What-and-where to match: Deep spatially multiplicative integration networks for person re-identification

Abstract

Matching pedestrians across disjoint camera views, known as person re-identification (re-id), is a challenging problem that is of importance to visual recognition and surveillance. Most existing methods exploit local regions within spatial manipulation to perform matching in local correspondence. However, they essentially extract fixed representations from pre-divided regions for each image and perform matching based on the extracted representation subsequently. For models in this pipeline, local finer patterns that are crucial to distinguish positive pairs from negative ones cannot be captured, and thus making them underperformed. In this paper, we propose a novel deep multiplicative integration gating function, which answers the question of what-and-where to match for effective person re-id. To address what to match, our deep network emphasizes common local patterns by learning joint representations in a multiplicative way. The network comprises two Convolutional Neural Networks (CNNs) to extract convolutional activations, and generates relevant descriptors for pedestrian matching. This thus, leads to flexible representations for pair-wise images. To address where to match, we combat the spatial misalignment by performing spatially recurrent pooling via a four-directional recurrent neural network to impose spatial dependency over all positions with respect to the entire image. The proposed network is designed to be end-to-end trainable to characterize local pairwise feature interactions in a spatially aligned manner. To demonstrate the superiority of our method, extensive experiments are conducted over three benchmark data sets: VIPeR, CUHK03 and Market-1501.

PAC-GAN: An effective pose augmentation scheme for unsupervised cross-view person re-identification

“…Person Re-Id [86,61,18,15] is a hot issue in the field of visual recognition and image processing. It is a task to associate and match pedestrians across camera views at different geo-locations and times in a distributed multicameras surveillance system [18].…”

Patch-based contour prior image denoising for salt and pepper noise

“…Baseline algorithm We use four existing denoising algorithms as baselines, including adaptive median filter (AMF), decision based algorithm (DBA [6]), method based on pixel density filter(BPDF) [27], Decision based Unsymmetrical Trimmed Variants (DBUTVF) [28], Adaptive Center Weighted Median Filter(ACWMF) [32], and Patch-based Approach to Remove Impulse-Gaussian Noise(PARIGI [16]). For fair comparison, all methods' code implementations are their publicly available versions and their parameters are set following the guidelines in original articles.…”

GPU based parallel optimization for real time panoramic video stitching

“…Video surveillance is the key and pioneer for smart city construction, play a huge role. It is applied to target tracking [1], person re-identification [2][3][4], traffic management [5]. With the maturity of high-performance computing [6] and deep learning technology [7][8], and the continuous research and improvement of video processing algorithms through many scholars [9][10], video surveillance technology has developed rapidly.…”