Deep Poselets for Human Detection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Human DetectionSimilar Papers 제목 키워드 기반
An MRF-Poselets Model for Detecting Highly Articulated Humans
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 DetectionUsing k-Poselets for Detecting People and Localizing Their Keypoints
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 DetectionPredictionActions and Attributes from Wholes and Parts
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 DetectionA Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets
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 LocalizationArticulated Pose Estimation Using Discriminative Armlet Classifiers
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