HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion

By Leonid Sigal, Alexandru O. Balan, Michael J. Black. 2010

1,365 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks, 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 Evaluation & Benchmarks

In 3D Vision & Pose

Citations in the corpus

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation (2014, neutral): “More complex examples come from the HumanEva dataset competitions [33] that use video or higher-resolution shape models such as SCAPE [3] and extensions.”
Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “[96] Parametrization of the Skeleton Conc Lowlv Hand X”
End-to-End Recovery of Human Shape and Pose (2017, background): “Video datasets with ground truth motion capture like HumanEva [38] and Human3.”
Learning Human Pose Estimation Features with Convolutional Networks (2013, methodology): “Further examples come from the HumanEva dataset competitions [41], or approaches that use higher-resolution shape models such as SCAPE [4] and further extensions [20, 8].”
Total Capture: 3D Human Pose Estimation Fusing Video and Inertial Sensors (2017, background): “6M [16] 3,136,356 4 Y N HumanEva [27] 40,000 7 Y N TNT15 [22] 13,000 8 N Y Total Capture(Proposed) 1,892,176 8 Y Y Table 3: Characterising existing 3D human pose datasets and TotalCapture”
DLow: Diversifying Latent Flows for Diverse Human Motion Prediction (2020, neutral): “6M [33] and HumanEva-I [63].”
Neural Body Fitting: Unifying Deep Learning and Model Based Human Pose and Shape Estimation (2018, methodology): “We used the following three datasets for evaluation: UP3D, [24], HumanEva-I [49] and Human3.”
Learning Camera Viewpoint Using CNN to Improve 3D Body Pose Estimation (2016, methodology): “Dataset: Earlier datasets on human 3D pose estimation such as Human Eva [22] is still commonly used for evaluations in the literature.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, background): “…points with time of ﬂight (TOF) depth sensors (Shahroudy et al., 2016), 3D human body reﬂective markers capture with motion capture systems (MoCap) (Sigal et al., 2010; Ionescu et al., 2014), orientation and acceleration of 3D human body data with Inertial Measurement Unit (IMU) (von Marcard et…”
2D Human Pose Estimation: New Benchmark and State of the Art Analysis (2014, background): “6M” [10] that includes images and 3D poses of people but are captured in the controlled indoor environments, whereas our dataset includes real-world images but provides 2D poses only.”
Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras (2015, methodology): “While most commercial systems require markers on the human body, marker-less approaches developed in research work directly on unmodified video streams [27, 32, 35].”
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments (2014, methodology): “This process is ongoing and was made possible by the availability of 3D human motion capture[8], [4], as well as human body scan datasets like the commercially available CAESAR, or smaller academic repositories like SCAPE[27] and INRIA4D[28].”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “6M dataset [143] wear shorts and tshirts, whereas in the HumanEva dataset [36] only one out of four subjects is female and only one wears clothes which are not tight.”
Ordinal Depth Supervision for 3D Human Pose Estimation (2018, background): “In contrast, the complexity of collecting images with corresponding 3D ground truth has constrained 3D human pose datasets in small scale [19] or strictly in studio settings [42, 16].”
Functional categorization of objects using real-time markerless motion capture (2011, methodology): “Although the approach performs very well on the HumanEva benchmark [28], it is not suitable for realtime applications.”
Challenges in multimodal gesture recognition (2016, background): “Viewing field: Upper body (Sapp and Taskar, 2013) / full body (Sigal et al., 2010) / egocentric (Fathi et al.”