Fine-Grained Spatial Alignment Model for Person Re-Identification With Focal Triplet Loss

Zhou, Qinqin; Zhong, Bineng; Lan, Xiangyuan; Sun, Gan; Zhang, Yulun; Zhang, Baochang; Ji, Rongrong

doi:10.1109/tip.2020.3004267

Cited by 83 publications

(31 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, deep-learning-based methods have also attracted considerable interest in the visual tracking community as robust visual trackers. According to their architectures, state-of-the-art deep-learning-based visual tracking methods are categorized as convolutional neural networks (CNNs) [26] [27] [28], Siamese neural networks (SNNs) [29] [30], recurrent neural networks (RNNs) [31] [32], generative adversarial networks (GANs) [33] [34]. Although these state-of-the-art methods have achieved significant progress, they are still not reliable for real-world applications mainly because they lack the intelligence for scene understanding [35].…”

Section: Related Work a Deep-learning-based Object Detection Andmentioning

confidence: 99%

Tracking In-Cabin Astronauts Using Deep Learning and Head Motion Clues

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

Section: Related Work a Deep-learning-based Object Detection Andmentioning

confidence: 99%

Tracking In-Cabin Astronauts Using Deep Learning and Head Motion Clues

Zhang

2021

IEEE Access

View full text Add to dashboard Cite

“…A discriminative association cost matrix is constructed using a coarse-to-fine schema with spatial, motion, and appearance information. They also proposed a fine-grained spatial alignment model [31] to effectively handle challenging scenarios such as complex poses, inaccurate detection, and occlusions arising from person re-identification or MOT. In particular, with this method, a pose resolution network is first designed using a channel parsing block to extract pose information at the pixel level.…”

Section: Related Studiesmentioning

confidence: 99%

Online Multiple Object Tracking Using Rule Distillated Siamese Random Forest

Lee

Kim

2020

IEEE Access

View full text Add to dashboard Cite

In a multiple object tracking (MOT) system, an association check between the tracker and detected objects is an important factor in determining the tracking performance. Siamese convolution neural network (CNN) is the most popular data association method in MOT owing to its good matching performance and network sharing support. However, it is unsuitable for real-time online tracking in low-end systems because numerous parameters and operations are still required. In this paper, instead of a CNN, we propose using a SiameseRF algorithm which combines Siamese structure and random forest (RF), enabling highspeed learning and classification. SiameseRF has a shared-rule based Siamese structure rather than shared weight, which improves the matching performance and solves existing slow CNN-based tracking issues. During the learning process, the shared RFs consisting of tree rules are learned in the directions of increasing similarity to the positive pair {anchor, positive} and increasing difference between the negative pair {anchor, negative}. However, because many rules that make up SiameseRF remain a burden for online processing, this study proposes an additional rule distillation algorithm to effectively remove redundant and unimportant rules causing an overfitting with SiameseRF. This reduction in the number of rules reduces the processing time and number of parameters in the rule distilled SiameseRF. In experiments conducted on MOT benchmark datasets, our proposed 30% rule distilled SiameseRF achieved up to a 1.12-times faster speed and a 1.13-times higher compression rate than basic SiameseRF while maintaining a similar or somewhat better tracking performance than other state-of-the-art CNN-based MOT algorithms.

show abstract

“…However, their performances are strongly affected by the quality of detection results. Thus, Zhou et al [44], [45] proposed the deep neural networks to revise misaligned detection results and showed that their alignment methods are useful in the tracking-by-detection framework.…”

Section: Related Work a Multiple Object Trackingmentioning

confidence: 99%

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

Kim

Koh

2020

IEEE Access

View full text Add to dashboard Cite

How to make an online tracking model effectively adapt to newly appearing objects and object disappearance as well as appearance variations of target objects from few examples is an essential issue in multiple object tracking (MOT). Learning target appearances from few examples is a few-shot classification problem, while identifications of newly appearing objects and object disappearance has the aspect of open-set classification. In this work, we regard online MOT as open-set few-show classification to address both learning from few examples (few-shot classification) and unknown classes such as new objects (open-set classification). Specifically, we develop an embedding neural network, called VOFNet, consisting of convolutional and recurrent parts, to perform open-set few-shot classification. The convolutional part constructs a feature from an example of a target object and the recurrent part determines a representative feature of a target object from few examples. Then VOFNet is trained to provide effective features for openset few-shot classification. Finally, we develop an online multiple object tracker based on the combination of VOFNet and the bipartite matching. The proposed tracker achieves 49.2 multiple object tracking accuracy (MOTA) with 28.9 frames per second on MOT17 dataset, which shows a significantly better trade-off between the accuracy and the speed than the existing algorithms. For example, the proposed algorithm yields about 3.17 times faster speed with 0.99 times lower accuracy than recent existing MOT algorithm [1]. INDEX TERMS Multiple object tracking, online tracking, open-set classification, few-shot classification.

show abstract

Fine-Grained Spatial Alignment Model for Person Re-Identification With Focal Triplet Loss

Cited by 83 publications

References 61 publications

Tracking In-Cabin Astronauts Using Deep Learning and Head Motion Clues

Tracking In-Cabin Astronauts Using Deep Learning and Head Motion Clues

Online Multiple Object Tracking Using Rule Distillated Siamese Random Forest

Online Multiple Object Tracking Based on Open-Set Few-Shot Learning

Contact Info

Product

Resources

About