July 2017: I joined Microsoft AI and Research as Senior Applied Scientist.NEW

I completed my Ph.D. in Computer Science at UCLA, as a member of the Vision Lab under the supervision of Prof. Stefano Soatto. My research spans the areas of Machine Learning, Computer Vision and Robotics, where my focus is on Deep Learning and Reinforcement Learning.

I received my diploma in Electrical and Computer Engineering at the National Technical University of Athens. In my final year I did research under the guidance of Prof. Petros Maragos. My diploma thesis proposes Computer Vision methods for the digital restoration of damaged paintings with application in the prehistoric Wall Paintings of Thera. It was presented at DSP'13.

Here is my CV, my LinkedIn and my Google Scholar profile.


Summer 2016: Research intern in Microsoft Research at Redmond.
We worked on Person Re-identification from depth and introduced a novel temporal-attention principle based on reinforcement learning (arXiv). Mentors: Zicheng Liu and Yinpeng Chen.

Summer 2015: R&D Engineering intern at Sony's Intelligent System Technology Dept. in Tokyo.
I designed and implemented deep reinforcement learning software for autonomous navigation. My role involved algorithmic design, implementation lead and experimentation on simulated and real data. Mentors: Yusuke Watanabe, Akira Nakamura and Kenta Kawamoto.

Summer 2014: Research intern in NASA's Jet Propulsion Laboratory.
We invented a novel algorithm for generic object proposals and large-scale detection (arXiv). Mentor: Thomas Fuchs.

Summer 2013: Research intern in the Computer Vision lab at Peking University in Beijing.
I did research in graphical models with Computer Vision applications. Mentor: Yizhou Wang.


N. Karianakis, Z. Liu, Y. Chen and S. Soatto.NEW
Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors.
arXiv preprint (arXiv:1705.09882), May 2017 [paper]

N. Karianakis, J. Dong and S. Soatto.NEW
An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability.
Conference on Computer Vision and Pattern Recognition (CVPR), June 2016 [project, code]

J. Dong, N. Karianakis, D. Davis, J. Hernandez, J. Balzer and S. Soatto.
Multiview Feature Engineering and Learning.
Conference on Computer Vision and Pattern Recognition (CVPR), June 2015 [paper, project]

S. Soatto, J. Dong and N. Karianakis.
Visual Scene Representations: Scaling and Occlusion in Convolutional Architectures.
International Conference on Learning Representations (ICLR), workshop, May 2015 [paper]

N. Karianakis, T. Fuchs and S. Soatto.
Boosting Convolutional Features for Robust Object Proposals
arXiv preprint (arXiv:1503.06350), March 2015 [paper]

N. Karianakis, Y. Wang and S. Soatto.
Learning to Discriminate in the Wild: Representation-Learning Network for Nuisance-Invariant Image Comparison.
UCLA CS Technical Report, December 2013 [paper]

N. Karianakis and P. Maragos.
An integrated System for Digital Restoration of Prehistoric Theran Wall Paintings.
Conference on Digital Signal Processing (DSP), July 2013 [paper / slides]


N. Karianakis.
Sampling Algorithms to Handle Nuisances in Large-Scale Recognition.
Ph.D. Dissertation, 2017 (University of California, Los Angeles) [pdf]

N. Karianakis.
Digital Restoration of Prehistoric Theran Wall Paintings.
Diploma Thesis, 2011 (National Technical University of Athens) [pdf (in Greek)]


J. Dong, X. Fei, N. Karianakis, K. Tsotsos and S. Soatto.
Visual-Inertial Scene Representations.
CVPR demo session, June 2016 [poster, demo]


An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability.
CVPR, June 2016 [pdf]

Learning to Discriminate in the Wild: Representation-Learning Network for Nuisance-Invariant Image Comparison.
UCLA SEAS Tech Forum, February 2014 [pdf]

How can Representation Learning deal with the problem of Nuisance Variability in Computer Vision?
Peking University intern, Summer 2013 [pdf]

Research Projects

Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors. [paper]

This work targets person re-identification (ReID) from depth sensors such as Kinect. Since depth is invariant to illumination and less sensitive than color to day-by-day appearance changes, a natural question is whether depth is an effective modality for Person ReID, especially in scenarios where individuals wear different colored clothes or over a period of several months. We explore the use of recurrent Deep Neural Networks for learning high-level shape information from low-resolution depth images. In order to tackle the small sample size problem, we introduce regularization and a hard temporal attention unit. The whole model can be trained end to end with a hybrid supervised loss. We carry out a thorough experimental evaluation of the proposed method on three person re-identification datasets, which include side views, views from the top and sequences with varying degree of partial occlusion, pose and viewpoint variations. To that end, we introduce a new dataset with RGB-D and skeleton data. In a scenario where subjects are recorded after three months with new clothes, we demonstrate large performance gains attained using Depth ReID compared to a state-of-the-art Color ReID. Finally, we show further improvements using the temporal attention unit in multi-shot setting.

An Empirical Evaluation of Current Convolutional Architectures’ Ability to Manage Nuisance Location and Scale Variability. [paper, project, code]

We conduct an empirical study to test the ability of convolutional neural networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio. We isolate factors by adopting a common convolutional architecture either deployed globally on the image to compute class posterior distributions, or restricted locally to compute class conditional distributions given location, scale and aspect ratios of bounding boxes determined by proposal heuristics. In theory, averaging the latter should yield inferior performance compared to proper marginalization. Yet empirical evidence suggests the converse, leading us to conclude that – at the current level of complexity of convolutional architectures and scale of the data sets used to train them – CNNs are not very effective at marginalizing nuisance variability. We also quantify the effects of context on the overall classification task and its impact on the performance of CNNs, and propose improved sampling techniques for heuristic proposal schemes that improve end-to-end performance to state-of-the-art levels. We test our hypothesis on a classification task using the ImageNet benchmark and on a wide-baseline matching task using the Oxford and Fischer’s datasets.

Boosting Convolutional Features for Robust Object Proposals. [paper]

We present a method to generate object proposals, in the form of bounding boxes in a test image, to be fed to a classifier such as a convolutional neural network (CNN), in order to reduce test time complexity of object detection and classification. We leverage on filters learned in the lower layers of CNNs to design a binary boosting classifier and a linear regressor to discard as many windows as possible that are unlikely to contain objects of interest. We test our method against competing proposal schemes, and end-to-end on the Imagenet detection challenge. We show state-of-the-art performance when at least 1000 proposals per frame are used, at a manageable computational complexity compared to alternate schemes that make heavier use of low-level image processing.

Learning to Discriminate in the Wild: Representation-Learning Network for Nuisance-Invariant Image Comparison. [paper]

We test the hypothesis that a representation-learning architecture can train away the nuisance variability present in images, owing to noise and changes of viewpoint and illumination. First, we establish the simplest possible classification task, a binary classification with no intrinsic variability, which amounts to the determination of co-visibility from different images of the same underlying scene. This is the Occlusion Detection problem and the data are typically two sequential, but not necessarily consecutive or in order, video frames. Our network, based on the Gated Restricted Boltzmann machine (Gated RBM), learns away the nuisance variability appearing on the background scene and the occluder, which are irrelevant with occlusions, and in turn is capable of discriminating between co-visible and occluded areas by thresholding a one-dimensional semi-metric. Our method, combined with Superpixels, outperforms algorithms using features specifically engineered for occlusion detection, such as optical flow, appearance, texture and boundaries. We further challenge our framework with another Computer Vision problem, Image Segmentation from a single frame. We cast it as binary classification too, but here we also have to deal with the intrinsic variability of the scene objects. We perform boundary detection according to a similarity map for all pairs of patches and finally provide a semantic image segmentation by leveraging Normalized Cuts.

An Integrated System for Digital Restoration of Prehistoric Theran Wall Paintings. [paper]

We present a computer vision system for robust restoration of prehistoric Theran wall paintings, replacing or just supporting the work of a specialist. In the case of significant information loss on some areas of murals, the local inpainting methods are not sufficient for satisfactory restoration. Our strategy is to detect an area of relevant semantics, geometry and color in another location of the wall paintings, which in turn is stitched into the missing area by applying a seamless image stitching algorithm. An important part of our digital restoration system is the damaged and missing areas detector. It is used in combination with total variation inpainting at first for the missing area extraction and repair, and secondly for the elimination of minor defects on the retrieved part in the non-local inpainting mechanism. We propose a morphological algorithm for rough detection and we improve upon this approach by incorporating edge information. For missing areas with complicated boundaries we enhance the detection by using iterated graph cuts.