Patterns of gaze play an important role in video analysis and understanding human behavior. This paper proposes a novel approach to solve the problem of activity recognition from first-person gaze movements. Novel n-gram statistical features are extracted from these movements via a multi scale and temporal representation scheme. A joint classification and segmentation of activities and a spatio-temporal contextual learning approach built upon confidence values from long-range neighborhoods reinforces the novelty and efficiency of the proposed approach. Experimental results show that the proposed method improves by 18% on the current baseline.
AggarwalJ. and RyooM., Human activity analysis: A review, ACM Computing Surveys43(16) (2011), 16-33.
2.
AhmadlouM. and AdeliH., Enhanced Probabilistic Neural Network with Local Decision Circles: A Robust Classifier, Integrated Computer-Aided Engineering17(3) (2010), 197-201.
3.
BetancourtA., MorerioP., RegazzoniC.S. and RauterbergM., The Evolution of First Person Vision Methods: A Survey, IEEE Transactions on Circuits and Systems for Video Technology25(5) (2015), 744-760.
4.
BullingA., WardJ., GellersenH. and TrosterG., Eye Movement Analysis for Activity Recognition using Electrooculography, IEEE Transactions on Pattern Analysis and Machine Intelligence33(4) (2011), 741-751.
5.
BullingA., WeichelC. and GellersenH., Eyecontext: Recognition of High-level Contextual Cues from Human Visual Behaviour, ACM SIGCHI Int. Conference on Human Factors in Computing Systems (CHI), 2013.
6.
CourtemancheF., AdmeurE., DufresneA., NajjarM. and MpondoF., Activity recognition using eye-gaze movements and traditional interactions, Interacting with Computers23 (2011), 202-213.
7.
DoshiA. and TrivediM.M., On the Roles of Eye Gaze and Head Dynamics in Predicting Driver's Intent to Change Lanes, IEEE Trans. on Intelligent Transportation Systems (ITS)10 (2009), 453-462.
8.
FanR.-E., ChangK.-W., HsiehC.-J., WangX.-R. and LinC.-J., Liblinear: A Library for Large Linear Classification, Journal of Machine Learning Research (JMLR)9 (2008), 1871-1874.
9.
FathiA., FarhadiA. and RehgJ.M., Understanding egocentric activities, IEEE International Conference on Computer Vision (ICCV) (2011), 407-414.
10.
FathiA., LiY. and RehgJ.M., Learning to Recognize Daily Actions using Gaze, European Conference on Computer Vision (ECCV)7572 (2012), 314-327.
11.
FischlerM.A. and BollesR.C., Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography, Communications of the ACM24 (1981), 381-395.
12.
HirschauerT., AdeliH. and BufordT., Computer-Aided Diagnosis of Parkinson's Disease using an Enhanced Probabilistic Neural Network, Journal of Medical Systems39(179) (2015).
13.
HuynhT., FritzM. and SchieleB., Discovery of Activity Patterns using Topic Models, Int. Conference on Ubiquitous Computing (UbiComp), 2008, 10-19.
14.
KeatF.T., RanganathS. and VenkateshY.V., Eye Gaze Based Reading Detection, Proc. IEEE Conf. Convergent Technologies for the Asia-Pacific Region2 (2003), 825-828.
15.
KitaniK.M., OkabeT., SatoY. and SugimotoA., Fast Unsupervised Ego-Action Learning for First-Person Sports Videos, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011), 3241-3248.
16.
LaffertyJ.D., McCallumA. and PereiraF.C.N., Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, Int. Conference on Machine Learning (ICML) (2001), 282-289.
17.
LaptevI. and LindebergT., Space-Time Interest Points, Int. Conference on Computer Vision (ICCV)1 (2003), 432-439.
18.
Le CoatF., PissalouxE., BonninP., TissotA., GariéTh. and DurbinF., Parallel Algorithm for Very Fast Velocity Field Estimation, IEEE Int. Conference on Image Procesing (1997), II-179-182.
19.
LeeG., MinguiK., SwathiK. and MinhoL., Action-perception cycle learning for incremental emotion recognition in a movie clip using 3D fuzzy GIST based on visual and EEG signals, Integrated Computer-Aided Engineering21(3) (2014), 295-310.
20.
LeslieC., EskinE. and NobleW.S., The Spectrum Kernel: A String Kernel for SVM Protein Classification, Pacific Symposium on Biocomputing7 (2002), 566-575.
21.
LiD., XuL., GoodmanE.D., XuY. and WuY., Integrating a Statistical Background - Foreground Extraction Algorithm and SVM Classifier for Pedestrian Detection and Tracking, Integrated Computer-Aided Engineering20(3) (2013), 201-216.
22.
LoweD.G., Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision60(2) (2004), 91-110.
23.
MartinezF., CarboneA. and PissalouxE., Combining First-Person and Third-Person Gaze for Attention Recognition, 10th IEEE Conf. on Automatic Face and Gesture Recognition, Shanghai, April 2013.
24.
MayolW.W. and MurrayD.W., Wearable hand activity recognition for event summarization, Int. Symposium on Wearable Computers (ISWC), 2005, 122-129.
25.
MeraoumiaA., ChitroubS. and BouridaneA., 2D and 3D Palmprint Iinformation, PCA and HMM for an Improved Person Recognition Performance, Integrated Computer-Aided Engineering20(3) (2013), 303-319.
26.
MesquitaR.G., A New Thresholding Algorithm for Document Images based on the Perception of Objects by Distance, Integrated Computer-Aided Engineering21(2) (2014), 133-146.
27.
NacharR., InatyE., BonninP. and AlayliY., Towards an automatic image co-registration technique using edge dominant corners primitive, Integrated Computer-Aided Engineering22(1) (2015), 1-19.
28.
OgakiK., KitaniK.M., SuganoY. and SatoY., Coupling Eye-Motion and Ego-Motion Features for First-Person Activity Recognition, IEEE CVPR (Computer Vision and Pattern Recognition) Workshop on Egocentric Vision (ECV), 2012, 1-7.
29.
PissalouxE., A Systolic Architecture For Stereo Image Matching, IEEE Asia-Pacific Conference on Circuits and Systems (APCCS), 2002, Bali, Indonesia.
30.
SaltonG. and McGillM.J., Introduction to modern information retrieval, McGraw-Hill, Inc. New York, N.Y., 1986.
31.
SchieleB., OliverN., JebaraT. and PentlandA., An Interactive Computer Vision System DyPERS: Dynamic Personal Enhanced Reality System, ICVS'99 (Int. Conference on Vision Systems), January 1999, 51-65.
32.
SpriggsE.H., De la TorreF. and HebertM., Temporal Segmentation and Activity Classification from First-Person Sensing, IEEE Workshop on Egocentric Vision, CVPR 2009, 17-24.
33.
StarnerT., WeaverJ. and PentlandA., Real-time American Sign Language Recognition using Desk and Wearable Computer based Video, IEEE Transactions on Pattern Analysis and Machine Intelligence20 (1998), 1371-1375.
34.
TuZ. and BaiX., Auto-Context and its Application to High-Level Vision Tasks and 3D Brain Image Segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence32 (2010), 1744-1757.
35.
VillarJ., ChiraC., SedanoJ., GonzaleS. and TrejoJ.M., A hybrid intelligent recognition system for the early detection of strokes, Integrated Computer-Aided Engineering22(3) (2015), 251-227.
36.
XuB., GuoP. and Philip ChenC.L., An Adaptive Regular ization Method for Sparse Representation, Integrated Computer-Aided Engineering21(1) (2014), 91-100.
