Joint Detection and Identification Feature Learning for Person Search

Xiao, Tong; Li, Shuang; Wang, Bochao; Li, Lin; Wang, Xiaogang

doi:10.1109/cvpr.2017.360

Cited by 836 publications

(843 citation statements)

References 48 publications

Supporting

Mentioning

838

Contrasting

Unclassified

Order By: Relevance

“…To improve the performance of re-identification network, we use the multiple loss and the more suitable features to train re-identification network. Finally, our proposed FMT-CNN achieves 77.15% mAP, 79.83% top-1 accuracy and 90.90% top-5 accuracy on CUHK-SYSU [3], which shows that FMT-CNN can outperform stateof-the-arts in both mAP and top-1 evaluation protocols. Our works can be summarized as the following three aspects.…”

mentioning

confidence: 77%

See 1 more Smart Citation

FMT: fusing multi-task convolutional neural network for person search

Zhai

Liu

Wang

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

Person search is to detect all persons and identify the query persons from detected persons in the image without proposals and bounding boxes, which is different from person re-identification. In this paper, we propose a fusing multi-task convolutional neural network(FMT-CNN) to tackle the correlation and heterogeneity of detection and re-identification with a single convolutional neural network. We focus on how the interplay of person detection and person re-identification affects the overall performance. We employ person labels in region proposal network to produce features for person reidentification and person detection network, which can improve the accuracy of detection and re-identification simultaneously. We also use a multiple loss to train our re-identification network. Experiment results on CUHK-SYSU Person Search dataset show that the performance of our proposed method is superior to state-of-the-art approaches in both mAP and top-1.Keywords Person search · heterogeneous task · multiple loss · region proposal network · person labels 1 IntroductionPerson search combines person detection and person re-identification, which detects all candidate persons in an image and then compares all possible pairs of the query persons to identify the target persons, which is different from person re-identification. It is a challenging and fast-growing field. It has many important applications in video surveillance and multimedia, such as pedestrian retrieval[1] and cross-camera visual tracking [2]. The recent work [3] proposed an end-to-end person search model based on a single convolutional neural network, which adopts proposed Online Instance Matching (OIM) loss function to

show abstract

mentioning

confidence: 77%

“…it has been successfully used to perform the tasks, such as person re-identification, face alignment. The recent work [3] introduced the multi-task learning into person search by combining the person detection and person re-identification. However, it only considers re-identification as expansion of detection task.…”

mentioning

confidence: 99%

FMT: fusing multi-task convolutional neural network for person search

Zhai

Liu

Wang

et al. 2019

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Setting MARS DukeMTMC-VideoReID rank-1 rank-5 rank-10 mAP rank-1 rank-5 rank-10 mAP OIM [33] Unsupervised 33. Table 2.…”

Section: Methodsmentioning

confidence: 99%

“…Following [33,32,14], we adopt the classification model with a non-parametric classifier, where a lookup table is used to store the features of all training images. The stored feature of each image is then used as the weight vector of each class.…”

Section: Baseline: Initialization With Hard Labelsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Person Re-identification via Cross-Camera Similarity Exploration

Lin

Yan

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Person re-identification (re-ID) is an important topic in computer vision. This paper studies the unsupervised setting of re-ID, which does not require any labeled information and thus is freely deployed to new scenarios. There are very few studies under this setting, and one of the best approach till now used iterative clustering and classification, so that unlabeled images are clustered into pseudo classes for a classifier to get trained, and the updated features are used for clustering and so on. This approach suffers two problems, namely, the difficulty of determining the number of clusters, and the hard quantization loss in clustering. In this paper, we follow the iterative training mechanism but discard clustering, since it incurs loss from hard quantization, yet its only product, image-level similarity, can be easily replaced by pairwise computation and a softened classification task. With these improvements, our approach becomes more elegant and is more robust to hyperparameter changes. Experiments on two image-based and video-based datasets demonstrate state-of-the-art performance under the unsupervised re-ID setting.

show abstract

Topology and channel affinity reinforced global attention for person re‐identification

Wang

Gao

Xin

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Person re‐identification (re‐id), with the goal to recognize persons from images captured by nonoverlapping cameras, is a challenging topic in computer vision. It has been studied extensively in recent years, and the attention mechanism is widely applied in person re‐id. But many works mainly focus on extracting discriminative features from local saliency regions, while ignoring some potentially global information between whole‐body features and body‐part features. In this study, we first proposed two effective global information for extracting discriminative features: spatial topology information (STI) and channel affinity information (CAI). On this basis, we further propose a Multi‐information Fusion reinforced Global Attention (MIFGA) module which can effectively fuse a variety of information and utilize more comprehensive information to guide the learning of attention, so as to obtain pedestrian features that are conducive to clustering. Specifically, the proposed MIFGA module includes spatial attention (MIFGA‐S) and channel attention (MIFGA‐C). MIFGA‐S mainly utilizes local feature semantic information and STI to guide the learning of spatial attention. Furthermore, to mine the potential topology information in original feature maps, the self‐learning graph convolution network is proposed. MIFGA‐C fuses channel semantic information and CAI to guide the learning of channel attention. Extensive ablation studies demonstrate that our proposed MIFGA significantly enhances the baseline model and achieves a competitive performance compared with the state‐of‐the‐art person re‐id methods on standard data sets Market‐1501, DukeMTMC‐reID, and CUHK03.

show abstract

Joint Detection and Identification Feature Learning for Person Search

Cited by 836 publications

References 48 publications

FMT: fusing multi-task convolutional neural network for person search

FMT: fusing multi-task convolutional neural network for person search

Unsupervised Person Re-identification via Cross-Camera Similarity Exploration

Topology and channel affinity reinforced global attention for person re‐identification

Contact Info

Product

Resources

About