Recognizing actions from still images

İkizler, Nazlı; Cinbiş, Ramazan Gökberk; Pehlivan, Selen; Duygulu, Pınar

doi:10.1109/icpr.2008.4761663

Cited by 96 publications

(63 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Histogram of Oriented Rectangles (CHORs) (Ikizler et al, 2008), Adaboost classifiers (Gupta et al, 2009). …”

Section: Low-level Evaluationmentioning

confidence: 99%

“…In this approach, the histogram-based methods prevail. It may be circular histograms of spatial and orientation binning (Ikizler et al, 2008) or the most popular Histogram of Oriented Gradients (HOG) (Dalal, and Triggs, 2005) with multiple modifications. The last research was the pioneer investigation in pose descriptor construction based on non-negative matrix factorization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human Action Poselets Estimation via Color G-Surf in Still Images

Favorskaya

Novikov

Savitskaya

2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Human activity is a persistent subject of interest in the last decade. On the one hand, video sequences provide a huge volume of motion information in order to recognize the human active actions. On the other hand, the spatial information about static human poses is valuable for human action recognition. Poselets were introduced as latent variables representing a configuration for mutual locations of body parts and allowing different views of description. In current research, some modifications of Speeded-Up Robust Features (SURF) invariant to affine geometrical transforms and illumination changes were tested. First, a grid of rectangles is imposed on object of interest in a still image. Second, sparse descriptor based on Gauge-SURF (G-SURF) invariant to color/lighting changes is constructed for each rectangle separately. A common Spatial POselet Descriptor (SPOD) aggregates the SPODs of rectangles with following random forest classification in order to receive fast classification results. The proposed approach was tested on samples from PASCAL Visual Object Classes (VOC) Dataset and Challenge 2010 providing accuracy 61-68% for all possible 3D poses locations and 82-86% for front poses locations regarding to nine action categories.

show abstract

“…Histogram of Oriented Rectangles (CHORs) (Ikizler et al, 2008), Adaboost classifiers (Gupta et al, 2009). …”

Section: Low-level Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Human Action Poselets Estimation via Color G-Surf in Still Images

Favorskaya

Novikov

Savitskaya

2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The goal of this work is to study recognition of common human actions represented in typical still images such as consumer photographs. This problem has received little attention in the past with the exception of few related papers focused on specific domains, such as sports actions [10,12,16,21] or, more recently, people playing musical instruments [22]. Learning from still images to recognize actions in video was investigated in [13].…”

Section: Introductionmentioning

confidence: 99%

“…The proposed methods [10,12,21] have mainly relied on the body pose as a cue for action recognition. While promising results have been demonstrated on sports actions [10,12,21], typical action images such as the ones illustrated in Figure 1 often contain heavy occlusions and significant changes in camera viewpoint and hence present a serious challenge for current body-pose estimation methods.…”

Section: Introductionmentioning

confidence: 99%

“…While promising results have been demonstrated on sports actions [10,12,21], typical action images such as the ones illustrated in Figure 1 often contain heavy occlusions and significant changes in camera viewpoint and hence present a serious challenge for current body-pose estimation methods. At the same time, the presence of particular objects [10] and scene types [16] often characterizes the action and can be used for action recognition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognizing human actions in still images: a study of bag-of-features and part-based representations

Delaitre¹,

Laptev²,

Šivic³

2010

Procedings of the British Machine Vision Conference 2010

225

202

View full text Add to dashboard Cite

Recognition of human actions is usually addressed in the scope of video interpretation. Meanwhile, common human actions such as "reading a book", "playing a guitar" or "writing notes" also provide a natural description for many still images. In addition, some actions in video such as "taking a photograph" are static by their nature and may require recognition methods based on static cues only. Motivated by the potential impact of recognizing actions in still images and the little attention this problem has received in computer vision so far, we address recognition of human actions in consumer photographs. We construct a new dataset available at [2] with seven classes of actions in 911 Flickr images representing natural variations of human actions in terms of camera view-point, human pose, clothing, occlusions and scene background. We study action recognition in still images using the state-of-the-art bag-of-features methods as well as their combination with the part-based Latent SVM approach of Felzenszwalb et al. [8]. In particular, we investigate the role of background scene context and demonstrate that improved action recognition performance can be achieved by (i) combining the statistical and part-based representations, and (ii) integrating person-centric description with the background scene context. We show results on our newly collected dataset of seven common actions as well as demonstrate improved performance over existing methods on the datasets of Gupta et al. [10] and .

show abstract

Kernel‐based low‐rank tensorized multiview spectral clustering

Liu

et al. 2020

Int J Intell Syst

View full text Add to dashboard Cite

Recognizing actions from still images

Abstract: Abstract

Cited by 96 publications

References 8 publications

Human Action Poselets Estimation via Color G-Surf in Still Images

Human Action Poselets Estimation via Color G-Surf in Still Images

Recognizing human actions in still images: a study of bag-of-features and part-based representations

Kernel‐based low‐rank tensorized multiview spectral clustering

Contact Info

Product

Resources

About