Part-Based Deep Hashing for Large-Scale Person Re-Identification

Zhu, Fuqing; Kong, Xiangwei; Zheng, Liang; Fu, Haiyan; Tian, Qi

doi:10.1109/tip.2017.2695101

Cited by 88 publications

(50 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, CNN-based features have achieved great progress on person Re-ID. Authors in [8], [9] utilized local cues by extracting multiple patches from a loosely associated image of human body parts. In addition, some attempts [10], [11] have been made to improve person Re-ID performance using person attributes.…”

Section: A Re-identification (Re-id)mentioning

confidence: 99%

Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

Qian

Jiang

Luo

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

Vehicle re-identification (Re-ID) has been attracting increasing interest in the field of computer vision due to the growing utilization of surveillance cameras in public security. However, vehicle Re-ID still suffers a similarity challenge despite the efforts made to solve this problem. This challenge involves distinguishing different instances with nearly identical appearances. In this paper, we propose a novel two-branch stripebased and attribute-aware deep convolutional neural network (SAN) to learn the efficient feature embedding for vehicle Re-ID task. The two-branch neural network, consisting of stripe-based branch and attribute-aware branches, can adaptively extract the discriminative features from the visual appearance of vehicles. A horizontal average pooling and dimension-reduced convolutional layers are inserted into the stripe-based branch to achieve partlevel features. Meanwhile, the attribute-aware branch extracts the global feature under the supervision of vehicle attribute labels to separate the similar vehicle identities with different attribute annotations. Finally, the part-level and global features are concatenated together to form the final descriptor of the input image for vehicle Re-ID. The final descriptor not only can separate vehicles with different attributes but also distinguish vehicle identities with the same attributes. The extensive experiments on both VehicleID and VeRi databases show that the proposed SAN method outperforms other state-of-the-art vehicle Re-ID approaches.

show abstract

Section: A Re-identification (Re-id)mentioning

confidence: 99%

Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

Qian

Jiang

Luo

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…These deep methods are proved to be effective for general object retrieval, where different categories have significant visual differences (e.g., CIFAR-10). Recently, deep hashing methods emerge as a promising solution for efficient person re-id [43,48]. Different from object retrieval, human bodies share similar appearance with subtle difference in some salient regions.…”

Section: Related Workmentioning

confidence: 99%

“…DRSCH is a triplet-based model and encodes the entire person image to hashing codes without considering the part-level semantics. PDH [48] integrates the part-based model into the triplet model and achieves significant improvements. However, the part partition strategy of PDH is specified based on human structure.…”

Section: Related Workmentioning

confidence: 99%

Deep Saliency Hashing for Fine-Grained Retrieval

Sheng

Yao

Sun

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In recent years, hashing methods have been proved to be effective and efficient for the large-scale Web media search. However, the existing general hashing methods have limited discriminative power for describing fine-grained objects that share similar overall appearance but have subtle difference. To solve this problem, we for the first time introduce the attention mechanism to the learning of fine-grained hashing codes. Specifically, we propose a novel deep hashing model, named deep saliency hashing (DSaH), which automatically mines salient regions and learns semanticpreserving hashing codes simultaneously. DSaH is a twostep end-to-end model consisting of an attention network and a hashing network. Our loss function contains three basic components, including the semantic loss, the saliency loss, and the quantization loss. As the core of DSaH, the saliency loss guides the attention network to mine discriminative regions from pairs of images. We conduct extensive experiments on both fine-grained and general retrieval datasets for performance evaluation. Experimental results on fine grained dataset, including Oxford Flowers-17, Stanford Dogs-120 and CUB Bird demonstrate that our DSaH performs the best for fine-grained retrieval task and beats strongest competitor (DTQ) by approximately 10% on both Stanford Dogs-120 and CUB Bird. DSaH is also comparable to several state-of-the-art hashing methods on general datasets, including CIFAR-10 and NUS-WIDE. Attention networkHashing network

show abstract

“…However, they usually suffer from the overfitting problem [4]. Recently, part-level representations have been proved to Kan be highly discriminative and achieved state-of-the-art performance [5]- [9]. Due to errors in pedestrian detection [10], [11], the location of each body part varies in normalized images, as illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification

Wang

Ding

Maybank

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Part-level representations are essential for robust person re-identification. Due to errors in pedestrian detection, there are usually severe mis-alignment problems for body parts, which degrade the quality of part representations. To handle this problem, we propose a novel model named Convolutional Deformable Part Models (CDPM). CDPM works by decoupling the complex part alignment procedure into two easier steps. First, a vertical alignment step detects each part in the vertical direction with the help of a multi-task learning model. Second, a horizontal refinement step based on self-attention suppresses the background information around each detected body part. Since the two steps are performed orthogonally and sequentially, the difficulty of part alignment is significantly reduced. In the testing stage, CDPM is able to accurately align flexible body parts without the need of any outside information. Extensive experimental results justify the effectiveness of CDPM for part alignment. Most impressively, CDPM achieves state-of-the-art performance on three large-scale datasets: Market-1501, DukeMTMC-ReID, and CUHK03.

show abstract

Part-Based Deep Hashing for Large-Scale Person Re-Identification

Cited by 88 publications

References 69 publications

Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

Stripe-based and attribute-aware network: a two-branch deep model for vehicle re-identification

Deep Saliency Hashing for Fine-Grained Retrieval

CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-Identification

Contact Info

Product

Resources

About