51 citations · 51 across the 1 of their papers we have counts for
3 papers · 1 filter
ACTNET: end-to-end learning of feature activations and multi-stream aggregation for effective instance image retrieval
Syed Sameed Husain, Eng-Jon Ong, Miroslaw Bober
We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable activation layer designed to impr…
REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval
Syed Sameed Husain, Miroslaw Bober
This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as…
Deep Architectures and Ensembles for Semantic Video Classification
Eng-Jon Ong, Sameed Husain, Mikel Bober-Irizar +1
This work addresses the problem of accurate semantic labelling of short videos. To this end, a multitude of different deep nets, ranging from traditional recurrent neural networks…