Dynamic Pooling for Complex Event Recognition

By Wei-Xin Li, Qian Yu, Ajay Divakaran, Nuno Vasconcelos. 2013

51 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Video Representation Learning Using Discriminative Pooling (2018, positive): “[27] propose an MIL setup for complex activity recognition using a dynamic pooling operator–a binary vector that selects input frames to be part of an action, which is learned by reducing the MIL problem to a set of linear programs.”
Video Event Detection by Inferring Temporal Instance Labels (2014, background): “[11] proposed dynamic pooling, which employs various strategies to split videos into segments based on temporal structures.”
Semantic Pooling for Complex Event Analysis in Untrimmed Videos (2016, methodology): “The standard way [5], [6] is to extract local descriptors using CNNs on each frame of a video clip and then aggregate video-wise, through either average-pooling or max-pooling or even more complicated pooling strategies, e.g., [7], [8].”
Revealing Event Saliency in Unconstrained Video Collection (2017, unknown): “By treating the locations of characteristic segments as hidden information, Li et al. [14] identified the segments most informative for detecting a given event via a multiple-instance learning paradigm.”
ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification (2017, background): “Other works in event detection and action classification rely on pooling hand crafted features over segments of videos [17, 30, 32, 37, 48].”
DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting (2014, methodology): “[10] employs a dynamic pooling procedure by selecting informative regions for pooling low level features.”
Semantic Aware Video Transcription Using Random Forest Classifiers (2014, background): “Usual goal is activity or event classification of pre-defined categories [32,27,18].”
A Robust and Efficient Video Representation for Action Recognition (2015, unknown): “Li et al (2013) attained 12.3% by automatically segmenting videos into coherent sub-sequences over which the features are pooled.”
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos (2016, methodology): “[20] who used a scoring function to identify discriminative frames in a video and then pooled over only these frames.”