Corpus ID: 11463294

Deep Poselets for Human Detection

@article{Bourdev2014DeepPF,
  title={Deep Poselets for Human Detection},
  author={Lubomir D. Bourdev and Fei Yang and R. Fergus},
  journal={ArXiv},
  year={2014},
  volume={abs/1407.0717}
}
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… Expand
Hierarchical Cascade of Classifiers for Efficient Poselet Evaluation
TLDR
This work presents an algorithm for training a hierarchical cascade of part-based detectors and applies it to speed up poselet evaluation, generating a family of cascade hierarchies, including trees that grow logarithmically on the number of poselet classifiers. Expand
Action detection in office scene based on deep convolutional neural networks
TLDR
This work attempted towards the solution starting from a persons pose with poselets as the basic building blocks, which implements multi-task learning with classification and localization of person and the corresponding actions simultaneously. Expand
Human pose search using deep networks
TLDR
Two novel ways for representing the image of a person striking a pose, one looking for parts and other looking at the whole image are proposed, and these representations are then used for retrieval. Expand
AttentionNet: Aggregating Weak Directions for Accurate Object Detection
TLDR
AttentionNet is presented, a novel detection method using a deep convolutional neural network, named AttentionNet, which detects objects without any separated models from the object proposal to the post bounding-box regression. Expand
Actions and Attributes from Wholes and Parts
TLDR
A part-based approach by leveraging convolutional network features inspired by recent advances in computer vision, which shows that adding parts leads to top-performing results for both tasks and observes that for deeper networks parts are less significant. Expand
Solving Occlusion Problem in Pedestrian Detection by Constructing Discriminative Part Layers
TLDR
A brand new approach based on the fusion of Mid-level body part mining and Convolutional Neural Network (CNN) to solve occlusion handling, named DP-CNN(Discriminative Parts CNN). Expand
DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns
TLDR
A novel convolutional neural network that mines mid-level image patches that are sufficiently dedicated to resolve the corresponding subtleties and train a newly designed CNN (DeepPattern) that learns discriminative patch groups. Expand
ADORE: An Adaptive Holons Representation Framework for Human Pose Estimation
TLDR
A framework called adaptive holons representation (ADORE) that takes advantage of local and global cues is proposed to improve the pose estimation accuracy and is more efficient than other deep models and has desirable performance. Expand
Convolutional Neural Networks for Detecting and Mapping Crowds in First Person Vision Applications
TLDR
Results demonstrate that this approach achieves a high accuracy on the recognition of crowds, as well as the possibility of a general interpretation of the context trough the classification of characteristics of the segmented background. Expand
An MRF-Poselets Model for Detecting Highly Articulated Humans
TLDR
A novel part-based model built upon poselets, a notion of parts, and Markov Random Field for modelling the human body structure under the variation of human poses and viewpoints is proposed. Expand
...
1
2
3
...

References

SHOWING 1-10 OF 25 REFERENCES
PANDA: Pose Aligned Networks for Deep Attribute Modeling
TLDR
A new method which combines part-based models and deep learning by training pose-normalized CNNs for inferring human attributes from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion is proposed. Expand
Poselets: Body part detectors trained using 3D human pose annotations
TLDR
A new dataset, H3D, is built of annotations of humans in 2D photographs with 3D joint information, inferred using anthropometric constraints, to address the classic problems of detection, segmentation and pose estimation of people in images with a novel definition of a part, a poselet. Expand
Detecting People Using Mutually Consistent Poselet Activations
TLDR
A new algorithm for detecting people using poselets is developed which uses only 2D annotations which are much easier for naive human annotators and is the current best performer on the task of people detection and segmentation. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Learning Hierarchical Features for Scene Labeling
TLDR
A method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel, alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information. Expand
Regionlets for Generic Object Detection
TLDR
This work proposes to model an object class by a cascaded boosting classifier which integrates various types of features from competing local regions, named as region lets, which significantly outperforms the state-of-the-art on popular multi-class detection benchmark datasets with a single method. Expand
Deep Neural Networks for Object Detection
TLDR
This paper presents a simple and yet powerful formulation of object detection as a regression problem to object bounding box masks, and defines a multi-scale inference procedure which is able to produce high-resolution object detections at a low cost by a few network applications. Expand
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
TLDR
This work designs a method to reuse layers trained on the ImageNet dataset to compute mid-level image representation for images in the PASCAL VOC dataset, and shows that despite differences in image statistics and tasks in the two datasets, the transferred representation leads to significantly improved results for object and action classification. Expand
Object Detection with Discriminatively Trained Part Based Models
We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results inExpand
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
TLDR
This integrated framework for using Convolutional Networks for classification, localization and detection is the winner of the localization task of the ImageNet Large Scale Visual Recognition Challenge 2013 and obtained very competitive results for the detection and classifications tasks. Expand
...
1
2
3
...