Temporal Action Localization (TAL) is an important problem in computer vision with uses in video surveillance and recommendation, healthcare, entertainment, and human-computer interaction. Being an inherently data-heavy process, TAL has been bound by the availability of computing power, resulting in its slow pace of innovation. This work aims to accelerate the development of TAL models by conducting a short review of TAL's state-of-the-art, and providing extensive data about the latest models' data and compute efficiency. By researching how TAL models perform in limited data and compute settings, we find that using less data than available is often beneficial to iterating a model quickly, while in some cases, TAL is constrained by the limited amount of data. Finally, we provide general guidelines that create a simple framework for efficient TAL model development.

The aim of this paper is to find out which Machine Learning (ML) model predicts the concentration of Chlorophyll-a, in the Palmar lake in Uruguay best. Currently there are no such models to predict the growth in this lake. The algorithms which will be compared in this paper are a Linear Regression model and the U-Net model. We will compare the losses of the two models to determine which algorithm performs best. The less loss a model has, the more accurate it is, and thus the better it is. The loss of the U-Net model failed to converge to a value, therefore it was impossible to compare the two models.

In this paper we analyze the performance of a novel clustering objective that optimizes a neural network to predict segmentation. We challenge the reported results by replicating the original experiments and conducting additional tests to gain an insight into the algorithm. We analyzed the efficiency of the clustering objective on a different architecture, dataset and hyper-parameters. To our surprise the algorithm demonstrated considerably lower results when running on the new setup. Further, in our work we detail the reasons behind the discrepancy and provide configurations under which the method performs best. We show that the objective is highly sensitive to the type of images it is predicting and the complexity of the architecture that is being used with.