Learning hierarchical poselets for human parsing

Wang, Yan; Tran, Duan; Liao, Zuwei

doi:10.1109/cvpr.2011.5995519

Cited by 133 publications

(166 citation statements)

References 25 publications

(53 reference statements)

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…Notice also that using dense features leads to better results than using of STIP features. This should be related to the fact that the features of [25] include motion boundaries and velocities in addition to HOG and HOF. Finally, notice that the results from [1] are 2-12% better, but they assume known segmentation.…”

Section: Methodsmentioning

confidence: 99%

“…The first one is a concatenation of histograms of oriented gradients (HOG) and histograms of optical flows (HOF) extracted from a cuboid centered around each STIP point [24]. Since STIP points tend to be sparse in space, we also use the dense features presented in [25], which consist of HOG, HOF, and histograms of motion boundaries and velocities (in term of x and y coordinates) computed around dense trajectories. CRF pairwise.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Surgical Gesture Segmentation and Recognition

Tao

Zappella

Hager

et al. 2013

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013

101

View full text Add to dashboard Cite

Abstract. Automatic surgical gesture segmentation and recognition can provide useful feedback for surgical training in robotic surgery. Most prior work in this field relies on the robot's kinematic data. Although recent work [1,2] shows that the robot's video data can be equally effective for surgical gesture recognition, the segmentation of the video into gestures is assumed to be known. In this paper, we propose a framework for joint segmentation and recognition of surgical gestures from kinematic and video data. Unlike prior work that relies on either frame-level kinematic cues, or segment-level kinematic or video cues, our approach exploits both cues by using a combined Markov/semi-Markov conditional random field (MsM-CRF) model. Our experiments show that the proposed model improves over a Markov or semi-Markov CRF when using video data alone, gives results that are comparable to state-of-the-art methods on kinematic data alone, and improves over state-of-the-art methods when combining kinematic and video data.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Surgical Gesture Segmentation and Recognition

Tao

Zappella

Hager

et al. 2013

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2013

101

View full text Add to dashboard Cite

show abstract

“…Performing exact inference on these models is typically intractable and approximate methods at learning and test time need to be used. Recent methods have also explored using part hierarchies [16,17] and condition the detection of smaller parts that model regions around anatomical joints on the localization of larger composite parts or poselets [11,10,18,19] that model limbs in canonical configurations and tend to be easier to detect.…”

Section: Related Workmentioning

confidence: 99%

Pose Machines: Articulated Pose Estimation via Inference Machines

Ramakrishna

Munoz

Hebert

et al. 2014

Computer Vision – ECCV 2014

194

131

View full text Add to dashboard Cite

Abstract. State-of-the-art approaches for articulated human pose estimation are rooted in parts-based graphical models. These models are often restricted to tree-structured representations and simple parametric potentials in order to enable tractable inference. However, these simple dependencies fail to capture all the interactions between body parts. While models with more complex interactions can be defined, learning the parameters of these models remains challenging with intractable or approximate inference. In this paper, instead of performing inference on a learned graphical model, we build upon the inference machine framework and present a method for articulated human pose estimation. Our approach incorporates rich spatial interactions among multiple parts and information across parts of different scales. Additionally, the modular framework of our approach enables both ease of implementation without specialized optimization solvers, and efficient inference. We analyze our approach on two challenging datasets with large pose variation and outperform the state-of-the-art on these benchmarks.

show abstract

“…In the image domain, Random Forests have been introduced for human body pose classification [11]. Finally, the combination of holistic and part-based methods has been explored by introducing the concept of Poselets [27] in the pictorial structures framework [2,28]. These approaches have proposed an intermediate representation but they still do not capture the whole anatomy of the human body.…”

Section: Related Workmentioning

confidence: 99%

Holistic Human Pose Estimation with Regression Forests

Belagiannis

Amann

Navab

et al. 2014

Articulated Motion and Deformable Objects

View full text Add to dashboard Cite

Abstract. In this work, we address the problem of human pose estimation in still images by proposing a holistic model for learning the appearance of the human body from image patches. These patches, which are randomly chosen, are used for extracting features and training a regression forest. During training, a mapping between image features and human poses, defined by joint offsets, is learned; while during prediction, the body joints are estimated with an efficient mode-seeking algorithm. In comparison to other holistic approaches, we can recover body poses from occlusion or noisy data. We demonstrate the power of our method in two publicly available datasets and propose a third one. Finally, we achieve state-of-the-art results in comparison to other approaches.

show abstract

Learning hierarchical poselets for human parsing

Abstract: We consider the problem of human parsing with partbased models. Most previous work in part-based models only considers rigid parts (e.g. torso, head, half

Cited by 133 publications

References 25 publications

Surgical Gesture Segmentation and Recognition

Surgical Gesture Segmentation and Recognition

Pose Machines: Articulated Pose Estimation via Inference Machines

Holistic Human Pose Estimation with Regression Forests

Contact Info

Product

Resources

About