Related papers: Zero-Shot Knowledge Base Resizing for Rate-Adaptiv…
Model quantization is a promising approach to compress deep neural networks and accelerate inference, making it possible to be deployed on mobile and edge devices. To retain the high performance of full-precision models, most existing…
Recently, the ever-increasing demand for bandwidth in multi-modal communication systems requires a paradigm shift. Powered by deep learning, semantic communications are applied to multi-modal scenarios to boost communication efficiency and…
Zero-shot skeleton-based action recognition aims to develop models capable of identifying actions beyond the categories encountered during training. Previous approaches have primarily focused on aligning visual and semantic representations…
Visual Word Sense Disambiguation (VWSD) is a novel challenging task that lies between linguistic sense disambiguation and fine-grained multimodal retrieval. The recent advancements in the development of visiolinguistic (VL) transformers…
Keyword extraction has been an important topic for modern natural language processing. With its applications ranging from ontology generation, fact verification in summarized text, and recommendation systems. While it has had significant…
Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is significant and heavily impacts serving costs.…
We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…
Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…
Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling…
Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a…
Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised…
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…
Token communication has emerged as a promising framework for efficient wireless transmission by representing source data as compact semantic tokens. However, transmitting full semantic tokens still incurs considerable communication…
Semantic communication is emerging as a key paradigm for 6G networks, where the goal is not to perfectly reconstruct bits but to preserve the meaning that matters for a given task. This shift can improve bandwidth efficiency, robustness,…
Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…
Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks. However, a key limitation is that these language models fundamentally lack visual…
Hashing has shown its efficiency and effectiveness in facilitating large-scale multimedia applications. Supervised knowledge e.g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the…
Semantic communication has been increasingly integrated into edge computing systems for reconstruction tasks, owing to its advantages in source compression, robustness to channel noise, and task execution efficiency. However, the black-box…
Foundation model-based semantic transmission has recently shown great potential in wireless image communication. However, existing methods exhibit two major limitations: (i) they overlook the varying importance of semantic components for…
Semantic knowledge bases are regarded as a promising technology for upcoming 6G communications. However, existing studies mainly focus on source-side semantic modeling while overlooking the structural impact of propagation environments on…