http://cvssp-data.eps.surrey.ac.uk/Personal/AdrianHilton/Publications_files/survey_techrep.pdf

A survey of advances in vision-based human motion capture and analysis

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

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power. Centre loss penalises the distance between the deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in an angular space and penalises the angles between the deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to the exact correspondence to the geodesic distance on the hypersphere. We present arguably the most extensive experimental evaluation of all the recent state-of-the-art face recognition methods on over 10 face recognition benchmarks including a new large-scale image database with trillion level of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state-of-the-art and can be easily implemented with negligible computational overhead. We release all refined training data, training codes, pre-trained models and training logs, which will help reproduce the results in this paper.

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

https://hal.inria.fr/inria-00459653/document

A survey of vision-based methods for action representation, segmentation and recognition

Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years. Its development in the past two decades can be regarded as an epitome of computer vision history. If we think of today's object detection as a technical aesthetics under the power of deep learning, then turning back the clock 20 years we would witness the wisdom of cold weapon era. This paper extensively reviews 400+ papers of object detection in the light of its technical evolution, spanning over a quarter-century's time (from the 1990s to 2019). A number of topics have been covered in this paper, including the milestone detectors in history, detection datasets, metrics, fundamental building blocks of the detection system, speed up techniques, and the recent state of the art detection methods. This paper also reviews some important detection applications, such as pedestrian detection, face detection, text detection, etc, and makes an in-deep analysis of their challenges as well as technical improvements in recent years.

Object Detection in 20 Years: A Survey

Lately, electroencephalography (EEG)-based auth- entication has received considerable attention from the scientific community. However, the limited usability of wet EEG electrodes as well as low accuracy for large numbers of users have so far prevented this new technology to become commonplace. In this study a novel EEG-based authentication system is presented, which is based on the rapid serial visual presentation paradigm and uses a knowledge-based approach for authentication. Twenty-nine subjects’ data were recorded and analyzed with wet EEG electrodes as well as dry ones. A true acceptance rate of 100% can be reached for all subjects with an average required login time of 13.5 s for wet and 27 s for dry electrodes. Average false acceptance rates for the dry electrode setup were estimated to be $3.33 \times 10^{-5}$ .

A High-Security EEG-Based Login System with RSVP Stimuli and Dry Electrodes

Vision-based human action recognition provides an advanced interface, and research in the field of human action recognition has been actively carried out. However, an environment from dynamic viewpoint, where we can be in any position, any direction, etc., must be considered in our living 3D space. In order to overcome the viewpoint dependency, we propose a Volume Motion Template (VMT) and Projected Motion Template (PMT). The proposed VMT method is an extension of the Motion History Image (MHI) method to 3D space. The PMT is generated by projecting the VMT into a 2D plane that is orthogonal to an optimal virtual viewpoint where the optimal virtual viewpoint is a viewpoint from which an action can be described in greatest detail, in 2D space. From the proposed method, any actions taken from different viewpoints can be recognized independent of the viewpoints. The experimental results demonstrate the accuracies and effectiveness of the proposed VMT method for view-independent human action recognition.

View-independent human action recognition with Volume Motion Template on single stereo camera

http://pr.korea.ac.kr/bbs/download.php?bo_table=sub4_1&wr_id=56&no=0

Accurate object contour tracking based on boundary edge selection

In the field of face recognition, a model learns to distinguish millions of face images with fewer dimensional embedding features, and such vast information may not be properly encoded in the conventional model with a single branch. We propose a novel face-recognition-specialized architecture called GroupFace that utilizes multiple group-aware representations, simultaneously, to improve the quality of the embedding feature. The proposed method provides self-distributed labels that balance the number of samples belonging to each group without additional human annotations, and learns the group-aware representations that can narrow down the search space of the target identity. We prove the effectiveness of the proposed method by showing extensive ablation studies and visualizations. All the components of the proposed method can be trained in an end-to-end manner with a marginal increase of computational complexity. Finally, the proposed method achieves the state-of-the-art results with significant improvements in 1:1 face verification and 1:N face identification tasks on the following public datasets: LFW, YTF, CALFW, CPLFW, CFP, AgeDB-30, MegaFace, IJB-B and IJB-C.

/pdf/groupface-learning-latent-groups-and-constructing-group-2yzwgybzvf.pdf

GroupFace: Learning Latent Groups and Constructing Group-Based Representations for Face Recognition

Object detector with region proposal networks such as Fast/Faster R-CNN [1, 2] have shown the state-of-the art performance on several benchmarks. However, they have limited success for detecting small objects. We argue the limitation is related to insufficient performance of Fast R-CNN block in Faster R-CNN. In this paper, we propose a refining block for Fast R-CNN. We further merge the block and Faster R-CNN into a single network (RF-RCNN). The RF-RCNN was applied on plate and human detection in RoadView image that consists of high resolution street images (over 30M pixels). As a result, the RF-RCNN showed great improvement over the Faster-RCNN.

Myung-Cheol Roh

Papers

A High-Security EEG-Based Login System with RSVP Stimuli and Dry Electrodes

View-independent human action recognition with Volume Motion Template on single stereo camera

Accurate object contour tracking based on boundary edge selection

GroupFace: Learning Latent Groups and Constructing Group-Based Representations for Face Recognition

Refining faster-RCNN for accurate object detection