English
Related papers

Related papers: Parallel Context Modeling for Sliding Window Atten…

200 papers

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make…

Machine Learning · Computer Science 2018-11-09 Mitchell Stern , Noam Shazeer , Jakob Uszkoreit

Decoding in a Transformer based language model is inherently sequential as a token's embedding needs to pass through all the layers in the network before the generation of the next token can begin. In this work, we propose a new…

Machine Learning · Computer Science 2025-08-27 Dylan Cutler , Arun Kandoor , Nishanth Dikkala , Nikunj Saunshi , Xin Wang , Rina Panigrahy

Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Yihui He , Jianing Qian , Jianren Wang , Cindy X. Le , Congrui Hetang , Qi Lyu , Wenping Wang , Tianwei Yue

Training neural video codec (NVC) with variable rate is a highly challenging task due to its complex training strategies and model structure. In this paper, we train an efficient variable bitrate neural video codec (EV-NVC) with the…

Multimedia · Computer Science 2025-11-04 Yongcun Hu , Yingzhen Zhai , Jixiang Luo , Wenrui Dai , Dell Zhang , Hongkai Xiong , Xuelong Li

Recently, deep image compression has shown a big progress in terms of coding efficiency and image quality improvement. However, relatively less attention has been put on video compression using deep learning networks. In the paper, we first…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Woonsung Park , Munchurl Kim

The proliferation of high resolution videos posts great storage and bandwidth pressure on cloud video services, driving the development of next-generation video codecs. Despite great progress made in neural video coding, existing approaches…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Yueyu Hu , Chenhao Zhang , Onur G. Guleryuz , Debargha Mukherjee , Yao Wang

Vision Transformers have substantially advanced the capabilities of segmentation models across both image and video domains. Among them, the Swin Transformer stands out for its ability to capture hierarchical, multi-scale representations,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Ka-Wai Yung , Felix J. S. Bragman , Jialang Xu , Imanol Luengo , Danail Stoyanov , Evangelos B. Mazomenos

We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interleaves layers without positional encodings (NoPE) and…

It is well believed that video captioning is a fundamental but challenging task in both computer vision and artificial intelligence fields. The prevalent approach is to map an input video to a variable-length output sentence in a sequence…

Computer Vision and Pattern Recognition · Computer Science 2019-05-06 Jingwen Chen , Yingwei Pan , Yehao Li , Ting Yao , Hongyang Chao , Tao Mei

The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the…

Image and Video Processing · Electrical Eng. & Systems 2022-09-09 Haisheng Fu , Feng Liang

In this paper, we introduce two new methods of mitigating decoder error propagation for low-latency sliding window decoding (SWD) of spatially coupled low density parity check (SC-LDPC) codes. Building on the recently introduced idea of…

Information Theory · Computer Science 2020-04-21 Min Zhu , David G. M. Mitchell , Michael Lentmaier , Daniel J. Costello

In this paper, we study decoding energy reduction opportunities using temporal-domain filtering and subsampling methods. In particular, we study spatiotemporal filtering using a contrast sensitivity function and temporal downscaling, i.e.,…

Image and Video Processing · Electrical Eng. & Systems 2023-06-13 Christian Herglotz , Matthias Kränzler , Robert Ludwig , André Kaup

SOTA decentralized SGD algorithms can overcome the bandwidth bottleneck at the parameter server by using communication collectives like Ring All-Reduce for synchronization. While the parameter updates in distributed SGD may happen…

Machine Learning · Computer Science 2022-11-10 Haoze He , Parijat Dube

We develop an automated video colorization framework that minimizes the flickering of colors across frames. If we apply image colorization techniques to successive frames of a video, they treat each frame as a separate colorization task.…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Thejan Wijesinghe , Chamath Abeysinghe , Chanuka Wijayakoon , Lahiru Jayathilake , Uthayasanker Thayasivam

Prevalent predictive coding-based video compression methods rely on a heavy encoder to reduce temporal redundancy, which makes it challenging to deploy them on resource-constrained devices. Since the 1970s, distributed source coding theory…

Image and Video Processing · Electrical Eng. & Systems 2023-04-04 Xinjie Zhang , Jiawei Shao , Jun Zhang

Streaming video generation (SVG) distills a pretrained bidirectional video diffusion model into an autoregressive model equipped with sliding window attention (SWA). However, SWA inevitably loses distant history during long video…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ruibin Li , Tao Yang , Fangzhou Ai , Tianhe Wu , Shilei Wen , Bingyue Peng , Lei Zhang

This paper presents a learning-based method to improve bi-prediction in video coding. In conventional video coding solutions, the motion compensation of blocks from already decoded reference pictures stands out as the principal tool used to…

Image and Video Processing · Electrical Eng. & Systems 2022-02-08 Franck Galpin , Philippe Bordes , Thierry Dumas , Pavel Nikitin , Fabrice Le Leannec

Motivated by video coding applications, the problem of sequential coding of correlated sources with encoding and/or decoding frame-delays is studied. The fundamental tradeoffs between individual frame rates, individual frame distortions,…

Information Theory · Computer Science 2008-09-30 Nan Ma , Ye Wang , Prakash Ishwar

Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural…

Computation and Language · Computer Science 2017-05-18 Xu Tian , Jun Zhang , Zejun Ma , Yi He , Juan Wei

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the…

Computation and Language · Computer Science 2025-02-06 Andrea Santilli , Silvio Severino , Emilian Postolache , Valentino Maiorca , Michele Mancusi , Riccardo Marin , Emanuele Rodolà
‹ Prev 1 4 5 6 7 8 10 Next ›