Foteini Markatopoulou

A Study on the Use of a Binary Local Descriptor and Color Extensions of Local Descriptors for Video Concept Detection

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 concept detection. 2) Based on a previously proposed paradigm for introducing color extensions of SIFT, we define in the same way color extensions for two other non-binary or binary local descriptors (SURF, ORB), and we experimentally show that this is a generally applicable paradigm. 3) In order to enable the efficient use and combination of these color extensions within a state-of-the-art concept detection methodology (VLAD), we study and compare two possible approaches for reducing the color descriptor’s dimensionality using PCA. We evaluate the proposed techniques on the dataset of the 2013 Semantic Indexing Task of TRECVID.

Cascade of classifiers based on binary, non-binary and deep convolutional network descriptors for video concept detection.

In this paper we propose a cascade architecture that can be used to train and combine different visual descriptors (local binary, local non-binary and Deep Convolutional Neural Network-based) for video concept detection. The proposed architecture is computationally more efficient than typical state-of-the-art video concept detection systems, without affecting the detection accuracy. In addition, this work presents a detailed study on combining descriptors based on Deep Convolutional Neural Networks with other popular local descriptors, both within a cascade and when using different late-fusion schemes. We evaluate our methods on the extensive video dataset of the 2013 TRECVID Semantic Indexing Task.

Comparison of Fine-Tuning and Extension Strategies for Deep Convolutional Neural Networks

In this study we compare three different fine-tuning strategies in order to investigate the best way to transfer the parameters of popular deep convolutional neural networks that were trained for a visual annotation task on one dataset, to a new, considerably different dataset. We focus on the concept-based image/video annotation problem and use ImageNet as the source dataset, while the TRECVID SIN 2013 and PASCAL VOC-2012 classification datasets are used as the target datasets. A large set of experiments examines the effectiveness of three fine-tuning strategies on each of three different pre-trained DCNNs and each target dataset. The reported results give rise to guidelines for effectively fine-tuning a DCNN for concept-based visual annotation.

Deep Multi-task Learning with Label Correlation Constraint for Video Concept Detection

In this work we propose a method that integrates multi-task learning (MTL) and deep learning. Our method appends a MTL-like loss to a deep convolutional neural network, in order to learn the relations between tasks together at the same time, and also incorporates the label correlations between pairs of tasks. We apply the proposed method on a transfer learning scenario, where our objective is to fine-tune the parameters of a network that has been originally trained on a large-scale image dataset for concept detection, so that it be applied on a target video dataset and a corresponding new set of target concepts. We evaluate the proposed method for the video concept detection problem on the TRECVID 2013 Semantic Indexing dataset. Our results show that the proposed algorithm leads to better concept-based video annotation than existing state-of-the-art methods.

Local Features and a Two-Layer Stacking Architecture for Semantic Concept Detection in Video

In this paper, we deal with the problem of extending and using different local descriptors, as well as exploiting concept correlations, toward improved video semantic concept detection. We examine how the state-of-the-art binary local descriptors can facilitate concept detection, we propose color extensions of them inspired by previously proposed color extensions of scale invariant feature transform, and we show that the latter color extension paradigm is generally applicable to both binary and nonbinary local descriptors. In order to use them in conjunction with a state-of-the-art feature encoding, we compact the above color extensions using PCA and we compare two alternatives for doing this. Concerning the learning stage of concept detection, we perform a comparative study and propose an improved way of employing stacked models, which capture concept correlations, using multilabel classification algorithms in the last layer of the stack. We examine and compare the effectiveness of the above algorithms in both semantic video indexing within a large video collection and in the somewhat different problem of individual video annotation with semantic concepts, on the extensive video data set of the 2013 TRECVID Semantic Indexing Task. Several conclusions are drawn from these experiments on how to improve the video semantic concept detection.

Ordering of Visual Descriptors in a Classifier Cascade Towards Improved Video Concept Detection

Concept detection for semantic annotation of video fragments e.g. keyframes is a popular and challenging problem. A variety of visual features is typically extracted and combined in order to learn the relation between feature-based keyframe representations and semantic concepts. In recent years the available pool of features has increased rapidly, and features based on deep convolutional neural networks in combination with other visual descriptors have significantly contributed to improved concept detection accuracy. This work proposes an algorithm that dynamically selects, orders and combines many base classifiers, trained independently with different feature-based keyframe representations, in a cascade architecture for video concept detection. The proposed cascade is more accurate and computationally more efficient, in terms of classifier evaluations, than state-of-the-art classifier combination approaches.

Concept Detection in Multimedia Web Resources About Home Made Explosives

This work investigates the effectiveness of a state-of-the-art concept detection framework for the automatic classification of multimedia content, namely images and videos, embedded in publicly available Web resources containing recipes for the synthesis of Home Made Explosives (HMEs), to a set of predefined semantic concepts relevant to the HME domain. The concept detection framework employs advanced methods for video (shot) segmentation, visual feature extraction (using SIFT, SURF, and their variations), and classification based on machine learning techniques (logistic regression). The evaluation experiments are performed using an annotated collection of multimedia HME content discovered on the Web, and a set of concepts, which emerged both from an empirical study, and were also provided by domain experts and interested stakeholders, including Law Enforcement Agencies personnel. The experiments demonstrate the satisfactory performance of our framework, which in turn indicates the significant potential of the adopted approaches on the HME domain.

Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection

Zero-example event detection is a problem where, given an event query as input but no example videos for training a detector, the system retrieves the most closely related videos. In this paper we present a fully-automatic zero-example event detection method that is based on translating the event description to a predefined set of concepts for which previously trained visual concept detectors are available. We adopt the use of Concept Language Models (CLMs), which is a method of augmenting semantic concept definition, and we propose a new concept-selection method for deciding on the appropriate number of the concepts needed to describe an event query. The proposed system achieves state-of-the-art performance in automatic zero-example event detection.

Online multi-task learning for semantic concept detection in video

In this paper we propose an online multi-task learning algorithm for video concept detection. In particular, we extend the Efficient Lifelong Learning Algorithm (ELLA) in the following ways: (a) we solve the objective function of ELLA using quadratic programming instead of solving the Lasso problem, (b) we add a new label-based constraint that considers concept correlations, (c) we use linear SVMs as base learners instead of logistic regression. Experimental results show improvement over both the single-task learning methods typically used in this problem and the original ELLA algorithm.

VERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval

This paper presents VERGE interactive search engine, which is capable of browsing and searching into video content. The system integrates content-based analysis and retrieval modules such as video shot segmentation, concept detection, clustering, as well as visual similarity and object-based search.