With the emergence of various online platforms, associating different platforms is playing an increasingly important role in many applications. Cross-platform recommendation aims to improve recommendation accuracy through associating information from different platforms. Existing methods do not fully exploit high-order nonlinear connectivity information in cross-domain recommendation scenario and suffer from domain-incompatibility problem. In this paper, we propose an end-to-end convolution and fusion model for cross-platform recommendation (CFCR). The proposed CFCR model utilizes Graph Convolution Networks (GCN) to extract user and item features on graphs from different platforms, and fuses cross-platform information by Multimodal AutoEncoder (MAE) with common latent user features. Therefore, the high-order connectivity information is preserved to the most extent and domain-invariant user representations are automatically obtained. The domain-incompatible information is spontaneously discarded to avoid messing up the cross-platform association. Extensive experiments for the proposed CFCR model on real-world dataset demonstrate its advantages over existing cross-platform recommendation methods in terms of various evaluation metrics.
{"title":"CFCR: A Convolution and Fusion Model for Cross-platform Recommendation","authors":"Shengze Yu, Xin Wang, Wenwu Zhu","doi":"10.1145/3469877.3495639","DOIUrl":"https://doi.org/10.1145/3469877.3495639","url":null,"abstract":"With the emergence of various online platforms, associating different platforms is playing an increasingly important role in many applications. Cross-platform recommendation aims to improve recommendation accuracy through associating information from different platforms. Existing methods do not fully exploit high-order nonlinear connectivity information in cross-domain recommendation scenario and suffer from domain-incompatibility problem. In this paper, we propose an end-to-end convolution and fusion model for cross-platform recommendation (CFCR). The proposed CFCR model utilizes Graph Convolution Networks (GCN) to extract user and item features on graphs from different platforms, and fuses cross-platform information by Multimodal AutoEncoder (MAE) with common latent user features. Therefore, the high-order connectivity information is preserved to the most extent and domain-invariant user representations are automatically obtained. The domain-incompatible information is spontaneously discarded to avoid messing up the cross-platform association. Extensive experiments for the proposed CFCR model on real-world dataset demonstrate its advantages over existing cross-platform recommendation methods in terms of various evaluation metrics.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125183782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhichao Fu, Tianlong Ma, Liang Xue, Yingbin Zheng, Hao Ye, Liang He
We perform fast single image super-resolution with flexible magnification for natural images. A novel coarse-to-fine super-resolution framework is developed for the magnification that is factorized into a maximum integer component and the quotient. Specifically, our framework is embedded with a light-weight upscale network for super-resolution with the integer scale factor, followed by the fine-grained network to guide interpolation on feature maps as well as to generate the super-resolved image. Compared with the previous flexible magnification super-resolution approaches, the proposed framework achieves a tradeoff between computational complexity and performance. We conduct experiments using the coarse-to-fine framework on the standard benchmarks and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches.
{"title":"A Coarse-to-fine Approach for Fast Super-Resolution with Flexible Magnification","authors":"Zhichao Fu, Tianlong Ma, Liang Xue, Yingbin Zheng, Hao Ye, Liang He","doi":"10.1145/3469877.3490564","DOIUrl":"https://doi.org/10.1145/3469877.3490564","url":null,"abstract":"We perform fast single image super-resolution with flexible magnification for natural images. A novel coarse-to-fine super-resolution framework is developed for the magnification that is factorized into a maximum integer component and the quotient. Specifically, our framework is embedded with a light-weight upscale network for super-resolution with the integer scale factor, followed by the fine-grained network to guide interpolation on feature maps as well as to generate the super-resolved image. Compared with the previous flexible magnification super-resolution approaches, the proposed framework achieves a tradeoff between computational complexity and performance. We conduct experiments using the coarse-to-fine framework on the standard benchmarks and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126495930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Existing methods often utilize temporal motion information and spatial layout information in video to predict video saliency. However, the fixations are not always consistent with the moving object of interest, because human eye fixations are determined not only by the spatio-temporal information, but also by the velocity of eye movement. To address this issue, a new saliency prediction method via deep eye movement learning (EML) is proposed in this paper. Compared with previous methods that use human fixations as ground truth, our method uses the optical flow of fixations between successive frames as an extra ground truth for the purpose of eye movement learning. Experimental results on DHF1K, Hollywood2, and UCF-sports datasets show the proposed EML model achieves a promising result across a wide of metrics.
{"title":"Video Saliency Prediction via Deep Eye Movement Learning","authors":"Jiazhong Chen, Jing Chen, Yuan Dong, Dakai Ren, Shiqi Zhang, Zongyi Li","doi":"10.1145/3469877.3490597","DOIUrl":"https://doi.org/10.1145/3469877.3490597","url":null,"abstract":"Existing methods often utilize temporal motion information and spatial layout information in video to predict video saliency. However, the fixations are not always consistent with the moving object of interest, because human eye fixations are determined not only by the spatio-temporal information, but also by the velocity of eye movement. To address this issue, a new saliency prediction method via deep eye movement learning (EML) is proposed in this paper. Compared with previous methods that use human fixations as ground truth, our method uses the optical flow of fixations between successive frames as an extra ground truth for the purpose of eye movement learning. Experimental results on DHF1K, Hollywood2, and UCF-sports datasets show the proposed EML model achieves a promising result across a wide of metrics.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131425318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hierarchical graph pooling has shown great potential for capturing high-quality graph representations through the node cluster selection mechanism. However, the current node cluster selection methods have inadequate clustering issues, and their scoring methods rely too much on the node representation, resulting in excessive graph structure information loss during pooling. In this paper, a local capsule pooling network (LCPN) is proposed to alleviate the above issues. Specifically, (i) a local capsule pooling (LCP) is proposed to alleviate the issue of insufficient clustering; (ii) a task-aware readout (TAR) mechanism is proposed to obtain a more expressive graph representation; (iii) a pooling information loss (PIL) term is proposed to further alleviate the information loss caused by pooling during training. Experimental results on the graph classification task, the graph reconstruction task, and the pooled graph adjacency visualization task show the superior performance of the proposed LCPN and demonstrate its effectiveness and efficiency.
{"title":"Hierarchical Graph Representation Learning with Local Capsule Pooling","authors":"Zidong Su, Zehui Hu, Yangding Li","doi":"10.1145/3469877.3495645","DOIUrl":"https://doi.org/10.1145/3469877.3495645","url":null,"abstract":"Hierarchical graph pooling has shown great potential for capturing high-quality graph representations through the node cluster selection mechanism. However, the current node cluster selection methods have inadequate clustering issues, and their scoring methods rely too much on the node representation, resulting in excessive graph structure information loss during pooling. In this paper, a local capsule pooling network (LCPN) is proposed to alleviate the above issues. Specifically, (i) a local capsule pooling (LCP) is proposed to alleviate the issue of insufficient clustering; (ii) a task-aware readout (TAR) mechanism is proposed to obtain a more expressive graph representation; (iii) a pooling information loss (PIL) term is proposed to further alleviate the information loss caused by pooling during training. Experimental results on the graph classification task, the graph reconstruction task, and the pooled graph adjacency visualization task show the superior performance of the proposed LCPN and demonstrate its effectiveness and efficiency.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131041741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Age estimation from a single facial image is a challenging and attractive research area in the computer vision community. Several facial datasets annotated with age and gender attributes became available in the literature. However, one major drawback is that these datasets do not consider the label distribution during data collection. Therefore, the models training on these datasets inevitably have bias for the age having least number of images. In this work, we analyze the age and gender distribution of previous datasets and publish an Uniform Age and Gender Dataset (UAGD) which has almost equal number of female and male images in each age. In addition, we investigate the impact of age and gender distribution on age estimation by comparing DEX CNN model trained on several different datasets. Our experiments show that UAGD dataset has good performance for age estimation task and also it is suitable for being an evaluation benchmark.
{"title":"A comparison study: the impact of age and gender distribution on age estimation","authors":"Chang Kong, Qiuming Luo, Guoliang Chen","doi":"10.1145/3469877.3490576","DOIUrl":"https://doi.org/10.1145/3469877.3490576","url":null,"abstract":"Age estimation from a single facial image is a challenging and attractive research area in the computer vision community. Several facial datasets annotated with age and gender attributes became available in the literature. However, one major drawback is that these datasets do not consider the label distribution during data collection. Therefore, the models training on these datasets inevitably have bias for the age having least number of images. In this work, we analyze the age and gender distribution of previous datasets and publish an Uniform Age and Gender Dataset (UAGD) which has almost equal number of female and male images in each age. In addition, we investigate the impact of age and gender distribution on age estimation by comparing DEX CNN model trained on several different datasets. Our experiments show that UAGD dataset has good performance for age estimation task and also it is suitable for being an evaluation benchmark.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132652394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Composed query image retrieval is a growing research topic. The object is to retrieve images not only generally resemble the reference image, but differ according to the desired modification text. Existing methods mainly explore composing modification text with global feature or local entity descriptor of reference image. However, they ignore the fact that modification text is indeed diverse and arbitrary. It not only relates to abstractive global feature or concrete local entity transformation, but also often associates with the fine-grained structured visual adjustment. Thus, it is insufficient to emphasize the global or local entity visual for the query composition. In this work, we tackle this task by hierarchical composition learning. Specifically, the proposed method first encodes images into three representations consisting of global, entity and structure level representations. Structure level representation is richly explicable, which explicitly describes entities as well as attributes and relationships in the image with a directed graph. Based on these, we naturally perform hierarchical composition learning by fusing modification text and reference image in the global-entity-structure manner. It can transform the visual feature conditioned on modification text to target image in a coarse-to-fine manner, which takes advantage of the complementary information among three levels. Moreover, we introduce a hybrid space matching to explore global, entity and structure alignments which can get high performance and good interpretability.
{"title":"Hierarchical Composition Learning for Composed Query Image Retrieval","authors":"Yahui Xu, Yi Bin, Guoqing Wang, Yang Yang","doi":"10.1145/3469877.3490601","DOIUrl":"https://doi.org/10.1145/3469877.3490601","url":null,"abstract":"Composed query image retrieval is a growing research topic. The object is to retrieve images not only generally resemble the reference image, but differ according to the desired modification text. Existing methods mainly explore composing modification text with global feature or local entity descriptor of reference image. However, they ignore the fact that modification text is indeed diverse and arbitrary. It not only relates to abstractive global feature or concrete local entity transformation, but also often associates with the fine-grained structured visual adjustment. Thus, it is insufficient to emphasize the global or local entity visual for the query composition. In this work, we tackle this task by hierarchical composition learning. Specifically, the proposed method first encodes images into three representations consisting of global, entity and structure level representations. Structure level representation is richly explicable, which explicitly describes entities as well as attributes and relationships in the image with a directed graph. Based on these, we naturally perform hierarchical composition learning by fusing modification text and reference image in the global-entity-structure manner. It can transform the visual feature conditioned on modification text to target image in a coarse-to-fine manner, which takes advantage of the complementary information among three levels. Moreover, we introduce a hybrid space matching to explore global, entity and structure alignments which can get high performance and good interpretability.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134281777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Unsupervised object re-identification is a challenging task due to the missing of labels for the dataset. Many unsupervised object re-identification approaches combine clustering-based pseudo-label prediction with feature fine-tuning. These methods have achieved great success in the field of unsupervised object Re-ID. However, the inevitable label noise caused by the clustering procedure was ignored. Such noisy pseudo labels substantially hinder the model’s capability on further improving feature representations. To this end, we propose a novel joint label refinement and contrastive learning framework with hybrid memory to alleviate this problem. Firstly, in order to reduce the noise of clustering pseudo labels, we propose a novel noise refinement strategy. This strategy refines pseudo labels at clustering phase and promotes clustering quality by boosting the label purity. In addition, we propose a hybrid memory bank. The hybrid memory dynamically generates prototype-level and un-clustered instance-level supervisory signals for learning feature representations. With all prototype-level and un-clustered instance-level supervisions, re-identification model is trained progressively. Our proposed unsupervised object Re-ID framework significantly reduces the influence of noisy labels and refines the learned features. Our method consistently achieves state-of-the-art performance on benchmark datasets.
{"title":"Joint label refinement and contrastive learning with hybrid memory for Unsupervised Marine Object Re-Identification","authors":"Xiaorui Han, Zhiqi Chen, Ruixue Wang, Pengfei Zhao","doi":"10.1145/3469877.3497695","DOIUrl":"https://doi.org/10.1145/3469877.3497695","url":null,"abstract":"Unsupervised object re-identification is a challenging task due to the missing of labels for the dataset. Many unsupervised object re-identification approaches combine clustering-based pseudo-label prediction with feature fine-tuning. These methods have achieved great success in the field of unsupervised object Re-ID. However, the inevitable label noise caused by the clustering procedure was ignored. Such noisy pseudo labels substantially hinder the model’s capability on further improving feature representations. To this end, we propose a novel joint label refinement and contrastive learning framework with hybrid memory to alleviate this problem. Firstly, in order to reduce the noise of clustering pseudo labels, we propose a novel noise refinement strategy. This strategy refines pseudo labels at clustering phase and promotes clustering quality by boosting the label purity. In addition, we propose a hybrid memory bank. The hybrid memory dynamically generates prototype-level and un-clustered instance-level supervisory signals for learning feature representations. With all prototype-level and un-clustered instance-level supervisions, re-identification model is trained progressively. Our proposed unsupervised object Re-ID framework significantly reduces the influence of noisy labels and refines the learned features. Our method consistently achieves state-of-the-art performance on benchmark datasets.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131340551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Temporal Sentence Grounding aims to localize the relevant temporal region in a given video according to the query sentence. It is a challenging task due to the semantic gap between different modalities and diversity of the event duration. Proposal generation plays an important role in previous mainstream methods. However, previous proposal generation methods apply the same feature extraction without considering the diversity of event duration. In this paper, we propose a novel temporal sentence grounding model with an U-shaped Network for efficient proposal generation (UN-TSG), which utilizes U-shaped structure to encode proposals of different lengths hierarchically. Experiments on two benchmark datasets demonstrate that with more efficient proposal generation method, our model can achieve the state-of-the-art grounding performance in faster speed and with less computation cost.
{"title":"Efficient Proposal Generation with U-shaped Network for Temporal Sentence Grounding","authors":"Ludan Ruan, Qin Jin","doi":"10.1145/3469877.3490606","DOIUrl":"https://doi.org/10.1145/3469877.3490606","url":null,"abstract":"Temporal Sentence Grounding aims to localize the relevant temporal region in a given video according to the query sentence. It is a challenging task due to the semantic gap between different modalities and diversity of the event duration. Proposal generation plays an important role in previous mainstream methods. However, previous proposal generation methods apply the same feature extraction without considering the diversity of event duration. In this paper, we propose a novel temporal sentence grounding model with an U-shaped Network for efficient proposal generation (UN-TSG), which utilizes U-shaped structure to encode proposals of different lengths hierarchically. Experiments on two benchmark datasets demonstrate that with more efficient proposal generation method, our model can achieve the state-of-the-art grounding performance in faster speed and with less computation cost.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127109081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Visible-infrared person re-identification (VI-ReID) is undoubtedly a challenging cross-modality person retrieval task with increasing appreciation. Compared to traditional person ReID that focuses on person images in a single RGB mode, VI-ReID suffers from additional cross-modality discrepancy due to the different imaging processes of spectrum cameras. Several effective attempts have been made in recent years to narrow cross-modality gap aiming to improve the re-identification performance, but rarely study the key problem of optimizing the search results combined with relevant feedback. In this paper, we present the idea of cross-modality visible-infrared person re-identification combined with human positive feedback. This method allows the user to quickly optimize the search performance by selecting strong positive samples during the re-identification process. We have validated the effectiveness of our method on a public dataset, SYSU-MM01, and results confirmed that the proposed method achieved superior performance compared to the current state-of-the-art methods.
{"title":"Visible-Infrared Cross-Modal Person Re-identification based on Positive Feedback","authors":"Lingyi Lu, Xin Xu","doi":"10.1145/3469877.3497693","DOIUrl":"https://doi.org/10.1145/3469877.3497693","url":null,"abstract":"Visible-infrared person re-identification (VI-ReID) is undoubtedly a challenging cross-modality person retrieval task with increasing appreciation. Compared to traditional person ReID that focuses on person images in a single RGB mode, VI-ReID suffers from additional cross-modality discrepancy due to the different imaging processes of spectrum cameras. Several effective attempts have been made in recent years to narrow cross-modality gap aiming to improve the re-identification performance, but rarely study the key problem of optimizing the search results combined with relevant feedback. In this paper, we present the idea of cross-modality visible-infrared person re-identification combined with human positive feedback. This method allows the user to quickly optimize the search performance by selecting strong positive samples during the re-identification process. We have validated the effectiveness of our method on a public dataset, SYSU-MM01, and results confirmed that the proposed method achieved superior performance compared to the current state-of-the-art methods.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117329453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The hashing technique has recently sparked much attention in information retrieval community due to its high efficiency in terms of storage and query processing. For cross-modal retrieval tasks, existing supervised hashing models either treat the semantic labels as the ground truth and formalize the problem to a classification task, or further add a similarity matrix as supervisory signals to pursue hash codes of high quality to represent coupled data. However, these approaches are incapable of ensuring that the learnt binary codes preserve well the semantics and similarity relationships contained in the supervised information. Moreover, for sophisticated discrete optimization problems, it is always addressed by continuous relaxation or bit-wise solver, which leads to a large quantization error and inefficient computation. To relieve these issues, in this paper, we present a two-step supervised discrete hashing method, i.e., laBel ReconstrUcting and Similarity preserving Hashing (BRUSH). We formulate it as an asymmetric pairwise similarity-preserving problem by using two latent semantic embeddings deducted from decomposing semantics and reconstructing semantics, respectively. Meanwhile, the unified binary codes are jointly generated based on both embeddings with the affinity guarantee, such that the discriminative property of the obtained hash codes can be significantly enhanced alongside preserving semantics well. In addition, by adopting two-step hash learning strategy, our method simplifies the procedure of the hashing function and binary codes learning, thus improving the flexibility and efficiency. The resulting discrete optimization problem is also elegantly solved by the proposed alternating algorithm without any relaxation. Extensive experiments on benchmarks demonstrate that BRUSH outperforms the state-of-the-art methods, in terms of efficiency and effectiveness.
{"title":"BRUSH: Label Reconstructing and Similarity Preserving Hashing for Cross-modal Retrieval","authors":"P. Zhang, Pengfei Zhao, Xin Luo, Xin-Shun Xu","doi":"10.1145/3469877.3490589","DOIUrl":"https://doi.org/10.1145/3469877.3490589","url":null,"abstract":"The hashing technique has recently sparked much attention in information retrieval community due to its high efficiency in terms of storage and query processing. For cross-modal retrieval tasks, existing supervised hashing models either treat the semantic labels as the ground truth and formalize the problem to a classification task, or further add a similarity matrix as supervisory signals to pursue hash codes of high quality to represent coupled data. However, these approaches are incapable of ensuring that the learnt binary codes preserve well the semantics and similarity relationships contained in the supervised information. Moreover, for sophisticated discrete optimization problems, it is always addressed by continuous relaxation or bit-wise solver, which leads to a large quantization error and inefficient computation. To relieve these issues, in this paper, we present a two-step supervised discrete hashing method, i.e., laBel ReconstrUcting and Similarity preserving Hashing (BRUSH). We formulate it as an asymmetric pairwise similarity-preserving problem by using two latent semantic embeddings deducted from decomposing semantics and reconstructing semantics, respectively. Meanwhile, the unified binary codes are jointly generated based on both embeddings with the affinity guarantee, such that the discriminative property of the obtained hash codes can be significantly enhanced alongside preserving semantics well. In addition, by adopting two-step hash learning strategy, our method simplifies the procedure of the hashing function and binary codes learning, thus improving the flexibility and efficiency. The resulting discrete optimization problem is also elegantly solved by the proposed alternating algorithm without any relaxation. Extensive experiments on benchmarks demonstrate that BRUSH outperforms the state-of-the-art methods, in terms of efficiency and effectiveness.","PeriodicalId":210974,"journal":{"name":"ACM Multimedia Asia","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121150961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：