no code implementations • 21 Aug 2020 • Alhabib Abbas, Yiannis Andreopoulos
We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time.
1 code implementation • 8 Oct 2019 • Yin Bi, Aaron Chadha, Alhabib Abbas, Eirina Bourtsoulatze, Yiannis Andreopoulos
The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs.
1 code implementation • ICCV 2019 • Yin Bi, Aaron Chadha, Alhabib Abbas, Eirina Bourtsoulatze, Yiannis Andreopoulos
Neuromorphic vision sensing (NVS)\ devices represent visual information as sequences of asynchronous discrete events (a. k. a., ``spikes'') in response to changes in scene reflectance.
1 code implementation • 27 Sep 2018 • Mohammad Jubran, Alhabib Abbas, Aaron Chadha, Yiannis Andreopoulos
Advanced video classification systems decode video frames to derive the necessary texture and motion representations for ingestion and analysis by spatio-temporal deep convolutional neural networks (CNNs).
no code implementations • 14 Oct 2017 • Aaron Chadha, Alhabib Abbas, Yiannis Andreopoulos
We demonstrate that selective access to MB motion vector (MV) information within compressed video bitstreams can also provide for selective, motion-adaptive, MB pixel decoding (a. k. a., MB texture decoding).
no code implementations • 13 Sep 2015 • Alhabib Abbas, Nikos Deligiannis, Yiannis Andreopoulos
We create vectors of locally aggregated centers (VLAC) by first clustering SIFT features to obtain local feature centers (LFCs) and then encoding the latter with respect to given centers of local feature centers (CLFCs), extracted from a training set.