Corpus ID: 593434

EXMOVES: Classifier-based Features for Scalable Action Recognition

  title={EXMOVES: Classifier-based Features for Scalable Action Recognition},
  author={Du Tran and L. Torresani},
  • Du Tran, L. Torresani
  • Published 2014
  • Computer Science
  • CoRR
  • This paper introduces EXMOVES, learned exemplar-based features for efficient recognition of actions in videos. The entries in our descriptor are produced by evaluating a set of movement classifiers over spatial-temporal volumes of the input sequence. Each movement classifier is a simple exemplar-SVM trained on low-level features, i.e., an SVM learned using a single annotated positive space-time volume and a large number of unannotated videos. Our representation offers two main advantages… CONTINUE READING
    6 Citations

    Figures, Tables, and Topics from this paper

    Action recognition using saliency learned from recorded human gaze
    • 7
    • PDF
    ML-HDP: A Hierarchical Bayesian Nonparametric Model for Recognizing Human Actions in Video
    • 18
    • Highly Influenced
    Semantic Highlight Retrieval and Term Prediction
    • 5


    Learning realistic human actions from movies
    • 3,422
    • Highly Influential
    • PDF
    Action bank: A high-level representation of activity in video
    • 736
    • Highly Influential
    • PDF
    A Hierarchical Model of Shape and Appearance for Human Action Classification
    • 475
    • PDF
    Recognizing human actions: a local SVM approach
    • 2,840
    • PDF
    HMDB: A large video database for human motion recognition
    • 1,966
    • Highly Influential
    • PDF
    Dense Trajectories and Motion Boundary Descriptors for Action Recognition
    • 1,377
    • Highly Influential
    • PDF
    Actions as space-time shapes
    • 1,466
    • PDF
    Recognizing action at a distance
    • 1,465
    • PDF
    Retrieving actions in movies
    • I. Laptev, P. Pérez
    • Computer Science
    • 2007 IEEE 11th International Conference on Computer Vision
    • 2007
    • 467
    • PDF
    Recognizing Human Activities from Silhouettes: Motion Subspace and Factorial Discriminative Graphical Model
    • Liang Wang, D. Suter
    • Mathematics, Computer Science
    • 2007 IEEE Conference on Computer Vision and Pattern Recognition
    • 2007
    • 215
    • PDF