Presents a review of 200 references in content-based image retrieval. The paper starts with discussing the working conditions of content-based retrieval: patterns of use, types of pictures, the role of semantics, and the sensory gap. Subsequent sections discuss computational steps for image retrieval systems. Step one of the review is image processing for retrieval sorted by color, texture, and local geometry. Features for retrieval are discussed next, sorted by: accumulative and global features, salient points, object and shape features, signs, and structural combinations thereof. Similarity of pictures and objects in pictures is reviewed for each of the feature types, in close connection to the types and means of feedback the user of the systems is capable of giving by interaction. We briefly discuss aspects of system engineering: databases, system architecture, and evaluation. In the concluding section, we present our view on: the driving force of the field, the heritage from computer vision, the influence on computer vision, the role of similarity and of interaction, the need for databases, the problem of evaluation, and the role of the semantic gap.

/pdf/content-based-image-retrieval-at-the-end-of-the-early-years-q45iy9ejai.pdf

Content-based image retrieval at the end of the early years

From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

Cultivation of mindfulness, the nonjudgmental awareness of experiences in the present moment, produces beneficial effects on well-being and ameliorates psychiatric and stress-related symptoms. Mindfulness meditation has therefore increasingly been incorporated into psychotherapeutic interventions. Although the number of publications in the field has sharply increased over the last two decades, there is a paucity of theoretical reviews that integrate the existing literature into a comprehensive theoretical framework. In this article, we explore several components through which mindfulness meditation exerts its effects: (a) attention regulation, (b) body awareness, (c) emotion regulation (including reappraisal and exposure, extinction, and reconsolidation), and (d) change in perspective on the self. Recent empirical research, including practitioners’ self-reports and experimental data, provides evidence supporting these mechanisms. Functional and structural neuroimaging studies have begun to explore the neuroscientific processes underlying these components. Evidence suggests that mindfulness practice is associated with neuroplastic changes in the anterior cingulate cortex, insula, temporo-parietal junction, fronto-limbic network, and default mode network structures. The authors suggest that the mechanisms described here work synergistically, establishing a process of enhanced self-regulation. Differentiating between these components seems useful to guide future basic research and to specifically target areas of development in the treatment of psychological disorders.

How Does Mindfulness Meditation Work? Proposing Mechanisms of Action From a Conceptual and Neural Perspective

The Visual Display of Quantitative Information

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Subject motion is a common problem in all forms of BOLD MRI and it is accepted that conventional motion correction does not remove all of this variance from the data. Hypothesis-driven approaches use the shifts from these corrections as unwanted-effects regressors, whereas data-driven analysis techniques often cannot, and so are more susceptible to this form of artefact. Modified temporal cluster analysis (MTCA) is a data-driven approach to the examination of fMRI and phMRI data. It is, however, susceptible to motion artefact, which we use here as an advantage and introduce the dual MTCA method as a means to discover when and where in the brain is being affected by motion which is uncorrected for, so that those slices may be suppressed before further data-driven analysis. This is particularly useful in experiments with long repetition times since only a subset of slices will require further correction. We apply this to placebo data from a phMRI study and conclude that it will be a useful step in the preprocessing and further analysis of such experiments.

Enhanced Motion Correction in Long TR phMRI through Dual Modified Temporal Cluster Analysis

We propose a novel approach to multimodal sensor fusion for Ambient Assisted Living (AAL) which takes advantage of learning using privileged information (LUPI). We address two major shortcomings of standard multimodal approaches, limited area coverage and reduced reliability. Our new framework fuses the concept of modality hallucination with triplet learning to train a model with different modalities to handle missing sensors at inference time. We evaluate the proposed model on inertial data from a wearable accelerometer device, using RGB videos and skeletons as privileged modalities, and show an improvement of accuracy of an average 6.6% on the UTD-MHAD dataset and an average 5.5% on the Berkeley MHAD dataset, reaching a new state-of-the-art for inertial-only classiﬁcation accuracy on these datasets. We validate our framework through several ablation studies.

Inertial Hallucinations - When Wearable Inertial Devices Start Seeing Things

We propose a method for detecting valuable left-behind items in vehicle cabins which uses a single overhead camera. An additional sub-network is incorporated into the Faster R-CNN framework in order to allow it to estimate item value based on visual properties, as well as to perform detection. A loss function which contains a user-specified minimum-value threshold is introduced, which enables warnings to be given if a detected item is above this threshold. As a significant amount of real data is time consuming to collect on the scale necessary for (deep) learning-based methods, an ImageNet model is first retrained on synthetic data to adapt it to our environment, before training on some real data. The effectiveness of this detection and validation approach is demonstrated by integrating additional valuation subnetworks into two convolutional neural network detection architectures.

Detection of valuable left-behind items in vehicle cabins

We present a dual-stream CNN that learns both appearance and facial features in tandem from still images and, after feature fusion, infers person identities. We then describe an alternative architecture of a single, lightweight ID-CondenseNet where a face detector-guided DC-GAN is used to generate distractor person images for enhanced training. For evaluation, we test both architectures on FLIMA, a new extension of an existing person re-identification dataset with added frame-by-frame annotations of face presence. Although the dual-stream CNN can outperform the CondenseNet approach on FLIMA, we show that the latter surpasses all state-of-the-art architectures in top-1 ranking performance when applied to the largest existing person re-identification dataset, MSMT17. We conclude that whilst re-identification performance is highly sensitive to the structure of datasets, distractor augmentation and network compression have a role to play for enhancing performance characteristics for larger scale applications.

/pdf/deep-compact-person-re-identification-with-distractor-1uxd6ffxzx.pdf

Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs

Current one-stage action detection methods, which simultaneously predict action boundaries and the corresponding class, do not estimate or use a measure of confidence in their boundary predictions, which can lead to inaccurate boundaries. We incorporate the estimation of boundary confidence into one-stage anchor-free detection, through an additional prediction head that predicts the refined boundaries with higher confidence. We obtain state-of-the-art performance on the challenging EPICKITCHENS-100 action detection as well as the standard THUMOS14 action detection benchmarks, and achieve improvement on the ActivityNet-1.3 benchmark.

Majid Mirmehdi

Papers

Enhanced Motion Correction in Long TR phMRI through Dual Modified Temporal Cluster Analysis

Inertial Hallucinations - When Wearable Inertial Devices Start Seeing Things

Detection of valuable left-behind items in vehicle cabins

Deep Compact Person Re-Identification with Distractor Synthesis via Guided DC-GANs

Refining Action Boundaries for One-stage Detection