Dynamic Feature Selection for Online Action Recognition

Bloom, Victoria; Argyriou, Vasileios; Makris, Dimitrios

doi:10.1007/978-3-319-02714-2_6

Cited by 30 publications

(41 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we conduct an extensive experimental study with the proposed approach and provide a comparison with twelve state-of-the-art OAD algorithms [19,8,5,9,20,15,44,14,32,16,17,7] on three skeleton-based datasets, MSRC-12 [8], G3D [44] and MAD [16].…”

Section: Experimental Evaluation and Discussionmentioning

confidence: 99%

“…In [7,12], the motion sequence located in the temporal sliding window is first split into sub-sequences called Motion Segments (MS) which are then modelled via a Dynamic Naive Bayes classifier for identifying the ongoing action, if any. Last, Bloom et al [6,13,14,15] proposed to decompose the motion according to a hierarchical body model and then consider the motion of the low level body parts. Authors relied also on a fixed-size temporal sliding window.…”

Section: Related Workmentioning

confidence: 99%

“…As in [15,5,33,14] we first followed a leave-subjectsout protocol, in which one subject from the full dataset is removed to get the test set while the larger remaining samples are used for building our model. We reported an average score over 10 runs.…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

“…It Methods F score DFS + AdaBoost, Bloom et al [15] 0.919 RTMS + SVM, Sharaf et al [5] 0.921 RF + ST, Baek et al [33] 0.948 CAM + DTW, Bloom et al [14] 0.978…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

See 3 more Smart Citations

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Boulahia

Anquetil

Multon

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

To cite this version:Said Yacine Boulahia, Eric Anquetil, Franck Multon, Richard Kulpa. CuDi3D: Curvilinear displacement based approach for online 3D action detection. Computer Vision and Image Understanding, Elsevier, 2018, 174, pp.57-69 AbstractBeing able to interactively detect and recognize 3D actions based on skeleton data, in unsegmented streams, has become an important computer vision topic. It raises three scientific problems in relation with variability. The first one is the temporal variability that occurs when subjects perform gestures with different speeds. The second one is the inter-class spatial variability, which refers to disparities between the displacement amounts induced by different classes (i.e. long vs. short movements). The last one is the intra-class spatial variability caused by differences in style and gesture amplitude. In this paper, we design an original approach that better considers these three issues. To address temporal variability we introduce the notion of curvilinear segmentation. It consists in extracting features, not on temporally-based sliding windows, but on trajectory segments for which the cumulated displacement equals a class-based amount. Second, to tackle inter-class spatial variability, we define several competing classifiers with their dedicated curvilinear windows. Last, we address intra-class spatial variability by designing a fusion system that takes the decisions and confidence scores of every competing classifier into account. Extensive experiments on four challenging skeleton-based datasets demonstrate the relevance of the proposed approach for action recognition and online action detection.

show abstract

Section: Experimental Evaluation and Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

“…It Methods F score DFS + AdaBoost, Bloom et al [15] 0.919 RTMS + SVM, Sharaf et al [5] 0.921 RF + ST, Baek et al [33] 0.948 CAM + DTW, Bloom et al [14] 0.978…”

Section: Gaming Action (G3d) Datasetmentioning

confidence: 99%

See 2 more Smart Citations

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Boulahia

Anquetil

Multon

et al. 2018

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…Some works have applied the sliding window technique to CHAR [8,11,12]. In [13], a sliding window is employed to accumulate and smooth the frame-wise predictions of a framebased low-latency recognition. Low-latency CHAR is also considered in [14], where so-called action points are proposed as natural temporal anchors.…”

Section: Related Workmentioning

confidence: 99%

Continuous Human Action Recognition in Ambient Assisted Living Scenarios

Chaaraoui

Flórez-Revuelta²

2015

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.

show abstract

Computer Vision - ECCV 2014 Workshops

Lourdes¹,

Bronstein²,

Rother³

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.Over the last few years, researchers from the computer vision and image processing community have joined other research groups in searching for the bases of aesthetic judgment of paintings and photographs. One of the most important issues, which has hampered research in the case of paintings compared to photographs, is the lack of subjective datasets available for public use. This issue has not only been mentioned in different publications, but was also widely discussed at different conferences and workshops. In the current work, we perform a subjective test on a recently released dataset of aesthetic paintings. The subjective test not only collects scores based on the subjective aesthetic quality, but also on other properties that have been linked to aesthetic judgment.

show abstract

Dynamic Feature Selection for Online Action Recognition

Cited by 30 publications

References 12 publications

CuDi3D: Curvilinear displacement based approach for online 3D action detection

CuDi3D: Curvilinear displacement based approach for online 3D action detection

Continuous Human Action Recognition in Ambient Assisted Living Scenarios

Computer Vision - ECCV 2014 Workshops

Contact Info

Product

Resources

About