Recently, interest point detectors and descriptors have become prominent in the field of computer vision and are typically used to determine correspondences between two images of the same scene. We present a design procedure for the Finite Element Laplacian Feature (FELF) Detector which is similar to the multi-scale approach used in the SURF detector and detects blob like features. We illustrat...

In this paper, we describe our method used to achieve our results which was submitted to the Recognition Task of the challenge. As for video features, we combined our proposed feature [1] and the dense trajectories based feature presented in [2]. We employed Fisher Vector encoding to represent videos using these features and trained multiclass linear SVMs to perform action recognition. We condu...

In this work we deal with the problem of how different local descriptors can be extended, used and combined for improving the effectiveness of video concept detection. The main contributions of this work are: 1) We examine how effectively a binary local descriptor, namely ORB, which was originally proposed for similarity matching between local image patches, can be used in the task of video con...

Large bedforms in the nearshore (with heights of 10 – 50 cm and lengths of 1-10 m) are observed to occur frequently and to be ubiquitous throughout the surf zone (e.g., Clifton et al. 1971, Gallagher et al. 2002, Hay and Wilson 1994, Thornton et al. 1998). However, their dynamics are poorly understood and they are generally neglected in models of sediment transport, morphology change and nearsh...

Practical use of SURF feature points in large-scale indexing and retrieval engines requires an efficient means for storing and decoding these features. This paper investigates several methods for compression and storage of SURF feature points, considering both storage consumption and disk-read efficiency. We compare each scheme with a baseline plaintext encoding scheme as used by many existing ...

1. Theoretical investigations of the vertical structure of mean currents, tidal flows, and low frequency (infragravity) oscillations on the inner shelf and inside the surf zone. This work expands on recent theoretical developments for shear instabilities that follow methodology developed for tidal flows on the continental shelf. Results will be compared with field data examined as part of the s...

We present a Conditional Random Field (CRF) approach to tracking-by-detection in which we model pairwise factors linking pairs of detections and their hidden labels, as well as higher order potentials defined in terms of label costs. Our method considers long-term connectivity between pairs of detections and models cue similarities as well as dissimilarities between them using time-interval sen...

Minimization techniques are commonly adopted methodologies for retrieving a 3D surface starting from its shaded representation (image), i.e. for solving the widely known shape from shading (SFS) problem. Unfortunately, depending on the imaged object to be reconstructed, retrieved surfaces often results to be completely different from the expected ones. In recent years, a number of interactive m...

The use of irony and sarcasm in social media allows us to study them at scale for the first time. However, their diversity has made it difficult to construct a high-quality corpus of sarcasm in dialogue. Here, we describe the process of creating a largescale, highly-diverse corpus of online debate forums dialogue, and our novel methods for operationalizing classes of sarcasm in the form of rhet...

This paper assesses the behaviour of international and domestic students on beaches in Queensland, Australia and their knowledge of beach safety practices. The data for the research was collected from Surf Life Saving Queensland lifeguards/savers, using a focus group interview and questionnaire survey distributed to a convenience sample of students from The University of Queensland. The results...