Richang Hong

Richang Hong

Auto-generated profile, based on publicly available information

Richang Hong

Hefei University of Technology

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2020 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
LWLe Wu
Le Wu
JLJunwei Li
Junwei Li
PSPeijie Sun
Peijie Sun
RHRichang Hong
Richang Hong
YGYong Ge
Yong Ge
MWMeng Wang
Meng Wang
Social recommendation has emerged to leverage social connections among users for predicting users’ unknown preferences, which could alleviate the data sparsity issue in collaborative filtering based recommendation. Early approaches relied on utilizing each user’s first-order social neighbors’ interests for better user modeling, and failed to model the social influence diffusion process from the global social network structure. Recently, we propose a preliminary work of a neural influence Diff usion Net work (i.e., DiffNet) for social recommendation L. Wu, P. Sun, Y. Fu, R. Hong, X. Wang, and M. Wang, “A neural influence diffusion model for social recommendation,” in Proc. Int. ACM SIGIR Conf. Res. Develop. Inf. Retrieval , 2019, pp. 235–244.. DiffNet models the recursive social diffusion process for each user, such that the influence diffusion hidden in the higher-order social network is captured in the user embedding process. Despite the superior performance of DiffNet, we argue that, as users play a central role in both user-user social network and user-item interest network, only modeling the influence diffusion process in the social network would neglect the latent collaborative interests of users hidden in the user-item interest network. To this end, in this paper, we propose DiffNet++, an improved algorithm of DiffNet that models the neural influence diffusion and interest diffusion in a unified framework. By reformulating the social recommendation as a heterogeneous graph with social network and interest network as input, DiffNet++ advances DiffNet by injecting both the higher-order user latent interest reflected in the user-item graph and higher-order user influence reflected in the user-user graph for user embedding learning. This is achieved by iteratively aggregating each user’s embedding from three aspects: the user’s previous embedding, the influence aggregation of social neighbors from the social network, and the interest aggregation of item neighbors from the user-item interest network. Furthermore, we design a multi-level attention network that learns how to attentively aggregate user embeddings from these three aspects. Finally, extensive experimental results on four real-world datasets clearly show the effectiveness of our proposed model. We release the source code at https://github.com/PeiJieSun/diffnet .

28 November 2011
Verified
Conference Paper
Open access
PDF file
JSJingkuan Song
Jingkuan Song
YYYi Yang
Yi Yang
ZHZi Huang
Zi Huang
HSHeng Tao Shen
Heng Tao Shen
RHRichang Hong
Richang Hong

15 April 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
RHRichang Hong
Richang Hong
DLDaqing Liu
Daqing Liu
XMXiaoyu Mo
Xiaoyu Mo
XHXiangnan He
Xiangnan He
HZHanwang Zhang
Hanwang Zhang
Grounding natural language in images, such as localizing "the black dog on the left of the tree", is one of the core problems in artificial intelligence, as it needs to comprehend the fine-grained and compositional language space. However, existing solutions rely on the association between the holistic language features and visual features, while neglect the nature of compositional reasoning implied in the language. In this paper, we propose a natural language grounding model that can automatically compose a binary tree structure for parsing the language and then perform visual reasoning along the tree in a bottom-up fashion. We call our model RVG-TREE: Recursive Grounding Tree, which is inspired by the intuition that any language expression can be recursively decomposed into two constituent parts, and the grounding confidence score can be recursively accumulated by calculating their grounding scores returned by sub-trees. RVG-TREE can be trained end-to-end by using the Straight-Through Gumbel-Softmax estimator that allows the gradients from the continuous score functions passing through the discrete tree construction. Experiments on several benchmarks show that our model achieves the state-of-the-art performance with more explainable reasoning.

28 December 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
MHMengqiu Hu
Mengqiu Hu
YYYang Yang
Yang Yang
FSFumin Shen
Fumin Shen
NXNing Xie
Ning Xie
RHRichang Hong
Richang Hong
HSHeng Tao Shen
Heng Tao Shen
In this paper, we study the problem of cross-modal retrieval by hashing-based approximate nearest neighbor (ANN) search techniques. Most existing cross-modal hashing work mainly addresses the issue of multi-modal integration complexity using the same mapping and similarity calculation for data from different media types. Nonetheless, this may cause information loss during the mapping process due to overlooking the specifics of each individual modality. In this work, we propose a simple yet effective cross-modal hashing approach, termed Collective Reconstructive Embeddings (CRE), which can simultaneously solve the heterogeneity and integration complexity of multi-modal data. To address the heterogeneity challenge, we propose to process heterogeneous types of data using different modalityspecific models. Specifically, we model textual data with cosine similarity based reconstructive embedding to alleviate the data sparsity to the greatest extent, while for image data we utilize the Euclidean distance to characterize the relationships of the projected hash codes. Meanwhile, we unify the projections of text and image to the Hamming space into a common reconstructive embedding through rigid mathematical reformulation, which not only reduces the optimization complexity significantly but also facilitates the inter-modal similarity preservation among different modalities. We further incorporate the code balance and uncorrelation criteria into the problem, and devise an efficient iterative algorithm for optimization. Comprehensive experiments on four widely-used multimodal benchmarks show that the proposed CRE can achieve superior performance compared to the state-of-the-arts on several challenging cross-modal tasks.

17 March 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
KLKang Liu
Kang Liu
FXFeng Xue
Feng Xue
DGDan Guo
Dan Guo
PSPeijie Sun
Peijie Sun
SQShengsheng Qian
Shengsheng Qian
RHRichang Hong
Richang Hong
Multimedia-based recommendation is a challenging task that requires not only learning collaborative signals from user-item interaction, but also capturing modality-specific user interest clues from complex multimedia content. Though significant progress on this challenge has been made, we argue that current solutions remain limited by multimodal noise contamination. Specifically, a considerable proportion of multimedia content is irrelevant to the user preference, such as the background, overall layout, and brightness of images; the word order and semantic-free words in titles; etc . We take this irrelevant information as noise contamination to discover user preferences. Moreover, most recent research has been conducted by graph learning. This means that noise is diffused into the user and item representations with the message propagation; the contamination influence is further amplified. To tackle this problem, we develop a novel framework named Multimodal Graph Contrastive Learning (MGCL), which captures collaborative signals from interactions and uses visual and textual modalities to respectively extract modality-specific user preference clues. The key idea of MGCL involves two aspects: First, to alleviate noise contamination during graph learning, we construct three parallel graph convolution networks to independently generate three types of user and item representations, containing collaborative signals, visual preference clues, and textual preference clues. Second, to eliminate as much preference-independent noisy information as possible from the generated representations, we incorporate sufficient self-supervised signals into the model optimization with the help of contrastive learning, thus enhancing the expressiveness of the user and item representations. Note that MGCL is not limited to graph learning schema, but also can be applied to most matrix factorization methods. We conduct extensive experiments on three public datasets to validate the effectiveness and scalability of MGCL 1 1We release the codes of MGCL at https://github.com/hfutmars/MGCL. .

1 October 2021 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
Shengeng TangShengeng Tang
Shengeng Tang
DGDan Guo
Dan Guo
RHRichang Hong
Richang Hong
MWMeng Wang
Meng Wang
Sign language translation (SLT) is a challenging weakly supervised task without word-level annotations. An effective method of SLT is to leverage multimodal complementarity and to explore implicit temporal cues. In this work, we propose a graph-based multimodal sequential embedding network (MSeqGraph), in which multiple sequential modalities are densely correlated. Specifically, we build a graph structure to realize the intra-modal and inter-modal correlations. First, we design a graph embedding unit (GEU), which embeds a parallel convolution with channel-wise and temporal-wise learning into the graph convolution to learn the temporal cues in each modal sequence and cross-modal complementarity. Then, a hierarchical GEU stacker with a pooling-based skip connection is proposed. Unlike the state-of-the-art methods, to obtain a compact and informative representation of multimodal sequences, the GEU stacker gradually compresses the channel d with multi-modalities m rather than the temporal dimension t. Finally, we adopt the connectionist temporal decoding strategy to explore the entire video's temporal transition and translate the sentence. Extensive experiments on the USTC-CSL and BOSTON-104 datasets demonstrate the effectiveness of the proposed method.