Multi-modal Alignment using Representation Codebook [PDF]
Computer Vision and Pattern Recognition, 2022 Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion.
Jiali Duan +6 more
semanticscholar +1 more source
EdVAE: Mitigating Codebook Collapse with Evidential Discrete Variational Autoencoders [PDF]
Pattern Recognition, 2023 Codebook collapse is a common problem in training deep generative models with discrete representation spaces like Vector Quantized Variational Autoencoders (VQ-VAEs).
Gulcin Baykal, M. Kandemir, Gozde Unal
semanticscholar +1 more source
Codebook design and beam training for extremely large-scale RIS: Far-field or near-field? [PDF]
China Communications, 2021 Reconfigurable intelligent surface (RIS) is more likely to develop into extremely large-scale RIS (XL-RIS) to efficiently boost the system capacity for future 6G communications. Beam training is an effective way to acquire channel state information (CSI)
Xiuhong Wei +4 more
semanticscholar +1 more source
Spatial-Chirp Codebook-Based Hierarchical Beam Training for Extremely Large-Scale Massive MIMO [PDF]
IEEE Transactions on Wireless Communications, 2022 Extremely large-scale multiple-input multiple-output (XL-MIMO) promises to provide ultrahigh data rates in millimeter-wave (mmWave) and Terahertz (THz) spectrum.
Xu Shi +3 more
semanticscholar +1 more source
Hierarchical Codebook Design for Near-Field mmWave MIMO Communications Systems [PDF]
IEEE Wireless Communications Letters, 2022 Communications system with analog or hybrid analog/digital architectures usually relies on a pre-defined codebook to perform beamforming. With the increase in the size of the antenna array, the characteristics of the spherical wavefront in the near-field
Jiawei Chen +3 more
semanticscholar +1 more source
New Method to Reduce the Size of Codebook in Vector Quantization of Images [PDF]
Al-Rafidain Journal of Computer Sciences and Mathematics, 2005 The vector quantization method for image compression inherently requires the generation of a codebook which has to be made available for both the encoding and decoding processes.
Sahar Ahmed
doaj +1 more source
A Partial Channel Reciprocity-Based Codebook for Wideband FDD Massive MIMO [PDF]
IEEE Transactions on Wireless Communications, 2022 The acquisition of channel state information (CSI) in Frequency Division Duplex (FDD) massive MIMO has been a formidable challenge. In this paper, we address this problem with a novel CSI feedback framework enabled by the partial reciprocity of uplink ...
Haifan Yin, D. Gesbert
semanticscholar +1 more source
Differential Data-Aided Beam Training for RIS-Empowered Multi-Antenna Communications
IEEE Access, 2022 The Reconfigurable Intelligent Surface (RIS) constitutes one of the prominent technologies for the next generation of wireless communications. It is envisioned to enhance the signal coverage in cases when the direct link of the communication is weak ...
Kun Chen-Hu +2 more
doaj +1 more source
Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation [PDF]
InterspeechThe multi-codebook speech codec enables the application of large language models (LLM) in TTS but bottlenecks efficiency and robustness due to multi-sequence prediction.
Hanzhao Li +8 more
semanticscholar +1 more source
A Review of Codebook Models in Patch-Based Visual Object Recognition [PDF]
, 2011 The codebook model-based approach, while ignoring any structural aspect in vision, nonetheless provides state-of-the-art performances on current datasets.
Niranjan, Mahesan +1 more
core +1 more source