English
Related papers

Related papers: FLASH Viterbi: Fast and Adaptive Viterbi Decoding …

200 papers

We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically "refills" the batch before…

Computation and Language · Computer Science 2021-08-17 Kevin Yang , Violet Yao , John DeNero , Dan Klein

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components…

Machine Learning · Computer Science 2020-02-21 Jeremy Howard , Sylvain Gugger

Scene Text Recognition (STR) is an important and challenging upstream task for building structured information databases, that involves recognizing text within images of natural scenes. Although current state-of-the-art (SOTA) models for…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Xianfu Cheng , Weixiao Zhou , Xiang Li , Jian Yang , Hang Zhang , Tao Sun , Wei Zhang , Yuying Mai , Tongliang Li , Xiaoming Chen , Zhoujun Li

Deformable image registration establishes non-linear spatial correspondences between fixed and moving images. Deep learning-based deformable registration methods have been widely studied in recent years due to their speed advantage over…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Yihao Liu , Junyu Chen , Lianrui Zuo , Aaron Carass , Jerry L. Prince

This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with…

Robotics · Computer Science 2025-01-24 Bingyang Zhou , Chunran Zheng , Ziming Wang , Fangcheng Zhu , Yixi Cai , Fu Zhang

The deep learning-based visual tracking algorithms such as MDNet achieve high performance leveraging to the feature extraction ability of a deep neural network. However, the tracking efficiency of these trackers is not very high due to the…

Computer Vision and Pattern Recognition · Computer Science 2019-11-06 Peidong Liu , Xiyu Yan , Yong Jiang , Shu-Tao Xia

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Zihua Wang , Ruibo Li , Haozhe Du , Joey Tianyi Zhou , Yu Zhang , Xu Yang

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Amelie Royer , Christoph H. Lampert

Spatiotemporal vector retrieval has emerged as a critical paradigm in modern information retrieval, enabling efficient access to massive, heterogeneous data that evolve over both time and space. However, existing spatiotemporal retrieval…

Information Retrieval · Computer Science 2026-01-15 Bingde Hu , Enhao Pan , Wanjing Zhou , Yang Gao , Zunlei Feng , Hao Zhong

Astrophysical transients with rapid development on sub-hour timescales are intrinsically rare. Due to their short durations, events like stellar superflares, optical flashes from gamma-ray bursts, and shock breakouts from young supernovae…

Visual Simultaneous Localization and Mapping (vSLAM) is a prevailing technology for many emerging robotic applications. Achieving real-time SLAM on mobile robotic systems with limited computational resources is challenging because the…

Robotics · Computer Science 2025-02-28 Yao Zhang , Yuyi Mao , Hui Wang , Zhiwen Yu , Song Guo , Jun Zhang , Liang Wang , Bin Guo

Image dehazing poses significant challenges in environmental perception. Recent research mainly focus on deep learning-based methods with single modality, while they may result in severe information loss especially in dense-haze scenarios.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Meng Yu , Te Cui , Haoyang Lu , Yufeng Yue

Vision foundation models (VFMs) have demonstrated remarkable performance across a wide range of downstream tasks. While several VFM adapters have shown promising results by leveraging the prior knowledge of VFMs, we identify two…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yifan Li , Xin Li , Tianqin Li , Wenbin He , Yu Kong , Liu Ren

Reconstructing the 3D shape of a deformable environment from the information captured by a moving depth camera is highly relevant to surgery. The underlying challenge is the fact that simultaneously estimating camera motion and tissue…

Computer Vision and Pattern Recognition · Computer Science 2024-08-09 Guido Caccianiga , Julian Nubert , Cesar Cadena , Marco Hutter , Katherine J. Kuchenbecker

Network slicing is a critical feature in 5G and beyond communication systems, enabling the creation of multiple virtual networks (i.e., slices) on a shared physical network infrastructure. This involves efficiently mapping each slice…

Networking and Internet Architecture · Computer Science 2024-12-10 Quang-Trung Luu , Minh-Thanh Nguyen , Tuan-Anh Do , Michel Kieffer , Van-Dinh Nguyen , Tai-Hung Nguyen , Huu-Thanh Nguyen

Vision Transformers (ViT) have recently demonstrated success across a myriad of computer vision tasks. However, their elevated computational demands pose significant challenges for real-world deployment. While low-rank approximation stands…

Computer Vision and Pattern Recognition · Computer Science 2023-11-08 Chi-Chih Chang , Yuan-Yao Sung , Shixing Yu , Ning-Chi Huang , Diana Marculescu , Kai-Chiang Wu

The usage of linear transformations has great relevance for data decorrelation applications, like image and video compression. In that sense, the discrete Tchebichef transform (DTT) possesses useful coding and decorrelation properties. The…

Multimedia · Computer Science 2024-10-14 P. A. M. Oliveira , R. J. Cintra , F. M. Bayer , S. Kulasekera , A. Madanayake , V. A. Coutinho

Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…

Computation and Language · Computer Science 2025-03-10 Jinwei Yao , Kaiqi Chen , Kexun Zhang , Jiaxuan You , Binhang Yuan , Zeke Wang , Tao Lin

In recent years, there has been a growing emphasis on compressing large pre-trained transformer models for resource-constrained devices. However, traditional pruning methods often leave the embedding layer untouched, leading to model…

Machine Learning · Computer Science 2024-06-13 Oshin Dutta , Ritvik Gupta , Sumeet Agarwal

This paper explores how deep learning techniques can improve visual-based SLAM performance in challenging environments. By combining deep feature extraction and deep matching methods, we introduce a versatile hybrid visual SLAM system…

Robotics · Computer Science 2024-06-05 Zhang Xiao , Shuaixin Li