Dr Relja Arandjelović (Др Реља Аранђеловић)
Links towards some of my projects and online demos.
Most of these are links towards external pages 
.
.
Blog post: Towards Robust and Verified AI
Specification Testing, Robust Training, and Formal Verification
Specification Testing, Robust Training, and Formal Verification
Code: On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
Training models that are verifiably robust to norm-bounded adversarial perturbations.
Training models that are verifiably robust to norm-bounded adversarial perturbations.
Project page and code: Neighbourhood Consensus Networks
Finding reliable dense correspondences between a pair of images, trained from weak supervision.
Finding reliable dense correspondences between a pair of images, trained from weak supervision.
Blog post: Objects that Sound
What can be learnt by looking at and listening to a large number of unlabelled videos?
What can be learnt by looking at and listening to a large number of unlabelled videos?
Project page and code: CNN Geometric matching with weak supervision
End-to-end weakly-supervised semantic alignment.
End-to-end weakly-supervised semantic alignment.
Project page and code: CNN Geometric matching
Convolutional neural network architecture for geometric matching.
Convolutional neural network architecture for geometric matching.
Code: VGG Image Search Engine (VISE)
Image search engine mainly based on the codebase I developed during my PhD and PostDoc at VGG. It implements memory efficient large-scale retrieval using local descriptors, spatial reranking, Hamming embedding, query expansion, etc.
Image search engine mainly based on the codebase I developed during my PhD and PostDoc at VGG. It implements memory efficient large-scale retrieval using local descriptors, spatial reranking, Hamming embedding, query expansion, etc.
Offline demo: NetVLAD
Place recognition results using NetVLAD for all queries in the 24/7 Tokyo dataset.
Place recognition results using NetVLAD for all queries in the 24/7 Tokyo dataset.
Project page: 24/7 Place Recognition by View Synthesis
Place recognition for situations where the scene undergoes a major change in appearance.
Place recognition for situations where the scene undergoes a major change in appearance.
Project page: Sculpture Retrieval and Identification
A retrieval based method for automatically determining the title and sculptor of an imaged sculpture.
A retrieval based method for automatically determining the title and sculptor of an imaged sculpture.
Demo: Smooth Sculpture Retrieval
Instantly search for specific smooth sculptures.
Click on the image, then outline the suggested (or any other) query region and click on 'Search'.
Instantly search for specific smooth sculptures.
Click on the image, then outline the suggested (or any other) query region and click on 'Search'.
Project page: Visual Search of BBC News
On-the-fly retrieval of object categories, instances and faces using a textual keyword.
On-the-fly retrieval of object categories, instances and faces using a textual keyword.
Demo: Visual Search of BBC News
Enter a text query in the textbox to the right, and hit search.
Example queries: Pound note, Mona Lisa, Buckingham palace, Big Ben, Coca Cola.
Further usage instructions
Blog post by the BBC Archive
Enter a text query in the textbox to the right, and hit search.
Example queries: Pound note, Mona Lisa, Buckingham palace, Big Ben, Coca Cola.
Further usage instructions
Blog post by the BBC Archive
Demo: Matching Ballad Illustrations
Instantly match and compare printed illustrations in the Bodleian library ballads.
Click on the image, then outline the suggested (or any other) query region and click on 'Search'.
Instantly match and compare printed illustrations in the Bodleian library ballads.
Click on the image, then outline the suggested (or any other) query region and click on 'Search'.
Code: Fast Semantic Segmentation via Soft Segments
An implementation of the fast semantic segmentation method described in our ACCV 2014 paper Visual vocabulary with a semantic twist.
An implementation of the fast semantic segmentation method described in our ACCV 2014 paper Visual vocabulary with a semantic twist.
