Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Non-technical reading
Published:
As I grow in maturity and have started taking on more responsibility in my roles, I realize that I’m starting to digest a lot of non-technical content that informs my views and beliefs. To complement my technical reading post, this is a list of non-technical reading that has shaped me. It isn’t necessarily in a particular order, and while I’ll add to it in reverse chronological order, they are all timeless reads as far as I’m concerned. The topics revolve around philosophy, management, organization, leadership, productivity, customer development, marketing, etc.
Personality profiles of researchers and leaders
Published:
I describe myself as a researcher and a leader - naturally, I’ve been trying to figure out what makes a strong researcher or leader in the hopes that I can identify what I need to work on. I think it’s useful to talk about success in these roles as it relates to psychometric profiles, in particular with the 5-factor/OCEAN/the big 5 model of personality.
On Leadership at Tech Startups
Published:
Qualifier: My experiences and perspectives are probably heavily influenced by a narrow view I have into the world involving mostly tech startups and knowledge workforces, coupled with my personal experiences. I am not the most well-educated in leadership and coaching theory, so my language is likely flawed at times, but I hope I get some sentiments across as intended. As with almost everything I’m interested in, I treat learning about leadership academically.
Research Philosophy
Published:
I’ve felt previously that it is important to develop a philosophy on how to do consistent, efficient, high quality, honest research. It serves as a reminder to base decisions in a grounding framework and provides comfort in times of uncertainty. It also helps me understand why certain collaborations are more successful and how to build/grow research teams that are energized. This page serves to document my continuously evolving research philosophy:
Technical reading
Published:
This is a list of select research works that I’ve read and like from most to least recently read, much like a communication of my stream of consciousness. I would like to think that I could have collaborated to write some of these and it is my dream that one day I might produce works like these.
Industry vs. academia after a PhD
Published:
I’ve been encouraged by colleagues to share my take on choosing a position industry or academia after graduating with a PhD. So here goes.
On balancing classes for an imbalanced class problem
Published:
The common suggestion that balancing classes in an imbalanced class problem boosts accuracy, either through oversampling the minority class or undersampling the majority class, is an over-generalization. In many cases, this is simply not true unless the minority class oversampling process includes data augmentation. Intuitively, this is because the amount of information in your minority class is fixed even if you oversample it (you’re just creating duplicates, which do not change the decision boundary). I realize this discussion is restricted to discriminative modeling.
Normalize if you regularize
Published:
There is a world of preprocessing methods from which a scientist has to choose. In each of the preprocessing tasks of cleaning, missing data handling, standardizing, encoding, binning, binarizing and etcetera, there are further choices to make. Some of these choices are data dependent, some not. Some are model dependent, some not. I want to talk about one such choice: z-score normalizing your training set before training.
On normality tests
Published:
I recently came across a very interesting problem. I wanted to verify if some of my data could be assumed to be normally distributed since I wanted to use statistical methods that assumed the same. One would assume that you would just run a statistical test for normality such as the Shapiro-Wilk or Anderson-Darling tests on the data and if the null hypothesis is not rejected, you would be okay to go ahead with the normality assumption.
Conditional probability maps of extreme temperatures
Published:
So I created my first R Shiny app and I obviously think its pretty cool. Props to the Shiny team for making the learning process of how to make these apps so enjoyable.
portfolio
Learn the K in K-means clustering
Intelligently split clusters to automatically determine the number of clusters in K-means.
Manifold Parzen Windows
A manifold-aware parzen windows density estimator. 
Street Scene
A new dataset and evaluation protocol for video anomaly detection. 
Video anomaly detection with auto-encoders
Reproduction of a paper that performs video frame-level video anomaly detection using convolutional auto-encoders
publications
Scalable nearest neighbor based hierarchical change detection framework for crop monitoring
Published in IEEE International Conference on Big Data, 2016
Download here
Real-Time Energy Audit of Built Environments: Simultaneous Localization and Thermal Mapping
Published in Journal of Infrastructure Systems, 2018
This paper is about performing SLAM with a thermal sensor.
Download here
Relational Long Short-Term Memory for Video Action Recognition
Published in arXiv, 2018
This paper presents a Relational LSTM network for Video Action Recognition.
Download here
Anomalous cluster detection in spatiotemporal meteorological fields
Published in Statistical Analysis and Data Mining: The ASA Data Science Journal, 2018
This paper presents a piecewise parameteric approach to detect anomalous clusters in gridded spatio-temporal data.
Download here
Estimating a Manifold from a Tangent Bundle Learner
Published in arXiv, 2019
This paper is about estimating a manifold from a tangent bundle learner.
Download here
Learning a distance function with a siamese network to localize anomalies in videos
Published in WACV 2020, 2020
This paper presents a new metric learning approach to localize anomalies in surveillance video.
Download here
Street Scene: A new dataset and evaluation protocol for video anomaly detection
Published in WACV 2020, 2020
This paper presents a new large dataset and evaluation protocol for video anomaly detection.
Download here
Multimodal Deep Learning Based Crop Classification Using Multispectral and Multitemporal Satellite Imagery
Published in KDD, 2020
This paper presents a multimodal strategy for crop classification using multispectral imagery and NDVI phenology time series
Download here
A Survey of Single-Scene Video Anomaly Detection
Published in TPAMI 2020, 2020
This survey article summarizes research trends on the topic of anomaly detection in videos
Download here
Local Clustering with Mean Teacher for Semi-supervised learning
Published in ICPR, 2021
This paper presents a simple method called Local Clustering to mitigate the issue of confirmation bias in Mean Teacher
Download here
Perceptual metric learning for video anomaly detection
Published in MVA 2021, 2021
This paper generalizes a previous metric learning approach to operate with arbitrary-sized region proposals to localize anomalies in surveillance video
Download here