中文
相关论文

相关论文: Parallel Context Modeling for Sliding Window Atten…

200 篇论文

Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple…

计算机视觉与模式识别 · 计算机科学 2022-06-16 Jingyun Liang , Jiezhang Cao , Yuchen Fan , Kai Zhang , Rakesh Ranjan , Yawei Li , Radu Timofte , Luc Van Gool

Multi-hybrid architectures are poised to take over language modeling due to better quality and performance. We introduce a hierarchical decomposition framework for linear recurrences that allows us to develop algorithms aligned with GPU…

机器学习 · 计算机科学 2025-12-17 Dragos Secrieru , Garyk Brixi , Yoshua Bengio , Taiji Suzuki , Michael Poli , Stefano Massaroli

Neural video compression (NVC) is a rapidly evolving video coding research area, with some models achieving superior coding efficiency compared to the latest video coding standard Versatile Video Coding (VVC). In conventional video coding…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Yeongwoong Kim , Suyong Bahk , Seungeon Kim , Won Hee Lee , Dokwan Oh , Hui Yong Kim

Intra prediction is an important component of modern video codecs, which is able to efficiently squeeze out the spatial redundancy in video frames. With preceding pixels as the context, traditional intra prediction schemes generate linear…

计算机视觉与模式识别 · 计算机科学 2019-05-28 Yueyu Hu , Wenhan Yang , Mading Li , Jiaying Liu

Video compression systems must support increasing bandwidth and data throughput at low cost and power, and can be limited by entropy coding bottlenecks. Efficiency can be greatly improved by parallelizing coding, which can be done at much…

图像与视频处理 · 电气工程与系统科学 2023-12-05 Amir Said , Hoang Le , Farzad Farhadzadeh

Coding 4K data has become of vital interest in recent years, since the amount of 4K data is significantly increasing. We propose a coding chain with spatial down- and upscaling that combines the next-generation VVC codec with machine…

图像与视频处理 · 电气工程与系统科学 2023-08-15 Kristian Fischer , Christian Herglotz , André Kaup

Video compression is widely used in digital television, surveillance systems, and virtual reality. Real-time video decoding is crucial in practical scenarios. Recently, neural video compression (NVC) combines traditional coding with deep…

图像与视频处理 · 电气工程与系统科学 2023-12-20 Siyu Zhang , Wendong Mao , Huihong Shi , Zhongfeng Wang

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control.…

Over the last few years, neural image compression has gained wide attention from research and industry, yielding promising end-to-end deep neural codecs outperforming their conventional counterparts in rate-distortion performance. Despite…

计算机视觉与模式识别 · 计算机科学 2023-07-14 Ahmed Ghorbel , Wassim Hamidouche , Luce Morin

In this paper, we first show that current learning-based video codecs, specifically the SSF codec, are not suitable for real-world applications due to the mismatch between the encoder and decoder caused by floating-point round-off errors.…

多媒体 · 计算机科学 2024-10-29 Ruhan Conceição , Marcelo Porto , Wen-Hsiao Peng , Luciano Agostini

In the framework of learned image compression, the context model plays a pivotal role in capturing the dependencies among latent representations. To reduce the decoding time resulting from the serial autoregressive context model, the…

图像与视频处理 · 电气工程与系统科学 2023-12-01 Yang Sui , Ding Ding , Xiang Pan , Xiaozhong Xu , Shan Liu , Bo Yuan , Zhenzhong Chen

In this paper, we propose a neural window decoder (NWD) for spatially coupled low-density parity-check (SC-LDPC) codes. The proposed NWD retains the conventional window decoder (WD) process but incorporates trainable neural weights. To…

机器学习 · 计算机科学 2026-01-30 Dae-Young Yun , Hee-Youl Kwak , Yongjune Kim , Sang-Hyo Kim , Jong-Seon No

Video captioning is a challenging task that captures different visual parts and describes them in sentences, for it requires visual and linguistic coherence. The attention mechanism in the current video captioning method learns to assign…

计算机视觉与模式识别 · 计算机科学 2021-10-19 Zhixin Sun , Xian Zhong , Shuqin Chen , Lin Li , Luo Zhong

Large-scale quantum computers have the potential to hold computational capabilities beyond conventional computers for certain problems. However, the physical qubits within a quantum computer are prone to noise and decoherence, which must be…

量子物理 · 物理学 2024-06-06 Luka Skoric , Dan E. Browne , Kenton M. Barnes , Neil I. Gillespie , Earl T. Campbell

Efficiently supporting long context length is crucial for Transformer models. The quadratic complexity of the self-attention computation plagues traditional Transformers. Sliding window-based static sparse attention mitigates the problem by…

硬件体系结构 · 计算机科学 2024-05-28 Zhenyu Bai , Pranav Dangi , Huize Li , Tulika Mitra

Parallel-across-the method time integration can provide small scale parallelism when solving initial value problems. Spectral deferred corrections (SDC) with a diagonal sweeper, which is closely related to iterated Runge-Kutta methods…

数值分析 · 数学 2025-02-12 Gayatri Čaklović , Thibaut Lunet , Sebastian Götschel , Daniel Ruprecht

Video super-resolution (VSR) is the task of restoring high-resolution frames from a sequence of low-resolution inputs. Different from single image super-resolution, VSR can utilize frames' temporal information to reconstruct results with…

图像与视频处理 · 电气工程与系统科学 2022-08-25 Wenyi Lian , Wenjing Lian

Window decoding, first proposed to reduce decoding complexity for real-time decoding, is an essential component to realize scalable, universal-fault tolerant computation. Prior work has focused on improving throughput through…

量子物理 · 物理学 2026-05-05 Tina Oberoi , Joshua Viszlai , Frederic T. Chong

We investigate the use of wavelet-space feature decomposition in neural super-resolution for rendering pipelines. Building on recent neural upscaling frameworks, we introduce a formulation that predicts stationary wavelet coefficients…

图形学 · 计算机科学 2025-09-23 Prateek Poudel , Prashant Aryal , Kirtan Kunwar , Navin Nepal , Dinesh Baniya Kshatri

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that…

图像与视频处理 · 电气工程与系统科学 2023-01-04 Hyomin Choi , Fabien Racape , Shahab Hamidi-Rad , Mateen Ulhaq , Simon Feltman