Classifying web videos using a global video descriptor

Solmaz, Berkan; Assari, Shayan Modiri; Shah, Mubarak

doi:10.1007/s00138-012-0449-x

Cited by 90 publications

(47 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparisons to available related works are described in Table II. www.ijacsa.thesai.org [14] group-wise cross validation 57.90% Todorovic [23] 2/3 training and 1/3 testing for each class 81.03% Solmaz et al [24] Leave One Group Out Cross validation(25 cross-validations) 73.70%…”

Section: Simulation Resultsmentioning

confidence: 99%

Regression-Based Feature Selection on Large Scale Human Activity Recognition

Mazaar¹,

Emary²,

Onsi³

2016

ijacsa

View full text Add to dashboard Cite

Abstract-In this paper, we present an approach for regression-based feature selection in human activity recognition. Due to high dimensional features in human activity recognition, the model may have over-fitting and can't learn parameters well. Moreover, the features are redundant or irrelevant. The goal is to select important discriminating features to recognize the human activities in videos. R-Squared regression criterion can identify the best features based on the ability of a feature to explain the variations in the target class. The features are significantly reduced, nearly by 99.33%, resulting in better classification accuracy. Support Vector Machine with a linear kernel is used to classify the activities. The experiments are tested on UCF50 dataset. The results show that the proposed model significantly outperforms state-of-the-art methods.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Regression-Based Feature Selection on Large Scale Human Activity Recognition

Mazaar¹,

Emary²,

Onsi³

2016

ijacsa

View full text Add to dashboard Cite

show abstract

“…While there is a large body of literature on human action/ activity recognition, such as [25,41,48,44], the problem of recognizing human interactions is a relatively less studied topic in computer vision. Related work on human interaction recognition typically addresses one of the following two interaction types: (i) human-object interactions, and (ii) human-human interactions.…”

Section: Related Workmentioning

confidence: 99%

Two-person interaction recognition via spatial multiple instance embedding

Sener

Ikizler-Cinbis

2015

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

a b s t r a c tIn this work, we look into the problem of recognizing two-person interactions in videos. Our method integrates multiple visual features in a weakly supervised manner by utilizing an embedding-based multiple instance learning framework. In our proposed method, first, several visual features that capture the shape and motion of the interacting people are extracted from each detected person region in a video. Then, twoperson visual descriptors are formed. Since the relative spatial locations of interacting people are likely to complement the visual descriptors, we propose to use spatial multiple instance embedding, which implicitly incorporates the distances between people into the multiple instance learning process. Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction.

show abstract

“…Another recently proposed video descriptor for human action recognition is Gist3D [16]. This is a global descriptor based on a 3D filter bank and describes the spatio-temporal 'gist' of a video.…”

Section: ) Spatio-temporal Detectorsmentioning

confidence: 99%

“…It should however be noted here that MBH performance comprises a complex multiple kernel combination of a horizontal MBHx and vertical MBHy component. In [16], a recognition accuracy of 73.7% is reported for a combination of Gist3D and Harris STIP + HOG/HOF descriptors. However, performance of the individual descriptors is Per-class recognition performances on UCF50 dataset.…”

Section: H Ucf50mentioning

confidence: 99%

Evaluation of Color Spatio-Temporal Interest Points for Human Action Recognition

Everts

Gemert

Gevers

2014

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-This paper considers the recognition of realistic human actions in videos based on spatio-temporal interest points (STIPs). Existing STIP-based action recognition approaches operate on intensity representations of the image data. Because of this, these approaches are sensitive to disturbing photometric phenomena, such as shadows and highlights. In addition, valuable information is neglected by discarding chromaticity from the photometric representation. These issues are addressed by color STIPs. Color STIPs are multichannel reformulations of STIP detectors and descriptors, for which we consider a number of chromatic and invariant representations derived from the opponent color space. Color STIPs are shown to outperform their intensity-based counterparts on the challenging UCF sports, UCF11 and UCF50 action recognition benchmarks by more than 5% on average, where most of the gain is due to the multichannel descriptors. In addition, the results show that color STIPs are currently the single best low-level feature choice for STIP-based approaches to human action recognition.

show abstract

Classifying web videos using a global video descriptor

Cited by 90 publications

References 25 publications

Regression-Based Feature Selection on Large Scale Human Activity Recognition

Regression-Based Feature Selection on Large Scale Human Activity Recognition

Two-person interaction recognition via spatial multiple instance embedding

Evaluation of Color Spatio-Temporal Interest Points for Human Action Recognition

Contact Info

Product

Resources

About