Video classification with CNNs: Using the codec as a spatio-temporal activity sensor

A Chadha, A Abbas… - IEEE Transactions on …, 2017 - ieeexplore.ieee.org
We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …
被引用次数：39 相关文章

Video Classification With CNNs: Using the Codec as a Spatio-Temporal Activity Sensor

A Chadha, A Abbas, Y Andreopoulos - … on Circuits and Systems for Video …, 2019 - dl.acm.org
We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …

Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor

A Chadha, A Abbas, Y Andreopoulos - arXiv e-prints, 2017 - ui.adsabs.harvard.edu
We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …

Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor

A Chadha, A Abbas, Y Andreopoulos - arXiv preprint arXiv:1710.05112, 2017 - arxiv.org
We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …

Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor

A Chadha, A Abbas… - IEEE Transactions on …, 2017 - discovery.ucl.ac.uk
We investigate video classification via a two-stream convolutional neural network (CNN)
design that directly ingests information extracted from compressed video bitstreams. Our …