paper-with-me

홈 › Papers

Deep Poselets for Human Detection

2014-07-02 · Lubomir Bourdev, Fei Yang, Rob Fergus

We address the problem of detecting people in natural scenes using a part approach based on poselets. We propose a bootstrapping method that allows us to collect millions of weakly labeled examples for each poselet type. We use these examples to train a Convolutional Neural Net to discriminate different poselet types and separate them from the background class. We then use the trained CNN as a way to represent poselet patches with a Pose Discriminative Feature (PDF) vector -- a compact 256-dimensional feature vector that is effective at discriminating pose from appearance. We train the poselet model on top of PDF features and combine them with object-level CNNs for detection and bounding box prediction. The resulting model leads to state-of-the-art performance for human detection on the PASCAL datasets.

📄 PDF Abstract BibTeX arXiv:1407.0717

Code (0)

등록된 구현이 없습니다.

Tasks

Human Detection

Similar Papers 제목 키워드 기반

An MRF-Poselets Model for Detecting Highly Articulated Humans

2015-12-01 · ICCV 2015 12 · Duc Thanh Nguyen, Minh-Khoi Tran, Sai-Kit Yeung

Detecting highly articulated objects such as humans is a challenging problem. This paper proposes a novel part-based model built upon poselets, a notion of parts, and Markov Random Field (MRF) for modelling the human bod…

Human Detection

Using k-Poselets for Detecting People and Localizing Their Keypoints

2014-06-01 · CVPR 2014 6 · Georgia Gkioxari, Bharath Hariharan, Ross Girshick, Jitendra Malik

A k-poselet is a deformable part model (DPM) with k parts, where each of the parts is a poselet, aligned to a specific configuration of keypoints based on ground-truth annotations. A separate template is used to learn th…

Human DetectionPrediction

Actions and Attributes from Wholes and Parts

2014-12-08 · ICCV 2015 12 · Georgia Gkioxari, Ross Girshick, Jitendra Malik

We investigate the importance of parts for the tasks of action and attribute classification. We develop a part-based approach by leveraging convolutional network features inspired by recent advances in computer vision. O…

AttributeClassificationGeneral ClassificationHuman Detection

A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets

2016-06-15 · CVPR 2016 6 · Ivan Lillo, Juan Carlos Niebles, Alvaro Soto

In this paper, we introduce a new hierarchical model for human action recognition using body joint locations. Our model can categorize complex actions in videos, and perform spatio-temporal annotations of the atomic acti…

Action RecognitionAction UnderstandingPose EstimationTemporal Action Localization

Articulated Pose Estimation Using Discriminative Armlet Classifiers

2013-06-01 · CVPR 2013 6 · Georgia Gkioxari, Pablo Arbelaez, Lubomir Bourdev, Jitendra Malik

We propose a novel approach for human pose estimation in real-world cluttered scenes, and focus on the challenging problem of predicting the pose of both arms for each person in the image. For this purpose, we build on t…

Pose Estimation