Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 3919–3929https://doi.org/10.1145/3589334.3645693The heterogeneous information network (HIN), which contains rich semantics depicted by meta-paths, has emerged as a potent tool for mitigating data sparsity in recommender systems. Existing HIN-based recommender systems operate under the assumption of ...
- short-paperMarch 2024
Efficient size-prescribed k-core search
ASONAM '23: Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningNovember 2023, Pages 271–275https://doi.org/10.1145/3625007.3627316k-core is a subgraph where every node has at least k neighbors within the subgraph. The k-core subgraphs has been employed in large platforms like Network Repository to comprehend the underlying structures and dynamics of the network. Existing studies ...
- research-articleMarch 2024
Centralization Problem for Opinion Convergence in Decentralized Networks
ASONAM '23: Proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningNovember 2023, Pages 658–665https://doi.org/10.1145/3625007.3627291This paper presents a novel perspective on the relationship between decentralization, a prevalent characteristic of multi-agent systems, and centralization, which involves imposing central control to achieve system-level objectives. Specifically, within ...
- research-articleFebruary 2024
User Experience Analysis of Library Intelligent Book-Lending Cabinets Service Based on MOA Model༚Case Study of China
CHCHI '23: Proceedings of the Eleventh International Symposium of Chinese CHINovember 2023, Pages 290–301https://doi.org/10.1145/3629606.3629633Paper book lending and circulation encounter challenges during the COVID-19 epidemic, while self-service based on network ordering offers apparent advantages. It has been proved and practiced that community-based book distribution may successfully boost ...
- tutorialNovember 2023
Graph Mining for Cybersecurity: A Survey
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 2Article No.: 47, Pages 1–52https://doi.org/10.1145/3610228The explosive growth of cyber attacks today, such as malware, spam, and intrusions, has caused severe consequences on society. Securing cyberspace has become a great concern for organizations and governments. Traditional machine learning based methods are ...
-
- research-articleNovember 2023
Rethinking and Improving Few-Shot Segmentation From a Contour-Aware Perspective
IEEE Transactions on Multimedia (TOM), Volume 252023, Pages 6917–6929https://doi.org/10.1109/TMM.2022.3215896Existing few-shot segmentation approaches basically adopt the idea of comparing the semantic prototype vector of the query image and support images, and then obtaining the segmentation result. However, recent studies have shown that a single feature ...
- research-articleOctober 2023
Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 1975–1986https://doi.org/10.1145/3581783.3611752The video frame interpolation (VFI) model applies the convolution operation to all locations, leading to redundant computations in regions with easy motion. We can use dynamic spatial pruning method to skip redundant computation, but this method cannot ...
- research-articleOctober 2023
MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector Prior
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 1964–1974https://doi.org/10.1145/3581783.3611750In recent years, many deep learning-based methods have been proposed to tackle the problem of optical flow estimation and achieved promising results. However, they hardly consider that most videos are compressed and thus ignore the pre-computed ...
- research-articleOctober 2023
Adaptive map matching based on dynamic word embeddings for indoor positioning
Graphical abstractDisplay Omitted
Highlights- Dynamic word embedding model is proposed to extract latent oriented information of map points for rich contextual information in data fusion with Inertial Measurement Unit (IMU) trajectory data.
- A novel method of using Variational ...
Map matching has been widely used in various indoor localization technologies. However, conventional map matching technologies based on probabilistic models, such as particle filter (PF), still have a series of limitations, such as ...
- research-articleSeptember 2023
A Motion Distillation Framework for Video Frame Interpolation
IEEE Transactions on Multimedia (TOM), Volume 262024, Pages 3728–3740https://doi.org/10.1109/TMM.2023.3314971In recent years, we have seen the success of deep video enhancement models. However, the performance improvement of new methods has gradually entered a bottleneck period. Optimizing model structures or increasing training data brings less and less ...
- research-articleAugust 2023
Learning survival distribution with implicit survival function
IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceAugust 2023, Article No.: 442, Pages 3975–3983https://doi.org/10.24963/ijcai.2023/442Survival analysis aims at modeling the relationship between covariates and event occurrence with some untracked (censored) samples. In implementation, existing methods model the survival distribution with strong assumptions or in a discrete time space for ...
- research-articleAugust 2023
Multi-modality deep network for JPEG artifacts reduction
IJCAI '23: Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceAugust 2023, Article No.: 429, Pages 3857–3865https://doi.org/10.24963/ijcai.2023/429In recent years, many convolutional neural network-based models are designed for JPEG artifacts reduction, and have achieved notable progress. However, few methods are suitable for extreme low-bitrate image compression artifacts reduction. The main ...
- research-articleMay 2023
ContextAVO: Local context guided and refining poses for deep visual odometry
Neurocomputing (NEUROC), Volume 533, Issue CMay 2023, Pages 86–103https://doi.org/10.1016/j.neucom.2023.02.014AbstractLearning-based monocular visual odometry (VO) has lately drawn significant attention for its robustness to camera parameters and environmental variations. The correlation of ego-motion in the local time dimension, denoted as the local ...
- research-articleApril 2023
Comparative analysis of urban underground public space and user walking paths based on the social network model
Neural Computing and Applications (NCAA), Volume 35, Issue 36Dec 2023, Pages 24981–24999https://doi.org/10.1007/s00521-023-08589-8AbstractThe operation status of the underground public space pedestrian system is of varying quality, but decision-makers and operators have no way of knowing its current operation status and how to retrofit it. In this paper, the social network model is ...
- research-articleFebruary 2023
Multi-modality deep network for extreme learned image compression
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial IntelligenceFebruary 2023, Article No.: 115, Pages 1033–1041https://doi.org/10.1609/aaai.v37i1.25184Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years, but suffer from blur and severe semantics loss at extremely low bitrates. To address this issue, ...
- ArticleOctober 2022
Disentanglement of Deep Features for Adversarial Face Detection
AbstractExisting adversarial face detectors are mostly developed against specific types of attacks, and limited by their generalizability especially in adversarial settings. In this paper, we propose a new detection strategy based on a dual-classifier ...
- research-articleOctober 2022
Dual Data Augmentation Method for Data-Deficient and Occluded Instance Segmentation
MMSports '22: Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in SportsOctober 2022, Pages 117–120https://doi.org/10.1145/3552437.3555697Instance segmentation is applied widely in image editing, image analysis and autonomous driving, etc. However, insufficient data and occlusion are common problems in practical application. DeepSportRadar Instance Segmentation challenge has focused on ...
- research-articleOctober 2022
Co-Completion for Occluded Facial Expression Recognition
MM '22: Proceedings of the 30th ACM International Conference on MultimediaOctober 2022, Pages 130–140https://doi.org/10.1145/3503161.3548183The existence of occlusions brings in semantically irrelevant visual patterns and leads to the content loss of occluded regions. Although previous works have made improvement on occluded facial expression recognition, they do not explicitly handle the ...
- research-articleOctober 2022
Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal
MM '22: Proceedings of the 30th ACM International Conference on MultimediaOctober 2022, Pages 6072–6082https://doi.org/10.1145/3503161.3547986Under stereo settings, the performance of image JPEG artifacts removal can be further improved by exploiting the additional information provided by a second view. However, incorporating this information for stereo image JPEG artifacts removal is a huge ...
- research-articleOctober 2022
Rethinking Super-Resolution as Text-Guided Details Generation
MM '22: Proceedings of the 30th ACM International Conference on MultimediaOctober 2022, Pages 3461–3469https://doi.org/10.1145/3503161.3547951Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However, the image-...