Person Re-identification via Recurrent Feature Aggregation

Yan, Yichao; Ni, Bingbing; Song, Zhichao; Ma, Chao; Yan, Yan; Yang, Xiaokang

doi:10.1007/978-3-319-46466-4_42

Cited by 177 publications

(156 citation statements)

References 35 publications

Supporting

Mentioning

156

Contrasting

Order By: Relevance

“…To validate the effectiveness of our proposed method, we compare our proposed method with several state-ofthe-art methods on PRID2011, iLIDS-VID, MARS, and DukeMTMC-VideoReID, include RCN [2], IDE+XQDA [55], RFA-Net [33], SeeForest [3], QAN [5], AMOC+EF [60], ASTPN [4], Snippet [7], STAN [6], EUG [57], SDM [21], RQEN [19], PersonVLAD [10], M3D [14], STMP [13], STA [15], TRL+XQDA [9], SCAN [11], STAL [12], and STE-NVAN [16].…”

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

confidence: 99%

“…Person Re-ID in still images is widely explored [22]- [32]. Currently, the researchers start to focus on video-based person Re-ID [2], [33]. Facilitated by deep learning technique, impressive progress has been observed with video person Re-ID recently.…”

Section: Related Workmentioning

confidence: 99%

“…Facilitated by deep learning technique, impressive progress has been observed with video person Re-ID recently. McLaughlin et al [2] and Yan et al [33] employ RNN to model the inter-sequence dependency and aggregate the features extracted from the video frames with average pooling or max pooling. Zhou et al [3] separately model the spatial and temporal coherence with two RNN networks: the temporal model (TAM) focuses on discriminative frames and spatial model (SRM) integrates the contexture at different locations for better similarity evaluation.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Wang

Yin

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Recent years have witnessed a great development of deep learning based video person re-identification (Re-ID).A key factor for video person Re-ID is how to effectively construct discriminative video feature representations for the robustness to many complicated situations like occlusions. Recent part-based approaches employ spatial and temporal attention to extract the representative local features. While the correlations between the parts are ignored in the previous methods, to leverage the relations of different parts, we propose an innovative adaptive graph representation learning scheme for video person Re-ID, which enables the contextual interactions between the relevant regional features. Specifically, we exploit pose alignment connection and feature affinity connection to construct an adaptive structure-aware adjacency graph, which models the intrinsic relations between graph nodes. We perform feature propagation on the adjacency graph to refine the original regional features iteratively, the neighbor nodes information is taken into account for part feature representation. To learn the compact and discriminative representations, we further propose a novel temporal resolution-aware regularization, which enforces the consistency among different temporal resolutions for the same identities. We conduct extensive evaluations on four benchmarks, i.e. iLIDS-VID, PRID2011, MARS, and DukeMTMC-VideoReID, the experimental results achieve the competitive performance which demonstrates the effectiveness of our proposed method.

show abstract

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

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Wang

Yin

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Taking this intuition into account, in [33], the authors propose a LSTM-based architecture to process image regions sequentially and enhance the discriminative capability of local feature representation by leveraging contextual information. Following the same pipeline, the authors in [34] proposed a sequential fusion framework that combines the frame-wise appearance information as well as temporal information to generate a robust sequence-level human representation. Nevertheless, similar to many other deep architectures, generating a huge amount of labeled training data is an issue that needs to be addressed carefully.…”

Section: Related Workmentioning

confidence: 99%

“…There has also been a growing number of methods that apply deep-learning methods [28][29][30][31][32][33][34] for person ReID in recent years.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Multiple Detections for Person Re-Identification

2018

View full text Add to dashboard Cite

Re-identification systems aim at recognizing the same individuals in multiple cameras, and one of the most relevant problems is that the appearance of same individual varies across cameras due to illumination and viewpoint changes. This paper proposes the use of cumulative weighted brightness transfer functions (CWBTFs) to model these appearance variations. Different from recently proposed methods which only consider pairs of images to learn a brightness transfer function, we exploit such a multiple-frame-based learning approach that leverages consecutive detections of each individual to transfer the appearance. We first present a CWBTF framework for the task of transforming appearance from one camera to another. We then present a re-identification framework where we segment the pedestrian images into meaningful parts and extract features from such parts, as well as from the whole body. Jointly, both of these frameworks contribute to model the appearance variations more robustly. We tested our approach on standard multi-camera surveillance datasets, showing consistent and significant improvements over existing methods on three different datasets without any other additional cost. Our approach is general and can be applied to any appearance-based method.

show abstract

Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification

Karianakis

Liu

Chen

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

We address the problem of person re-identification from commodity depth sensors. One challenge for depth-based recognition is data scarcity. Our first contribution addresses this problem by introducing split-rate RGB-to-Depth transfer, which leverages large RGB datasets more effectively than popular fine-tuning approaches. Our transfer scheme is based on the observation that the model parameters at the bottom layers of a deep convolutional neural network can be directly shared between RGB and depth data while the remaining layers need to be fine-tuned rapidly. Our second contribution enhances re-identification for video by implementing temporal attention as a Bernoulli-Sigmoid unit acting upon frame-level features. Since this unit is stochastic, the temporal attention parameters are trained using reinforcement learning. Extensive experiments validate the accuracy of our method in person re-identification from depth sequences. Finally, in a scenario where subjects wear unseen clothes, we show large performance gains compared to a state-of-the-art model which relies on RGB data.

show abstract

Person Re-identification via Recurrent Feature Aggregation

Cited by 177 publications

References 35 publications

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Few-Shot Deep Adversarial Learning for Video-Based Person Re-Identification

Exploiting Multiple Detections for Person Re-Identification

Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-identification

Contact Info

Product

Resources

About