Dynamic Image Networks for Action Recognition

Hakan Bilen, Basura Fernando, Efstratios Gavves, Andrea Vedaldi, Stephen Gould

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis especially when convolutional neural networks (CNNs) are used. The dynamic image is based on the rank pooling concept and is obtained through the parameters of a ranking machine that encodes the temporal evolution of the frames of the video. Dynamic images are obtained by directly applying rank pooling on the raw image pixels of a video producing a single RGB image per video. This idea is simple but powerful as it enables the use of existing CNN models directly on video data with fine-tuning. We present an efficient and effective approximate rank pooling operator, speeding it up orders of magnitude compared to rank pooling. Our new approximate rank pooling CNN layer allows us to generalize dynamic images to dynamic feature maps and we demonstrate the power of our new representations on standard benchmarks in action recognition achieving state-of-the-art performance.
Original languageEnglish
Title of host publicationComputer Vision and Pattern Recognition 2016
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages9
Publication statusPublished - 12 Dec 2016
Event29th IEEE Conference on Computer Vision and Pattern Recognition - Las Vegas, United States
Duration: 26 Jun 20161 Jul 2016


Conference29th IEEE Conference on Computer Vision and Pattern Recognition
Abbreviated titleCVPR 2016
CountryUnited States
CityLas Vegas
Internet address


  • computer vision
  • Action Recognition, Weakly Supervised Learning, Object Detection

Fingerprint Dive into the research topics of 'Dynamic Image Networks for Action Recognition'. Together they form a unique fingerprint.

Cite this