中文
相关论文

相关论文: Lightweight Attentional Feature Fusion: A New Base…

200 篇论文

Temporal Action Localization (TAL) aims to identify actions' start, end, and class labels in untrimmed videos. While recent advancements using transformer networks and Feature Pyramid Networks (FPN) have enhanced visual feature recognition…

计算机视觉与模式识别 · 计算机科学 2023-10-06 Edward Fish , Jon Weinbren , Andrew Gilbert

Video-based person recognition is challenging due to persons being blocked and blurred, and the variation of shooting angle. Previous research always focused on person recognition on still images, ignoring similarity and continuity between…

计算机视觉与模式识别 · 计算机科学 2021-01-01 Fangtao Li , Wenzhe Wang , Zihe Liu , Haoran Wang , Chenghao Yan , Bin Wu

In recent years, deep learning models have demonstrated remarkable success in various domains, such as computer vision, natural language processing, and speech recognition. However, the generalization capabilities of these models can be…

计算机视觉与模式识别 · 计算机科学 2023-04-10 Neelesh Mungoli

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node…

计算机视觉与模式识别 · 计算机科学 2022-11-18 Zhaoliang Chen , Lele Fu , Jie Yao , Wenzhong Guo , Claudia Plant , Shiping Wang

Deep neural networks show great potential for automating various visual quality inspection tasks in manufacturing. However, their applicability is limited in more volatile scenarios, such as remanufacturing, where the inspected products and…

计算机视觉与模式识别 · 计算机科学 2026-02-12 Johannes C. Bauer , Paul Geng , Stephan Trattnig , Petr Dokládal , Rüdiger Daub

Recognition of low-quality face images remains a challenge due to invisible or deformation in partial facial regions. For low-quality images dominated by missing partial facial regions, local region similarity contributes more to face…

计算机视觉与模式识别 · 计算机科学 2024-12-09 Wang Yu , Wei Wei

3D object detection based on LiDAR-camera fusion is becoming an emerging research theme for autonomous driving. However, it has been surprisingly difficult to effectively fuse both modalities without information loss and interference. To…

计算机视觉与模式识别 · 计算机科学 2020-12-09 Guojun Wang , Bin Tian , Yachen Zhang , Long Chen , Dongpu Cao , Jian Wu

We propose MASTAF, a Model-Agnostic Spatio-Temporal Attention Fusion network for few-shot video classification. MASTAF takes input from a general video spatial and temporal representation,e.g., using 2D CNN, 3D CNN, and Video Transformer.…

计算机视觉与模式识别 · 计算机科学 2022-10-18 Rex Liu , Huanle Zhang , Hamed Pirsiavash , Xin Liu

News text classification is a crucial task in natural language processing, essential for organizing and filtering the massive volume of digital content. Traditional methods typically rely on statistical features like term frequencies or…

计算与语言 · 计算机科学 2025-11-24 Mohammad Zare

Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view…

计算机视觉与模式识别 · 计算机科学 2024-05-24 Hongkai Chen , Zixin Luo , Yurun Tian , Xuyang Bai , Ziyu Wang , Lei Zhou , Mingmin Zhen , Tian Fang , David McKinnon , Yanghai Tsin , Long Quan

Regression-based methods have shown high efficiency and effectiveness for multi-view human mesh recovery. The key components of a typical regressor lie in the feature extraction of input views and the fusion of multi-view features. In this…

计算机视觉与模式识别 · 计算机科学 2023-12-19 Kai Jia , Hongwen Zhang , Liang An , Yebin Liu

Event classification is inherently sequential and multimodal. Therefore, deep neural models need to dynamically focus on the most relevant time window and/or modality of a video. In this study, we propose the Multi-level Attention Fusion…

计算机视觉与模式识别 · 计算机科学 2021-06-15 Mathilde Brousmiche , Jean Rouat , Stéphane Dupont

Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore an effective audio-visual fusion strategy for audiovisual…

音频与语音处理 · 电气工程与系统科学 2020-08-07 Liangfa Wei , Jie Zhang , Junfeng Hou , Lirong Dai

A critical challenge to image-text retrieval is how to learn accurate correspondences between images and texts. Most existing methods mainly focus on coarse-grained correspondences based on co-occurrences of semantic objects, while failing…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Guoliang Wang , Yanlei Shang , Yong Chen

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection. However, the inconsistency across different feature scales is a primary limitation for the single-shot detectors based…

计算机视觉与模式识别 · 计算机科学 2019-11-26 Songtao Liu , Di Huang , Yunhong Wang

Automated radiology report generation is essential for improving diagnostic efficiency and reducing the workload of medical professionals. However, existing methods face significant challenges, such as disease class imbalance and…

统计方法学 · 统计学 2025-07-11 Qin Zhou , Guoyan Liang , Xindi Li , Jingyuan Chen , Wang Zhe , Chang Yao , Sai Wu

Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Wenping Jin , Li Zhu , Jing Sun

3D vehicle detection based on multi-modal fusion is an important task of many applications such as autonomous driving. Although significant progress has been made, we still observe two aspects that need to be further improvement: First, the…

计算机视觉与模式识别 · 计算机科学 2020-09-24 Zehan Zhang , Ming Zhang , Zhidong Liang , Xian Zhao , Ming Yang , Wenming Tan , ShiLiang Pu

In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Jingyu Guo , Christos Matsoukas , Fredrik Strand , Kevin Smith

Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval. The core assumption of most methods is that images undergo affine transformations, disregarding more…

计算机视觉与模式识别 · 计算机科学 2023-04-04 Guilherme Potje , Felipe Cadar , Andre Araujo , Renato Martins , Erickson R. Nascimento