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-articleOctober 2024JUST ACCEPTED
LLM-enhanced Composed Image Retrieval: An Intent Uncertainty-aware Linguistic-Visual Dual Channel Matching Model
Composed image retrieval (CoIR) involves a multi-modal query of the reference image and modification text describing the desired changes, allowing users to express image retrieval intents flexibly and effectively. The key of CoIR lies in how to properly ...
- research-articleApril 2024
A supervised contrastive learning-based model for image emotion classification
AbstractImages play a vital role in social media platforms, which can more vividly reflect people’s inner emotions and preferences, so visual sentiment analysis has become an important research topic. In this paper, we propose a Supervised Contrastive ...
- research-articleMarch 2024
An enhanced gradient-tracking bound for distributed online stochastic convex optimization
AbstractGradient-tracking (GT) based decentralized methods have emerged as an effective and viable alternative method to decentralized (stochastic) gradient descent (DSGD) when solving distributed online stochastic optimization problems. Initial studies ...
- research-articleFebruary 2024
Prerequisite-Enhanced Category-Aware Graph Neural Networks for Course Recommendation
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 18, Issue 5Article No.: 112, Pages 1–21https://doi.org/10.1145/3643644The rapid development of Massive Open Online Courses (MOOCs) platforms has created an urgent need for an efficient personalized course recommender system that can assist learners of all backgrounds and levels of knowledge in selecting appropriate courses. ...
- research-articleMarch 2024
Facial expression-enhanced recommendation for virtual fitting rooms
AbstractWith the development of Augmented Reality (AR) technology in the retail industry, virtual fitting room (VFR) are considered promising enhancement of e-commerce by providing users with an immersive environment to try on new products, especially ...
Highlights- Recommendation methods for virtual fitting room shopping environments.
- Predicting user preferences using facial expressions and other interaction behaviors.
- The experiment demonstrates the proposed method outperforms baseline ...
-
- research-articleMay 2024
Unbiased compression saves communication in distributed optimization: when and how much?
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 2081, Pages 47991–48020Communication compression is a common technique in distributed optimization that can alleviate communication overhead by transmitting compressed gradients and model parameters. However, compression can introduce information distortion, which slows down ...
- research-articleOctober 2023
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment
MM '23: Proceedings of the 31st ACM International Conference on MultimediaPages 1098–1107https://doi.org/10.1145/3581783.3612023Video Quality Assessment (VQA), which aims to predict the perceptual quality of a video, has attracted raising attention with the rapid development of streaming media technology, such as Facebook, TikTok, Kwai, and so on. Compared with other sequence-...
- research-articleOctober 2023
Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment
MM '23: Proceedings of the 31st ACM International Conference on MultimediaPages 6695–6704https://doi.org/10.1145/3581783.3611795Video quality assessment (VQA) has attracted growing attention in recent years. While the great expense of annotating large-scale VQA datasets has become the main obstacle for current deep-learning methods. To surmount the constraint of insufficient ...
- research-articleJuly 2023
AdaNPC: exploring non-parametric classifier for test-time adaptation
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 1748, Pages 41647–41676Many recent machine learning tasks focus to develop models that can generalize to unseen distributions. Domain generalization (DG) has become one of the key topics in various fields. Several literatures show that DG can be arbitrarily hard without ...
- research-articleJuly 2023
DSGD-CECA: decentralized SGD with communication-optimal exact consensus algorithm
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 320, Pages 8067–8089Decentralized Stochastic Gradient Descent (SGD) is an emerging neural network training approach that enables multiple agents to train a model collaboratively and simultaneously. Rather than using a central parameter server to collect gradients from all ...
- research-articleFebruary 2023
Dual Subgraph-Based Graph Neural Network for Friendship Prediction in Location-Based Social Networks
ACM Transactions on Knowledge Discovery from Data (TKDD), Volume 17, Issue 3Article No.: 42, Pages 1–28https://doi.org/10.1145/3554981With the wide use of Location-Based Social Networks (LBSNs), predicting user friendship from online social relations and offline trajectory data is of great value to improve the platform service quality and user satisfaction. Existing methods mainly focus ...
- research-articleMarch 2024
Removing data heterogeneity influence enhances network topology dependence of decentralized SGD
The Journal of Machine Learning Research (JMLR), Volume 24, Issue 1Article No.: 280, Pages 13275–13327We consider decentralized stochastic optimization problems, where a network of n nodes cooperates to find a minimizer of the globally-averaged cost. A widely studied decentralized algorithm for this problem is the decentralized SGD (D-SGD), in which each ...
- research-articleJanuary 2023
A New Multinetwork Mean Distillation Loss Function for Open-World Domain Incremental Object Detection
International Journal of Intelligent Systems (IJIS), Volume 2023https://doi.org/10.1155/2023/3044155The development of object detection networks has reached a high point, and there have been significant improvements in accuracy and detection speed. Object detection is widely used in intelligent robots, self-driving cars, and other edge-intelligent ...
- research-articleDecember 2022
Semantic and Structural View Fusion Modeling for Social Recommendation
IEEE Transactions on Knowledge and Data Engineering (IEEECS_TKDE), Volume 35, Issue 11Pages 11872–11884https://doi.org/10.1109/TKDE.2022.3230972Existing studies have shown that user-item interaction data and social relation data can be jointly used for enhancing the performance of social recommendation. However, limited research has a focus on investigating how to deeply exploit different views ...
- research-articleApril 2024
Revisiting optimal convergence rate for smooth and non-convex stochastic decentralized optimization
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 2636, Pages 36382–36395Decentralized optimization is effective to save communication in large-scale machine learning. Although numerous algorithms have been proposed with theoretical guarantees and empirical successes, the performance limits in decentralized optimization, ...
- research-articleApril 2024
Lower bounds and nearly optimal algorithms in distributed learning with communication compression
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 1377, Pages 18955–18969Recent advances in distributed optimization and learning have shown that communication compression is one of the most effective means of reducing communication. While there have been many results for convergence rates with compressed communication, a ...
- research-articleApril 2024
Communication-efficient topologies for decentralized learning with O(1) consensus rate
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing SystemsArticle No.: 79, Pages 1073–1085Decentralized optimization is an emerging paradigm in distributed learning in which agents achieve network-wide solutions by peer-to-peer communication without the central server. Since communication tends to be slower than computation, when each agent ...
- research-articleDecember 2022
Nonlinear Kalman Filter Based Shop Floor RFID Data Fusion Algorithm
CSAE '22: Proceedings of the 6th International Conference on Computer Science and Application EngineeringArticle No.: 53, Pages 1–7https://doi.org/10.1145/3565387.3565440Radio frequency identification (RFID) technology is one of the main means to obtain the location data of production elements such as personnel and materials in intelligent workshops, but its positioning accuracy has many uncertainties. In order to map ...
- ArticleJune 2022
Image Classification via Multi-branch Position Attention Network
Pattern Recognition and Artificial IntelligencePages 96–108https://doi.org/10.1007/978-3-031-09037-0_9AbstractImage classification is a hot spot in the field of pattern recognition and artificial intelligence. When there are apparent inter-class similarity and intra-class diversity, such as in the area of remote sensing, image classification becomes very ...
- research-articleJanuary 2022
A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning
IEEE Transactions on Signal Processing (TSP), Volume 70Pages 3264–3279https://doi.org/10.1109/TSP.2022.3184770We study the consensus decentralized optimization problem where the objective function is the average of <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> agents private non-convex cost functions; moreover, the agents can only ...