula et al. 2013; Koppula and Saxena 2013; ACM Transactions on Graphics, Vol. 33, No. 6, Article 212, Publication Date: November 2014 Jiang et al. 2013; Wei et al. 2013a].”
Simultaneous Feature and Body-Part Learning for real-time robot awareness of human behaviors (2017, background): “Wei et al. [13] implemented a hierarchical graph to represent spatio-temporal joint positions and displacements, where the differences in skeletal joint positions between two successive frames were deﬁned as features.”
Deep Bilinear Learning for RGB-D Action Recognition (2018, background): “Recent works show that combining RGB, depth, and skeleton together can improve the system performance [37, 12, 39, 28, 19].”
Real-Time RGB-D Activity Prediction by Soft Regression (2016, methodology): “Since existing RGB-D sequence features [10, 11, 38] are not for online feature extraction, they are less applicable for online activity prediction.”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, background): “Therefore, the RGB-D approach becomes an effective way to describe activities of interactions [30, 10, 15, 23, 4, 11].”