Deep Asymmetric Pairwise Hashing

Shen, Fumin; Gao, Xin; Liu, Li; Yang, Yang; Shen, Heng Tao

doi:10.1145/3123266.3123345

Cited by 114 publications

(47 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Due to their convincing performance and high interpretability of modeling object relationships, GCNs has been widely applied in many computer vision task which needs to explore the relation of different vision instance. In terms of applications, existing works has led to considerable performance improvement by using GCNs in traditional computer vision tasks [2], for example, skeleton-based action recognition [25], [48], link prediction [45], [49], semi-supervised classification [15], hashing [22], [23], [56], person-reid [24], and multi-label image recognition [3], and etc.…”

Section: Related Workmentioning

confidence: 99%

Temporal Reasoning Graph for Activity Recognition

Zhang

Shen

et al. 2020

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Despite great success has been achieved in activity analysis, it still has many challenges. Most existing work in activity recognition pay more attention to design efficient architecture or video sampling strategy. However, due to the property of fine-grained action and long term structure in video, activity recognition is expected to reason temporal relation between video sequences. In this paper, we propose an efficient temporal reasoning graph (TRG) to simultaneously capture the appearance features and temporal relation between video sequences at multiple time scales. Specifically, we construct learnable temporal relation graphs to explore temporal relation on the multi-scale range. Additionally, to facilitate multi-scale temporal relation extraction, we design a multihead temporal adjacent matrix to represent multi-kinds of temporal relations. Eventually, a multi-head temporal relation aggregator is proposed to extract the semantic meaning of those features convolving through the graphs. Extensive experiments are performed on widely-used large-scale datasets, such as Something-Something and Charades, and the results show that our model can achieve state-of-the-art performance. Further analysis shows that temporal relation reasoning with our TRG can extract discriminative features for activity recognition.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporal Reasoning Graph for Activity Recognition

Zhang

Shen

et al. 2020

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, HashNet [5] tackles the data imbalance problem between similar and dissimilar pairs and alleviates this problem by adjusting the weights of similar pairs. To additionally accelerate the training procedure, several asymmetric deep hashing methods [41] are proposed, e.g., Asymmetric Deep Supervised Hashing (ADSH) [24], which only learns the hash function for query points to reduce the computational complexity. For deriving compact hash codes, the objective functions in hashing learning are always designed by the following three principles: i) preserving the similarity of data points in the original space, ii) distributing the codes to uniformly fulfill the code space, and iii) generating compact binary codes.…”

Section: Hashingmentioning

confidence: 99%

Searching Privately by Imperceptible Lying: A Novel Private Hashing Method with Differential Privacy

Wang

Zhang

2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

In the big data era, with the increasing amount of multi-media data, approximate nearest neighbor (ANN) search has been an important but challenging problem. As a widely applied large-scale ANN search method, hashing has made great progress, and achieved sublinear search time with low memory space. However, the advances in hashing are based on the availability of large and representative datasets, which often contain sensitive information. Typically, the privacy of this individually sensitive information is compromised. In this paper, we tackle this valuable yet challenging problem and formulate a task termed as private hashing, which takes into account both searching performance and privacy protection. Specifically, we propose a novel noise mechanism, i.e., Random Flipping, and two private hashing algorithms, i.e., PHashing and PITQ, with the refined analysis within the framework of differential privacy, since differential privacy is a well-established technique to measure the privacy leakage of an algorithm. Random Flipping targets binary scenarios and leverages the "Imperceptible Lying" idea to guarantee ϵ-differential privacy by flipping each datum of the binary matrix (noise addition). To preserve ϵ-differential privacy, PHashing perturbs and adds noise to the hash codes learned by non-private hashing algorithms using Random Flipping. However, the noise addition for privacy in PHashing will cause severe performance drops. To alleviate this problem, PITQ leverages the power of alternative learning to distribute the noise generated by Random Flipping into each iteration while preserving ϵ-differential privacy. Furthermore, to empirically evaluate our algorithms, we conduct comprehensive experiments on the image search task and demonstrate that proposed algorithms achieve equal performance compared with non-private hashing methods.

show abstract

“…Thus in this paper, we propose a novel asymmetric hashing method to address the aforementioned problem. Note that a similar work was described by Shen et al [25], named deep asymmetric pairwise hashing (DAPH). However, our study is quite distinctive from DAPH.…”

Section: Introductionmentioning

confidence: 97%

“…Despite the wide applications of the deep neural network to hashing learning, most of these networks are symmetric structures in which the similarity [24] between each pair of points are estimated by the Hamming distance between the outputs of the same hash function [25]. As described in [25], a crucial problem is that this symmetric scheme would result in the difficulty of optimizing the discrete constraint. Thus in this paper, we propose a novel asymmetric hashing method to address the aforementioned problem.…”

Section: Introductionmentioning

confidence: 99%

Dual Asymmetric Deep Hashing Learning

Zhang²,

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Due to the impressive learning power, deep learning has achieved a remarkable performance in supervised hash function learning. In this paper, we propose a novel asymmetric supervised deep hashing method to preserve the semantic structure among different categories and generate the binary codes simultaneously. Specifically, two asymmetric deep networks are constructed to reveal the similarity between each pair of images according to their semantic labels. Furthermore, since the binary codes in the Hamming space also should keep the semantic affinity existing in the original space, another asymmetric pairwise loss is introduced to capture the similarity between the binary codes and real-value features. This asymmetric loss not only improves the retrieval performance, but also contributes to a quick convergence at the training phase. By taking advantage of the two-stream deep structures and two types of asymmetric pairwise functions, an alternative algorithm is designed to efficiently optimize the deep features and highquality binary codes. Experimental results on three real-world datasets substantiate the effectiveness and superiority of our approach as compared with the state-of-the-art.

show abstract

Deep Asymmetric Pairwise Hashing

Cited by 114 publications

References 20 publications

Temporal Reasoning Graph for Activity Recognition

Temporal Reasoning Graph for Activity Recognition

Searching Privately by Imperceptible Lying: A Novel Private Hashing Method with Differential Privacy

Dual Asymmetric Deep Hashing Learning

Contact Info

Product

Resources

About