Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies lack spatial and temporal cues, which makes difficult to deal with large variations lighting conditions, viewing angles, body poses occlusions. Recently, several deep learning based person approaches have proposed achieved remarkable performance. However, most those extract discriminative features from whole frame at one...

Visible-infrared person re-identification (VI-ReID) is a cross-modality retrieval problem, which aims at matching the same pedestrian between visible and infrared cameras. Due to existence of pose variation, occlusion, huge visual differences two modalities, previous studies mainly focus on learning image-level shared features. Since they usually learn global representation or extract uniformly divided part features, these methods are sensitive misalignments. In this paper, we propose...

We investigate the problem of person search in wild this work. Instead comparing query against all candidate regions generated a query-blind manner, we propose to recursively shrink area from whole image till achieving precise localization target person, by fully exploiting information and contextual cues every recursive step. develop Neural Person Search Machines (NPSM) implement such for search. Benefiting its neural mechanism, NPSM is able selectively focus loose region tighter one...

Video-based person re-identification plays a central role in realistic security and video surveillance. In this paper, we propose novel accumulative motion context (AMOC) network for addressing important problem, which effectively exploits the long-range robustly identifying same under challenging conditions. Given sequence of or different persons, proposed AMOC jointly learns appearance representation from collection adjacent frames using two-stream convolutional architecture. Then,...

In this paper, a novel unsupervised hashing algorithm, referred to as t-USMVH, and its extension deep hashing, t-UDH, are proposed support large-scale video-to-video retrieval. To improve robustness of the learning, t-USMVH combines multiple types feature representations effectively fuses them by examining continuous relevance score based on Gaussian estimation over pairwise distances, also discrete neighbor cardinality reciprocal neighbors. reduce sensitivity scale changes for mapping...

Video-based person re-identification (ReID) matches the same people across video sequences with rich spatial and temporal information in complex scenes. It is highly challenging to capture discriminative when occlusions pose variations exist between frames. A key solution this problem rests on extracting invariant features of sequences. In paper, we propose a novel method for discovering coherence by designing region-level saliency granularity mining network (SGMN). Firstly, address varying...

There are more than 66 million people suffering from hearing impairment and this disability brings them difficulty in video content understanding due to the loss of audio information. If scripts available, captioning technology can help a certain degree by synchronously illustrating during playing videos. However, we show that existing techniques far satisfactory assisting hearing-impaired audience enjoy In article, introduce scheme enhance accessibility using Dynamic Captioning approach,...

In spread spectrum (SS) based robust audio watermarking, the scaling parameter is an important factor for balancing between robustness and imperceptibility. There have been intense studies of embedded optimization in light signal-to-noise ratio (SNR), but little attention has given to constrained SNR. Moreover, traditional population-based stochastic search algorithms optimizing significantly increase computation pressure corresponding watermarking schemes. This paper comprehensively...

Video encryption is becoming increasingly important as multimedia applications gain more and popularity. With a focus on the widely-used H.264 video coding standard, various algorithms based intra prediction mode have been developed while suffering limited scrambling space inadequate security. In this paper, existing are first analyzed with respect to perception performance, plaintext key An algorithm then proposed by taking into account distribution synchronization, leading improved effect....

In software testing, optimal testing resource allocation problems (OTRAPs) are important when seeking a good tradeoff between reliability, cost, and time with limited resources. There have been intensive studies of OTRAPs using multiobjective evolutionary algorithms (MOEAs), but little attention has paid to the constraint handling. This paper comprehensively investigates effect handling on performance nondominated sorting genetic algorithm II (NSGA-II) for solving OTRAPs, from both...

Person attribute recognition aims to identify the labels from pedestrian images. Extracting contextual relation images and attributes, including spatial-semantic relations, spatial context semantic correlation, is beneficial enhance discrimination of features for recognizing attributes. Thus, this work proposes a sequence learning (SCRL) method capture these relations. It first embeds attributes into sequences in two branches. Then SCRL flexibly learns with parallel attention model...

Furniture style describes the discriminative appearance characteristics of furniture. It plays an important role in real-world indoor decoration. In this article, we explore furniture features and study problem classification. Differing from traditional object classification, classification aims at classifying different terms “style” that its (e.g., American style, Gothic Rococo etc.) rather than “kind” is more related to functional structure bed, desk, etc.). To pursue efficient features,...

Robust anatomical correspondence detection is a key step in many medical image applications such as registration and motion correction. In the computer vision field, graph matching techniques have emerged powerful approach for detection. By considering potential correspondences nodes, edges can be used to measure pairwise agreement between possible correspondences. this paper, we present novel, hierarchical method with sparsity constraint further augment power of conventional methods...

Person re-identification across disjoint camera views plays a significant role in video surveillance. Several margin-based metric learning algorithms have recently been proposed to learn an optimal metric, with the goal that samples of same person always belong class while those from different classes are separated by large margin. These approaches require no modification or extension order solve problems multiple (as opposed binary) classification. However, formation margin these methods is...

We investigate the problem of person search in wild this work. Instead comparing query against all candidate regions generated a query-blind manner, we propose to recursively shrink area from whole image till achieving precise localization target person, by fully exploiting information and contextual cues every recursive step. develop Neural Person Search Machines (NPSM) implement such for search. Benefiting its neural mechanism, NPSM is able selectively focus loose region tighter one...

Existing approaches usually form the tracking task as an appearance matching procedure. However, discrimination ability of features is insufficient in these trackers, which caused by their weak feature supervision constraints and inadequate exploitation spatial contexts. To tackle this issue, article proposes a novel (AMT) method to strengthen restraints capture discriminative representations. Specifically, we first utilize triplet structural loss function, improves learning capability...