Spatio-temporal Matching for Human Detection in Video

By Feng Zhou, Fernando De la Torre. 2014

56 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

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 Human-Computer Interaction

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Zhou and De la Torre [197] Spatio-temporal Matching BoW Lowlv Hand X X X”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, unknown): “In the past, this usually involved inferring a 3D human pose either optimizing an energy function derived from image information, such as silhouettes [5, 13, 20, 21, 24, 29, 43, 53], feature trajectories [68] and 2D joint locations [3, 4, 19, 33, 45, 51, 62, 63], or 2D recognitionbased pose retrieva”
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (2017, unknown): “Much of this work has been realized by assuming manually labeled 2D joint locations; however, there is some recent work that has used a 2D pose detector to automatically provide the input joints [59], [60] or solved 2D and 3D pose estimation jointly [12], [61].”
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach (2015, methodology): “Zhou and De La Torre [17] formulated human pose estimation as a matching problem, where a learned spatio-temporal pose model was matched to point trajectories extracted from a video.”
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision (2016, background): “Some 3D pose estimation approaches take advantage of this generalizability of 2D pose estimation, and propose to lift the 2D keypoints to 3D [64, 71, 7, 68, 32, 75, 78, 74, 55, 54, 12].”
LCR-Net: Localization-Classification-Regression for Human Pose (2017, methodology): “Finally, other methods solve 2D and 3D pose estimation jointly or iteratively [25, 35, 36].”
Bayesian Image Based 3D Pose Estimation (2016, methodology): “Focusing on 2D input data, some works assume the 2D body joints locations already given [6], while others extract features from silhouettes such as HOG [7], PHOG [1], SIFT [8] and shape context [9], or dense trajectories [10].”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, background): “Zhou et al. [56] run a 2D pose detector [54] and then optimize 3D pose, automatically rejecting outliers.”
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2015, methodology): “Much of this work has been realized by assuming manually labeled 2D joint locations; however, there is some recent work that has used a 2D pose detector to automatically provide the input joints [40, 48] or solved 2D and 3D pose estimation jointly [39, 54].”
Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision (2016, background): “2D-3D lifting is related to non-rigid and articulated structure-from-motion from image sequences [48, 50] where sub-space motion or pose models, such as bilinear models [87], are assumed.”
Recovering Accurate 3D Human Pose in the Wild Using IMUs and a Moving Camera (2018, background): “Several works lift 2D detections to 3D using learning or geometric reasoning [18, 29, 35, 9, 26, 49, 33, 48, 44, 34, 13, 43, 45].”
Joint action recognition and pose estimation from video (2015, methodology): “Video pose estimation methods capture motion information by adding many pairwise terms among parts at subsequent frames to the graphical model[3, 36, 21], however, these models are loopy and require approximate inference.”
LCR-Net: Localization-Classiﬁcation-Regression for Human Pose (unknown): “Finally, other meth-ods solve 2D and 3D pose estimation jointly or iteratively [25, 35, 36].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, unknown): “In the past, this usually involved inferring a 3D human pose by optimizing an energy function derived from image information, such as silhouettes [6, 14, 21, 22, 25, 31, 44, 49, 60], trajectories [75], cm im”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, unknown): “Finally, some recent approaches treat 2D and 3D pose estimation jointly or iteratively [45], [46], [47], [48], [49].”
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild (2016, methodology): “Some approaches use as input the 2D joints automatically provided by a 2D pose detector [32, 38], while others jointly solve the 2D and 3D pose estimation [31, 43].”