Test Whats new message.
Scheduled Maintenance on Monday 1/13/2025
Single article sales and account management will be unavailable from 5:00 AM - 7:00 PM ET (09:00 - 23:00 UTC). We apologize for the inconvenience.
Showing 1-18 of 18 results
- Sort
Filter Results
Show
Sort By
Results
Self-Supervised Uncertainty-Guided Refinement for Robust Joint Optical Flow and Depth Estimation
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2025 | Conference Paper |
Jointly estimating the optical flow and depth tasks in real-world scenes presents considerable hurdles due to some phenomena, such as occlusion, ambiguous textures, and illumination variation. The lack of guidance from the labeled data makes these challenges harder to overcome. This paper presents a novel approach to learning the regions with high uncertainties in a self-supervised manner. Our met...Show More
Dynamic Graph Convolutional Networks with Spatiotemporal Missing Pattern Awareness
Bingheng Pang;Zhuoxuan Liang;Wei Li;Xiangping Zheng;Rokia Abdein
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2025 | Conference Paper |
Missing data is ubiquitous phenomenon in the time series community, significantly challenging forecasting due to incomplete ground truth and sparse data. Most previous Multi-variate Time Series Forecasting with Missing Values (MTSFMV) approaches usually assume static missing patterns, neglecting the dynamic changes over time and space, leading to suboptimal forecasting results. To tackle these cha...Show More
A Universal List Decoding Algorithm With Application to Decoding of Polar Codes
This paper is concerned with a guessing codeword decoding (GCD) of linear block codes, which is optimal and typically requires a fewer number of searches than the naive exhaustive search decoding (ESD). Compared with the guessing random additive noise decoding (GRAND), which is only efficient for high-rate codes, the GCD is efficient for not only high-rate codes but also low-rate codes. We prove t...Show More
Participation-Dependent Privacy Preservation in Cross-Silo Federated Learning
In cross-silo federated learning (FL), clients of common interest cooperatively train a global model without sharing local sensitive data, but they still face potential privacy leakage due to privacy threats from malicious attackers. Although some articles have proposed effective privacy-preserving mechanisms for FL (such as differential privacy (DP)), clients in cross-silo FL are usually differen...Show More
SCL-GCD of Short Polar Codes
GLOBECOM 2024 - 2024 IEEE Global Communications Conference
Year: 2024 | Conference Paper |
This paper is concerned with the SCL-GCD algorithm of polar codes, which performs the successive-cancellation list (SCL) decoding algorithm for a lower rate sub-code and the guessing codeword decoding (GCD) algorithm for a higher rate sub-code. We propose to implement the GCD algorithm in a parallel way and design early stopping criteria for reducing complexity and decoding latency without sacrifi...Show More
This paper is concerned with a universal guessing codeword decoding (GCD) of linear block codes, referred to as locally constrained GCD (LC-GCD), which does not require the online Gaussian elimination (GE). Distinguished from the GCD algorithm, the proposed LC-GCD queries the partial error patterns using the serial list Viterbi algorithm (SLVA) over a trellis specified by a local parity-check matr...Show More
Quasi-OSD of Binary Image of RS Codes with Applications to JSCC
2024 IEEE International Symposium on Information Theory (ISIT)
Year: 2024 | Conference Paper |
Cited by: Papers (4)
We propose quasi ordered statistic decoding (quasi-OSD) of binary image of Reed-Solomon (RS) codes and explore the application of RS codes to joint source-channel coding (JSCC). Unlike the conventional OSD algorithms that use Gaussian elimination to obtain the systematic matrix, the proposed quasi-OSD algorithm utilizes the parallel Lagrange interpolation at the symbol level, which achieves a lowe...Show More
Trellis-Based Construction of Polar Codes for SCL Decoding
2024 IEEE International Symposium on Information Theory (ISIT)
Year: 2024 | Conference Paper |
In this paper, we propose an approach to construction of polar codes for successive cancellation list (SCL) decoding with a preset list size. For a given code length, we construct a trellis through which a path corresponds to a polar code. Then, we employ a sequential search algorithm to find an expected path based on four path metrics and five path selection rules. Additionally, for polarization-...Show More
Simultaneous Wireless Information and Power Transfer with Polar Coded Probabilistic Amplitude Shaping
2024 IEEE International Conference on Communications Workshops (ICC Workshops)
Year: 2024 | Conference Paper |
In this paper, we propose a new simultaneous wireless information and power transfer (SWIPT) scheme by adopting the polar coded probabilistic amplitude shaping (PAS) framework. Here, the polar code is employed to support the reliable wireless information transfer (WIT), while the constant composition distribution matcher (CCDM) alters the distribution of channel inputs to implement the wireless po...Show More
Select The Best: Enhancing Graph Representation with Adaptive Negative Sample Selection
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Graph contrastive learning (GCL) has emerged as a powerful tool to address real-world widespread label scarcity problems and has achieved impressive success in the graph learning domain. Albeit their remarkable performance, most current works mainly focus on designing sample augmentation methods, while the effect of negative sample selection strategy is largely ignored by previous works but rather...Show More
Intent Does Matter! Propagating High-Order Relations for Exploring Interest Preferences
Xiangping Zheng;Xun Liang;Bo Wu;Junlan Feng;Yuhui Guo;Sensen Zhang
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Session-based recommendation (SBR) aims to predict the user’s action at the next timestamp according to an anonymous yet short interaction sequence (i.e., session). Almost all the existing SBR solutions for user preference are only based on the current session without exploiting the high-order relations among other sessions, which may restrict the SBR representation ability and even deteriorate th...Show More
Cross-Modal Matching and Adaptive Graph Attention Network for RGB-D Scene Recognition
Yuhui Guo;Xun Liang;James T. Kwok;Xiangping Zheng;Bo Wu;Yuefeng Ma
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2023 | Conference Paper |
Cited by: Papers (1)
Despite the significant advances in RGB-D scene recognition, there are several major limitations that need further investigation. For example, simply extracting modal-specific features neglects the complex relationships among multiple modalities of features. Moreover, cross-modal features have not been considered in most existing methods. To address these concerns, we propose to integrate the task...Show More
Reinforced Sample Selection for Graph Neural Networks Transfer Learning
2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Graph neural networks (GNNs) have become a practical paradigm for learning graph-structured data, which can generate node representations by recursively aggregating information from neighbor nodes. Recent works utilize self-supervised tasks to learn transferable knowledge from source domain graphs and improve the GNNs performance on target domain graphs. However, there are considerable low-quality...Show More
Win-Win Cooperation: Semantic Encoding Learning and Saliency Selection for Weakly supervised Semantic Segmentation
IEEE Transactions on Cognitive and Developmental Systems
Year: 2022 | Early Access Article |
Cited by: Papers (1)
Image-level weakly supervised semantic segmentation methods have attracted increasing attention due to data labeling efficiency, but these methods mostly focus on utilizing the localization maps generated by the classification network to produce pseudo labels, leading to sparse object regions, object boundary mismatch and co-occurring pixels existing in the target objects. To address these issues,...Show More
CoNet: Co-Embedding by Reinforcing Graph Feature and Topology Information
2022 IEEE International Conference on Multimedia and Expo (ICME)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Sparsity and smoothness are two main factors that affect the performance of Graph Convolutional Networks (GCNs). Sparsity ensures that models have the first-class generalization ability, while smoothness benefits to reduce noise and make edges reliable. As real-world graphs are often incom-plete and noisy, most GCNs learn node embeddings only acting them as ground-truth information, which unavoida...Show More
Adaptive Attention Graph Capsule Network
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2022 | Conference Paper |
From the perspective of the spatial domain, Graph Convolutional Network (GCN) is essentially a process of iteratively aggregating neighbor nodes. However, the existing GCNs using simple average or sum aggregation may neglect the characteristics of each node and the topology between nodes, resulting in a large amount of early-stage information lost during the graph convolution step. To tackle the a...Show More
Graph Fine-Grained Contrastive Representation Learning
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Existing graph contrastive methods have benefited from ingenious data augmantations and mutual information estimation operations that are carefully designated to augment graph views and maximize the agreement between representations produced at the aftermost layer of two view networks. However, the design of graph CL schemes is coarse-grained and difficult to capture the universal and intrinsic pr...Show More
Improving Dynamic Graph Convolutional Network with Fine-Grained Attention Mechanism
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2022 | Conference Paper |
Cited by: Papers (5)
Graph convolutional network (GCN) is a novel framework that utilizes a pre-defined Laplacian matrix to learn graph data effectively. With its powerful nonlinear fitting ability, GCN can produce high-quality node embedding. However, generalized GCN can only handle static graphs, whereas a large number of graphs are dynamic and evolve over time, which limits the application field of GCN. Facing the ...Show More
IEEE Account
Purchase Details
Profile Information
Need Help?
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Contact Us
- Help
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Sitemap
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.