We explore the effect of dimensionality on the nearest neighbor problem. We show that under a broad set of conditions (much broader than independent and identically distributed dimensions), as dimensionality increases, the distance to the nearest data point approaches the distance to the farthest data point. To provide a practical perspective, we present empirical results on both real and synthetic data sets that demonstrate that this effect can occur for as few as 10-15 dimensions. These results should not be interpreted to mean that high-dimensional indexing is never meaningful; we illustrate this point by identifying some high-dimensional workloads for which this effect does not occur. However, our results do emphasize that the methodology used almost universally in the database literature to evaluate high-dimensional indexing techniques is flawed, and should be modified. In particular, most such techniques proposed in the literature are not evaluated versus simple linear scan, and are evaluated over workloads for which nearest neighbor is not meaningful. Often, even the reported experiments, when analyzed carefully, show that linear scan would outperform the techniques being proposed on the workloads studied in high (10-15) dimensionality!.

When is nearest neighbor meaningful

We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized data points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approximation for the tangent space at each data point, and those tangent spaces are then aligned to give the global coordinates of the data points with respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can be quite small in some cases. We illustrate our algorithm using curves and surfaces both in two-dimensional/three-dimensional (2D/3D) Euclidean spaces and in higher-dimensional Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.

/pdf/principal-manifolds-and-nonlinear-dimensionality-reduction-442mrhilga.pdf

Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

The major change in the second edition of this book is the addition of a new chapter on probabilistic retrieval. This chapter has been included because I think this is one of the most interesting and active areas of research in information retrieval. There are still many problems to be solved so I hope that this particular chapter will be of some help to those who want to advance the state of knowledge in this area. All the other chapters have been updated by including some of the more recent work on the topics covered. In preparing this new edition I have benefited from discussions with Bruce Croft, The material of this book is aimed at advanced undergraduate information (or computer) science students, postgraduate library science students, and research workers in the field of IR. Some of the chapters, particularly Chapter 6 * , make simple use of a little advanced mathematics. However, the necessary mathematical tools can be easily mastered from numerous mathematical texts that now exist and, in any case, references have been given where the mathematics occur. I had to face the problem of balancing clarity of exposition with density of references. I was tempted to give large numbers of references but was afraid they would have destroyed the continuity of the text. I have tried to steer a middle course and not compete with the Annual Review of Information Science and Technology. Normally one is encouraged to cite only works that have been published in some readily accessible form, such as a book or periodical. Unfortunately, much of the interesting work in IR is contained in technical reports and Ph.D. theses. For example, most the work done on the SMART system at Cornell is available only in reports. Luckily many of these are now available through the National Technical Information Service (U.S.) and University Microfilms (U.K.). I have not avoided using these sources although if the same material is accessible more readily in some other form I have given it preference. I should like to acknowledge my considerable debt to many people and institutions that have helped me. Let me say first that they are responsible for many of the ideas in this book but that only I wish to be held responsible. My greatest debt is to Karen Sparck Jones who taught me to research information retrieval as an experimental science. Nick Jardine and Robin …

Information retrieval

Speech emotion recognition using deep 1D & 2D CNN LSTM networks

We address the problem of tracking and recognizing faces in real-world, noisy videos. We track faces using a tracker that adaptively builds a target model reflecting changes in appearance, typical of a video setting. However, adaptive appearance trackers often suffer from drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, our tracker introduces visual constraints using a combination of generative and discriminative models in a particle filtering framework. The generative term conforms the particles to the space of generic face poses while the discriminative one ensures rejection of poorly aligned targets. This leads to a tracker that significantly improves robustness against abrupt appearance changes and occlusions, critical for the subsequent recognition phase. Identity of the tracked subject is established by fusing pose-discriminant and person-discriminant features over the duration of a video sequence. This leads to a robust video-based face recognizer with state-of-the-art recognition performance. We test the quality of tracking and face recognition on real-world noisy videos from YouTube as well as the standard Honda/UCSD database. Our approach produces successful face tracking results on over 80% of all videos without video or person-specific parameter tuning. The good tracking performance induces similarly high recognition rates: 100% on Honda/UCSD and over 70% on the YouTube set containing 35 celebrities in 1500 sequences.

/pdf/face-tracking-and-recognition-with-visual-constraints-in-253utyq21i.pdf

Face tracking and recognition with visual constraints in real-world videos

The method involves obtaining data representing an extract (E) of a flow and a timestamp for restoration of the extract by a restitution device (TV) A triggering instant is obtained according to the timestamp and another timestamp associated with data representing the extract, where the data is obtained from a flow representative of the content An action is triggered at the triggering instant, where the action is a restitution of content complementary to content of the flow during restitution on the restitution device Independent claims are also included for the following: (1) a method for transmitting time information relative to a flow during broadcast of multimedia content (2) a device for triggering an action relative to a flow during representative broadcast of multimedia content and restituted by a restitution device (3) a server (4) a computer program product comprising a set of instructions to implement steps of a method for triggering an action relative to a flow during diffusion and/or a method for transmitting time information relative to the flow during broadcast

Triggering an action relative to a flow

In this paper, we propose two boosting-based approaches
for Arabic embedded text detection in news videos.
The first approach uses Multi-Block Local Binary Patterns
features whereas the second one relies on Haar-like features.
Both approaches learn text and non-text classes using a multiexit
asymmetric boosting cascade. Bootstrap has also been used
in order to improve the rejection ability of the classifiers. Text
localization is performed by a sliding window search on a multiscale
pyramid of the input image. The proposed approaches have
been evaluated on a large database of images coming from 4
different Arabic TV channels.

Boosting-based approaches for Arabic text detection in news videos

This paper addresses the problem of unsupervised TV programs structuring. Program structuring allows direct and non linear access to the desired parts of a program. Our work addresses the structuring of recurrent TV programs like news, entertainment programs, TV shows, TV magazines. In a previous work we proposed a program structuring method based on the detection of video recurrences. In this paper we extend our study to audio recurrences and verify their influence on the final structuring. We evaluate the structuring results on both approaches (audio and video) separately and jointly. We use for evaluation a 62 hours dataset corresponding to 97 episodes of TV programs.

Audio Recurrence Contribution to a Video-based TV Program Structuring Approach

The invention relates to a method for analyzing multimedia content, comprising a temporal succession of elementary entities to verify that the media content or may not comprise at least one reference content referenced in a basic contenus.Un such a method comprises the following steps for at least one individual entity of the multimedia content to be analyzed selected according to a predetermined selection rule, known current elementary entity: - assigning a likelihood probability to each elementary entity of a set of entities elementary current candidate, - assigning a transition probability between the or said elementary entities current candidate and at least one previous candidate elementary entity - assigning a probability of identifying at least one scenario composed by a temporal succession of candidate elementary entities - a recognition decision said reference content and / or further analysis by means of a following elementary entity of said multimedia content.

Method of analyzing a multimedia content, a computer program product and corresponding analysis device

The invention relates to a method for processing a digital data stream including sequences and intersequences, wherein said method comprises a step (E1) of cutting the stream into segments on the fly and calculating signatures for said segments, and a step (E2) of detecting intersequences during which the following operations are applied to said stream on the fly: a first detection of intersequences by separation detection; the supply of a reference base (BR) with at least the signatures of the intersequences detected by the first detection; a second detection of intersequences by comparing the signatures of the stream segments obtained during the cutting step (E1) with the signatures of the intersequence segments contained in the reference base (BR).

Sid-Ahmed Berrani

Papers

Triggering an action relative to a flow

Boosting-based approaches for Arabic text detection in news videos

Audio Recurrence Contribution to a Video-based TV Program Structuring Approach

Method of analyzing a multimedia content, a computer program product and corresponding analysis device

Digital data stream processing