SVDNet for Pedestrian Retrieval

Sun, Yifan; Zheng, Liang; Deng, Weijian; Wang, Shengjin

doi:10.1109/iccv.2017.410

Cited by 735 publications

(372 citation statements)

References 37 publications

Supporting

Mentioning

368

Contrasting

Order By: Relevance

“…4 indicates that we project the feature embeddings V a and V b into an orthogonal common space and maintain their norm of V a and V b . This property has proved valuable for eliminating the correlation between different channels (i.e., Cdimension) [50] and improving the network's generalization ability [3,48].…”

Section: Co-attention Mechanisms In Cosnetmentioning

confidence: 99%

See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

471

226

View full text Add to dashboard Cite

We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view. We emphasize the importance of inherent correlation among video frames and incorporate a global co-attention mechanism to improve further the state-of-the-art deep learning based solutions that primarily focus on learning discriminative foreground representations over appearance and motion in short-term temporal segments. The co-attention layers in our network provide efficient and competent stages for capturing global correlations and scene context by jointly computing and appending co-attention responses into a joint feature space. We train COSNet with pairs of video frames, which naturally augments training data and allows increased learning capacity. During the segmentation stage, the co-attention model encodes useful information by processing multiple reference frames together, which is leveraged to infer the frequently reappearing and salient foreground objects better. We propose a unified and end-to-end trainable framework where different co-attention variants can be derived for mining the rich context within videos. Our extensive experiments over three large benchmarks manifest that COSNet outperforms the current alternatives by a large margin.

show abstract

Section: Co-attention Mechanisms In Cosnetmentioning

confidence: 99%

See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

471

226

View full text Add to dashboard Cite

show abstract

“…Moreover, the proposed method outperforms the partbased method PAN [32] under occlusions, since we exploit the spatial dependencies based on LSTM to learn discriminative representations. Compared with SVDNet [33], the proposed method achieves higher rank-1 accuracy and mAP under small occlusions. However, the proposed method obtains slightly inferior results under large occlusions (s = 0.6) on the CUHK03 dataset.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Adaptive deep metric embeddings for person re-identification under occlusions

2019

View full text Add to dashboard Cite

Person re-identification (ReID) under occlusions is a challenging problem in video surveillance. Most of existing person ReID methods take advantage of local features to deal with occlusions. However, these methods usually independently extract features from the local regions of an image without considering the relationship among different local regions. In this paper, we propose a novel person ReID method, which learns the spatial dependencies between the local regions and extracts the discriminative feature representation of the pedestrian image based on Long Short-Term Memory (LSTM), dealing with the problem of occlusions. In particular, we propose a novel loss (termed the adaptive nearest neighbor loss) based on the classification uncertainty to effectively reduce intra-class variations while enlarging inter-class differences within the adaptive neighborhood of the sample. The proposed loss enables the deep neural network to adaptively learn discriminative metric embeddings, which significantly improve the generalization capability of recognizing unseen person identities. Extensive comparative evaluations on challenging person ReID datasets demonstrate the significantly improved performance of the proposed method compared with several state-of-the-art methods.

show abstract

“…We leverage an open-source project, SVDNet (Sun et al, 2017), for person re-identification. We choose this method because of its mesrits in computational performance and comparable accuracy as the state-of-the-art.…”

Section: Identifying the Contact Graphmentioning

confidence: 99%

Droplet-Transmitted Infection Risk Ranking Based on Close Proximity Interaction

Guo

Shi

et al. 2020

Front. Neurorobot.

View full text Add to dashboard Cite

We propose an automatic method to identify people who are potentially-infected by droplet-transmitted diseases. This high-risk group of infection was previously identified by conducting large-scale visits/interviews, or manually screening among tons of recorded surveillance videos. Both are time-intensive and most likely to delay the control of communicable diseases like influenza. In this paper, we address this challenge by solving a multi-tasking problem from the captured surveillance videos. This multi-tasking framework aims to model the principle of Close Proximity Interaction and thus infer the infection risk of individuals. The complete workflow includes three essential sub-tasks: (1) person re-identification (REID), to identify the diagnosed patient and infected individuals across different cameras, (2) depth estimation, to provide a spatial knowledge of the captured environment, (3) pose estimation, to evaluate the distance between the diagnosed and potentially-infected subjects. Our method significantly reduces the time and labor costs. We demonstrate the advantages of high accuracy and efficiency of our method. Our method is expected to be effective in accelerating the process of identifying the potentially infected group and ultimately contribute to the well-being of public health.

show abstract

SVDNet for Pedestrian Retrieval

Cited by 735 publications

References 37 publications

See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks

See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks

Adaptive deep metric embeddings for person re-identification under occlusions

Droplet-Transmitted Infection Risk Ranking Based on Close Proximity Interaction

Contact Info

Product

Resources

About