Feedback-Aided Rateless Codes Unequal Error Protection for Multimodal Communication

In multimodal communication, the importance of different modalities varies due to factors such as the nonuniform distribution of information, differences in error tolerance, variations in information redundancy, network environment, and bandwidth limitations, as well as the synergistic effects between modalities. During transmission, due to network conditions and bandwidth constraints, it may not be possible to transmit the information of each modality to the receiver in an intact form to perform multimodal tasks. In response to the transmission characteristics and the unequal error protection requirements described above, this paper proposes an end-to-end multimodal rateless codes unequal error protection scheme from the perspective of logical links. We also introduced a feedback mechanism to implement algorithms such as adaptive code length adjustment, adaptive degree distribution, adaptive weight rotation allocation, and maximum weight constraints. Compared to previous schemes, the proposed solution in this paper further reduces the decoding overhead and recovery latency of less important modality, thus improving resource utilization.

Authors

Institutions

Publication Details

Published
2025-06-17
DOI
https://doi.org/10.1109/vtc2025-spring65109.2025.11174744
Primary Topic
Advanced Research in Systems and Signal Processing
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Feedback-Aided Rateless Codes Unequal Error Protection for Multimodal Communication

Haobo Huang, Yusun Fu, Junpeng Yin
Advanced Research in Systems and Signal Processing
article

Feedback-Aided Rateless Codes Unequal Error Protection for Multimodal Communication

Haobo Huang, Yusun Fu, Junpeng Yin
article en

Abstract

In multimodal communication, the importance of different modalities varies due to factors such as the nonuniform distribution of information, differences in error tolerance, variations in information redundancy, network environment, and bandwidth limitations, as well as the synergistic effects between modalities. During transmission, due to network conditions and bandwidth constraints, it may not be possible to transmit the information of each modality to the receiver in an intact form to perform multimodal tasks. In response to the transmission characteristics and the unequal error protection requirements described above, this paper proposes an end-to-end multimodal rateless codes unequal error protection scheme from the perspective of logical links. We also introduced a feedback mechanism to implement algorithms such as adaptive code length adjustment, adaptive degree distribution, adaptive weight rotation allocation, and maximum weight constraints. Compared to previous schemes, the proposed solution in this paper further reduces the decoding overhead and recovery latency of less important modality, thus improving resource utilization.

Shanghai Jiao Tong University (CN)
Openalex Percentile: Top 66%
Advanced Research in Systems and Signal Processing
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Feedback-Aided Rateless Codes Unequal Error Protection for Multimodal Communication — Haobo Huang, Yusun Fu, et al. · (2025) | TGRS Research Map | TGRS