AAGCN: Adjacency-aware Graph Convolutional Network for person re-identification

Pan, Honghu; Bai, Yang; He, Zhenyu; Zhang, Chunkai

doi:10.1016/j.knosys.2021.107300

Cited by 19 publications

(5 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, GCNs [43][44][45][46] perform the local neighbourhood aggregation on graph nodes to learn node features. To this end, the spectral-based graph convolution is introduced for node aggregation.…”

Section: Graph Convolutional Networkmentioning

confidence: 99%

“…The convolutional neural networks (CNNs) [40–42] extract the image features via local aggregation of convolutional kernel. Similarly, GCNs [43–46] perform the local neighbourhood aggregation on graph nodes to learn node features. To this end, the spectral‐based graph convolution is introduced for node aggregation.…”

Section: Related Workmentioning

confidence: 99%

“…To reduce the prediction error accumulation, HRI [50] develops the attention‐based GCNs, which could evaluate the similarity between the current motion sequences and the historical motion context. For person Re‐ID, to reduce the intra‐class variance, AAGCN [51] proposes the adjacent‐aware GCN to smooth the intra‐class features. MGH [5] and STGCN [52] employ GCNs to aggregate the video features, in which the Euclidean neighbourhood is connected for network propagation.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Pose‐guided adversarial video prediction for image‐to‐video person re‐identification

He,

Chen,

Pan

2023

IET Image Processing

Self Cite

View full text Add to dashboard Cite

The image‐to‐video (I2V) person re‐identification (Re‐ID) is a cross‐modality pedestrian retrieval task, whose crux is to reduce the large modality discrepancy between images and videos. To this end, this paper proposes to predict the following video frames from a single image. Thus, the I2V person Re‐ID can be transformed to video‐to‐video (V2V) Re‐ID. Considering that predicting video frames from a single image is an ill‐posed problem, this paper proposes two strategies to improve the quality of the predicted videos. First, a pose‐guided video prediction pipeline is proposed. The given single image and pedestrian pose are encoded via image encoder and pose encoder, respectively; then, the image feature and pose feature are concatenated as the input of the video decoder. The authors minimize the difference between the predicted video and true video, and simultaneously minimize the difference between the true pose and predicted pose. Second, the conditional adversarial training strategy is employed to generate high‐quality video frames. Specifically, the discriminator takes the source image as condition and distinguishes whether the input frames are fake or true following frames of the source image. Experimental results demonstrate that the pose‐guided adversarial video prediction can effectively improve accuracy of I2V Re‐ID.

show abstract

Section: Graph Convolutional Networkmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Pose‐guided adversarial video prediction for image‐to‐video person re‐identification

He,

Chen,

Pan

2023

IET Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…For the objectives or loss functions, TriNet [1] proposed the hard triplet mining strategy on the basis of triplet loss to learn pedestrian representations; BoT [2] combined the cross entropy loss and triplet loss to train network; moreover, the center loss [18] and angular loss [19] have also been successfully applied in the V2V person ReID. For the network, early works [1] learned the global features from pedestrian images via a single CNN branch.Next, the multi-branch architecture has been adopted to learn the multi-granularity or part-level features [20], [21], [22]. Furthermore, data augmentation or generation [23], [11] could also improve the ReID accuracy, which belongs to the data-based category.…”

Section: A Visible-to-visible Person Reidmentioning

confidence: 99%

How Image Generation Helps Visible-to-Infrared Person Re-Identification?

Pan¹,

Chen²,

He³

et al. 2022

Preprint

View full text Add to dashboard Cite

Compared to visible-to-visible (V2V) person reidentification (ReID), the visible-to-infrared (V2I) person ReID task is more challenging due to the lack of sufficient training samples and the large cross-modality discrepancy. To this end, we propose Flow2Flow, a unified framework that could jointly achieve training sample expansion and cross-modality image generation for V2I person ReID. Specifically, Flow2Flow learns bijective transformations from both the visible image domain and the infrared domain to a shared isotropic Gaussian domain with an invertible visible flow-based generator and an infrared one, respectively. With Flow2Flow, we are able to generate pseudo training samples by the transformation from latent Gaussian noises to visible or infrared images, and generate cross-modality images by transformations from existing-modality images to latent Gaussian noises to missing-modality images. For the purpose of identity alignment and modality alignment of generated images, we develop adversarial training strategies to train Flow2Flow. Specifically, we design an image encoder and a modality discriminator for each modality. The image encoder encourages the generated images to be similar to real images of the same identity via identity adversarial training, and the modality discriminator makes the generated images modal-indistinguishable from real images via modality adversarial training. Experimental results on SYSU-MM01 and RegDB demonstrate that both training sample expansion and crossmodality image generation can significantly improve V2I ReID accuracy.

show abstract

“…Nowadays, intelligent video surveillance technology has been widely deployed [1,2]. Pedestrian attributes, such as age, clothing style, gender, and accessary, are important soft-biometrics in video surveillance applications, such as person re-identification [3,4,5,6], person search [7,8], human parsing [9], and pedestrian detection [10,11]. Thus, the recognition of them, called Pedestrian Attribute Recognition (PAR), has received great attention in recent years.…”

Section: Introductionmentioning

confidence: 99%

Reinforced Pedestrian Attribute Recognition with Group Optimization Reward

Zhong¹,

Hu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Pedestrian Attribute Recognition (PAR) is a challenging task in intelligent video surveillance. Two key challenges in PAR include complex alignment relations between images and attributes, and imbalanced data distribution. Existing approaches usually formulate PAR as a recognition task. Different from them, this paper addresses it as a decision-making task via a reinforcement learning framework. Specifically, PAR is formulated as a Markov decision process (MDP) by designing ingenious states, action space, reward function and state transition. To alleviate the inter-attribute imbalance problem, we apply an Attribute Grouping Strategy (AGS) by dividing all attributes into subgroups according to their region and category information. Then we employ an agent to recognize each group of attributes, which is trained with Deep Q-learning algorithm. We also propose a Group Optimization Reward (GOR) function to alleviate the intra-attribute imbalance problem. Experimental results on the three benchmark datasets of PETA, RAP and PA100K illustrate the effectiveness and competitiveness of the proposed approach and demonstrate that the application of reinforcement learning to PAR is a valuable research direction.

show abstract

AAGCN: Adjacency-aware Graph Convolutional Network for person re-identification

Cited by 19 publications

References 49 publications

Pose‐guided adversarial video prediction for image‐to‐video person re‐identification

Pose‐guided adversarial video prediction for image‐to‐video person re‐identification

How Image Generation Helps Visible-to-Infrared Person Re-Identification?

Reinforced Pedestrian Attribute Recognition with Group Optimization Reward

Contact Info

Product

Resources

About