paper-with-me

홈 › Papers

Poselet Key-Framing: A Model for Human Activity Recognition

2013-06-01 · CVPR 2013 6 · Michalis Raptis, Leonid Sigal

In this paper, we develop a new model for recognizing human actions. An action is modeled as a very sparse sequence of temporally local discriminative keyframes collections of partial key-poses of the actor(s), depicting key states in the action sequence. We cast the learning of keyframes in a max-margin discriminative framework, where we treat keyframes as latent variables. This allows us to (jointly) learn a set of most discriminative keyframes while also learning the local temporal context between them. Keyframes are encoded using a spatially-localizable poselet-like representation with HoG and BoW components learned from weak annotations; we rely on structured SVM formulation to align our components and mine for hard negatives to boost localization performance. This results in a model that supports spatio-temporal localization and is insensitive to dropped frames or partial observations. We show classification performance that is competitive with the state of the art on the benchmark UT-Interaction dataset and illustrate that our model outperforms prior methods in an on-line streaming setting.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionHuman Activity RecognitionTemporal Localization

Similar Papers 제목 키워드 기반

Moving poselets: A discriminative and interpretable skeletal motion representation for action recognition

2015-12-07 · 2015 IEEE International Conference on Computer Vision Workshop (ICCVW) 2015 12 · Lingling Tao, René Vidal

Given a video or time series of skeleton data, action recognition systems perform classification using cues such as motion, appearance, and pose. For the past decade, actions have been modeled using low-level feature rep…

Action RecognitionDictionary LearningMultimodal Activity RecognitionTime Series Analysis

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.…

Human 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

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