Multi-Shot Human Re-Identification Using Adaptive Fisher Discriminant Analysis

Li, Yang; Wu, Ziyan; Karanam, Srikrishna; Radke, Richard J.

doi:10.5244/c.29.73

Cited by 42 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, we also conduct experiments on three small video re-ID datasets. On these datasets, we compare with twenty state-of-the-art methods, including VR [48], DVR [52], DVDL [65], STFV3D [49], AFDA [51], LFDA [17], STFV3D+KISSME [66], PaMM [55], TDL [54], SIIDL [53], RFA [38], RNN [31], RNN+OF [31], RCN+KISSME [32], CNN+BRNN [37], ASTPN [35], CNN+XQDA [33], CNN+SRM+TAM [34], CAR [36] and QAN [39]. Among the compared approaches, the first ten approaches use hand-crafted features and the left are deep learning based models.…”

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

confidence: 99%

See 1 more Smart Citation

Video Person Re-Identification by Temporal Residual Learning

Zhang

Wang

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we propose a novel feature learning framework for video person re-identification (re-ID). The proposed framework largely aims to exploit the adequate temporal information of video sequences and tackle the poor spatial alignment of moving pedestrians. More specifically, for exploiting the temporal information, we design a temporal residual learning (TRL) module to simultaneously extract the generic and specific features of consecutive frames. The TRL module is equipped with two bi-directional LSTM (BiLSTM), which are respectively responsible to describe a moving person in different aspects, providing complementary information for better feature representations. To deal with the poor spatial alignment in video re-ID datasets, we propose a spatial-temporal transformer network (ST 2 N) module. Transformation parameters in the ST 2 N module are learned by leveraging the high-level semantic information of the current frame as well as the temporal context knowledge from other frames. The proposed ST 2 N module with less learnable parameters allows effective person alignments under significant appearance changes. Extensive experimental results on the largescale MARS, PRID2011, ILIDS-VID and SDU-VID datasets demonstrate that the proposed method achieves consistently superior performance and outperforms most of the very recent state-of-the-art methods.

show abstract

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

confidence: 99%

“…In recent years, video based re-ID has drawn increasing attention due to its numerous applications. Existing video re-ID methods can be roughly categorized into two classes: hand-crafted feature based methods [49], [51]- [56] and deep learning based methods [31]- [36].…”

Section: Related Workmentioning

confidence: 99%

Video Person Re-Identification by Temporal Residual Learning

Zhang

Wang

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Similarly, Liu et al [28] proposed a video-based pedestrian re-identification method based on the proposed spatiotemporal body-action model. Li et al [7] also proposed a multi-shot person reidentification method based on iterative appearance clustering and subspace learning for effective multi-shot matching. In addition, a multi-shot matching person re-identification using deep recurrent neural network (RNN) [29] was recently proposed.…”

Section: B Multi-shot Matching Methodsmentioning

confidence: 99%

“…However, it is difficult to identify people with singleshot appearance matching because of the people's aforementioned severe appearance changes. Several multi-shot matching Yeong methods [1], [6], [7] have been proposed in recent years to overcome the limitation of single-shot matching; however, the ambiguities that arise due to the viewpoint and pose variations remain.…”

Section: Introductionmentioning

confidence: 99%

PaMM: Pose-Aware Multi-Shot Matching for Improving Person Re-Identification

Cho

Yoon

2018

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views. Although a significant progress has been made in person re-identification over the last decade, it remains a challenging task because the appearances of people can seem extremely different across diverse camera viewpoints and person poses. In this paper, we propose a novel framework for person re-identification by analyzing camera viewpoints and person poses called pose-aware multi-shot matching. It robustly estimates individual poses and efficiently performs multi-shot matching based on the pose information. The experimental results obtained by using public person re-identification data sets show that the proposed methods outperform the current state-of-the-art methods, and are promising for accomplishing person re-identification under diverse viewpoints and pose variances.

show abstract

“…Since the primary focus of this paper is on image-based person re-id, we employ the simplest feature fusion scheme for video re-id: Given a video sequence, we compute features of each frame which are aggregated by max-pooling to form video level representation. In contrast, most of the state-ofthe-art video-based re-id methods [40,37,52,23,30,22] utilized the RNN models such as LSTM to perform temporal/sequence video feature fusion from each frame. Experimental settings.…”

Section: Datasets and Settingsmentioning

confidence: 99%

Multi-scale Deep Learning Architectures for Person Re-identification

Qian

Jiang

et al. 2017

2017 IEEE International Conference on Computer Vision (ICCV)

247

136

View full text Add to dashboard Cite

Person Re-identification (re-id) aims to match people across non-overlapping camera views in a public space. It is a challenging problem because many people captured in surveillance videos wear similar clothes. Consequently, the differences in their appearance are often subtle and only detectable at the right location and scales. Existing re-id models, particularly the recently proposed deep learning based ones match people at a single scale. In contrast, in this paper, a novel multi-scale deep learning model is proposed. Our model is able to learn deep discriminative feature representations at different scales and automatically determine the most suitable scales for matching. The importance of different spatial locations for extracting discriminative features is also learned explicitly. Experiments are carried out to demonstrate that the proposed model outperforms the state-of-the art on a number of benchmarks.

show abstract

Multi-Shot Human Re-Identification Using Adaptive Fisher Discriminant Analysis

Cited by 42 publications

References 8 publications

Video Person Re-Identification by Temporal Residual Learning

Video Person Re-Identification by Temporal Residual Learning

PaMM: Pose-Aware Multi-Shot Matching for Improving Person Re-Identification

Multi-scale Deep Learning Architectures for Person Re-identification

Contact Info

Product

Resources

About