Efficient On-the-fly Category Retrieval Using ConvNets and GPUs
By Ken Chatfield, Karen Simonyan, Andrew Zisserman. 2014
27 citations recorded by the source corpus.
We investigate the gains in precision and speed, that can be obtained by using Convolutional Networks (ConvNets) for on-the-fly retrieval – where classifiers are learnt at run time for a textual query from downloaded images, and used to rank large image or video datasets.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Efficiency & Compression
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Barbara Caputo
- Andrew Zisserman
- Tinne Tuytelaars
- Luc Van Gool
- Trevor Darrell
- Gabriella Csurka
- Jiashi Feng
- Andrea Vedaldi
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Andrew Zisserman
- Dacheng Tao
- Trevor Darrell
- Cordelia Schmid
- Andrea Vedaldi
- Xiaogang Wang
- Jitendra Malik
In Information Retrieval & Search
- Tinne Tuytelaars
- Andrew Zisserman
- Carl Doersch
- Ondřej Chum
- Josef Sivic
- Herv'e J'egou
- Li Fei-Fei
- Matthijs Douze
In Efficiency & Compression
Citations in the corpus
- CrossTransformers: spatially-aware few-shot transfer (2020, background): “Deep neural network representations can bring some visual knowledge from datasets like ImageNet [67] to bear on different tasks beyond ImageNet [14, 31, 61], but empirically, this requires a non-trivial amount of labeled data in the new task.”
- A Deeper Look at Dataset Bias (2015, background): “Considering the current dimensionality of data collections, the new state of the art established by the CNN features, and the growing interest towards models that should be able to generalize while learning on-the-fly [5], it is now time to make a point on the dataset bias problem with its old and n”