Related papers: Parallel Context Modeling for Sliding Window Atten…
While some studies have proven that Swin Transformer (Swin) with window self-attention (WSA) is suitable for single image super-resolution (SR), the plain WSA ignores the broad regions when reconstructing high-resolution images due to a…
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…
Implementing algorithms on a fault-tolerant quantum computer will require fast decoding throughput and latency times to prevent an exponential increase in buffer times between the applications of gates. In this work we begin by quantifying…
To achieve higher coding efficiency, Versatile Video Coding (VVC) includes several novel components, but at the expense of increasing decoder computational complexity. These technologies at a low bit rate often create contouring and ringing…
This paper presents an N-gram context-based Swin Transformer for learned image compression. Our method achieves variable-rate compression with a single model. By incorporating N-gram context into the Swin Transformer, we overcome its…
Long contexts improve capabilities of large language models but pose serious hardware challenges: compute and memory footprints grow linearly with sequence length. Particularly, the decoding phase continuously accesses massive KV cache,…
For neural video codec, it is critical, yet challenging, to design an efficient entropy model which can accurately predict the probability distribution of the quantized latent representation. However, most existing video codecs directly use…
Transformer-based LLMs have achieved exceptional performance across a wide range of NLP tasks. However, the standard self-attention mechanism suffers from quadratic time complexity and linearly increased cache size. Sliding window attention…
We introduce a practical real-time neural video codec (NVC) designed to deliver high compression ratio, low latency and broad versatility. In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational…
Fast SC decoding overcomes the latency caused by the serial nature of the SC decoding by identifying new nodes in the upper levels of the SC decoding tree and implementing their fast parallel decoders. In this work, we first present a novel…
Efficient video coding is highly dependent on exploiting the temporal redundancy, which is usually achieved by extracting and leveraging the temporal context in the emerging conditional coding-based neural video codec (NVC). Although the…
The quadratic complexity of self attention in Transformer based LLMs renders long context inference prohibitively expensive. While Sliding Window Attention (SWA), the simplest sparse attention pattern, offers a linear complexity…
Modern retrospective analytics systems leverage cascade architecture to mitigate bottleneck for computing deep neural networks (DNNs). However, the existing cascades suffer two limitations: (1) decoding bottleneck is either neglected or…
In this paper, we study sliding window decoding of braided convolutional codes (BCCs) in the context of a streaming application, where decoder error propagation can be a serious problem. A window extension algorithm and a resynchronization…
The ever-growing multimedia traffic has underscored the importance of effective multimedia codecs. Among them, the up-to-date lossy video coding standard, Versatile Video Coding (VVC), has been attracting attentions of video coding…
Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the…
Recent advances in transformer-based Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their quadratic computational complexity concerning sequence length remains a significant bottleneck…
The advent of neuralmorphic spike cameras has garnered significant attention for their ability to capture continuous motion with unparalleled temporal resolution.However, this imaging attribute necessitates considerable resources for binary…
Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…
The recently developed pure Transformer architectures have attained promising accuracy on point cloud learning benchmarks compared to convolutional neural networks. However, existing point cloud Transformers are computationally expensive…