中文
相关论文

相关论文: Spatial-Temporal Attention Network for Open-Set Fi…

200 篇论文

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

计算机视觉与模式识别 · 计算机科学 2018-12-12 Dongliang He , Zhichao Zhou , Chuang Gan , Fu Li , Xiao Liu , Yandong Li , Limin Wang , Shilei Wen

Spike-based Transformer presents a compelling and energy-efficient alternative to traditional Artificial Neural Network (ANN)-based Transformers, achieving impressive results through sparse binary computations. However, existing spike-based…

神经与进化计算 · 计算机科学 2025-03-04 Donghyun Lee , Yuhang Li , Youngeun Kim , Shiting Xiao , Priyadarshini Panda

Hyperspectral image super-resolution has attained widespread prominence to enhance the spatial resolution of hyperspectral images. However, convolution-based methods have encountered challenges in harnessing the global spatial-spectral…

图像与视频处理 · 电气工程与系统科学 2023-11-30 Shi Chen , Lefei Zhang , Liangpei Zhang

How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications.…

计算机视觉与模式识别 · 计算机科学 2021-07-27 Man Yao , Huanhuan Gao , Guangshe Zhao , Dingheng Wang , Yihan Lin , Zhaoxu Yang , Guoqi Li

Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are based on Convolutional Neural Networks (CNNs). Despite…

图像与视频处理 · 电气工程与系统科学 2022-04-12 Renjie Zou , Chunfeng Song , Zhaoxiang Zhang

This paper addresses the task of segmenting class-agnostic objects in semi-supervised setting. Although previous detection based methods achieve relatively good performance, these approaches extract the best proposal by a greedy strategy,…

计算机视觉与模式识别 · 计算机科学 2020-12-11 Daizong Liu , Shuangjie Xu , Xiao-Yang Liu , Zichuan Xu , Wei Wei , Pan Zhou

The Localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS). However, due to lack of intelligence in the traditional transportation system, it can take tremendous…

计算机视觉与模式识别 · 计算机科学 2018-04-09 Sijia Chen , Bin Song , Jie Guo , Xiaojiang Du , Mohsen Guizani

The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-features can usually be distributed in grouped form in the…

计算机视觉与模式识别 · 计算机科学 2019-05-28 Xiang Li , Xiaolin Hu , Jian Yang

Previous methods for dynamic facial expression in the wild are mainly based on Convolutional Neural Networks (CNNs), whose local operations ignore the long-range dependencies in videos. To solve this problem, we propose the spatio-temporal…

计算机视觉与模式识别 · 计算机科学 2022-05-11 Fuyan Ma , Bin Sun , Shutao Li

Skeleton-based gesture recognition methods have achieved high success using Graph Convolutional Network (GCN). In addition, context-dependent adaptive topology as a neighborhood vertex information and attention mechanism leverages a model…

计算机视觉与模式识别 · 计算机科学 2024-04-04 Ikuo Nakamura

Recently, many works have designed wider and deeper networks to achieve higher image super-resolution performance. Despite their outstanding performance, they still suffer from high computational resources, preventing them from directly…

计算机视觉与模式识别 · 计算机科学 2023-03-03 Axi Niu , Pei Wang , Yu Zhu , Jinqiu Sun , Qingsen Yan , Yanning Zhang

Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit…

计算机视觉与模式识别 · 计算机科学 2023-02-06 Jiale Zhang , Yulun Zhang , Jinjin Gu , Yongbing Zhang , Linghe Kong , Xin Yuan

Visual attention modeling has recently gained momentum in developing visual hierarchies provided by Convolutional Neural Networks. Despite recent successes of feedforward processing on the abstraction of concepts form raw images, the…

计算机视觉与模式识别 · 计算机科学 2017-08-23 Mahdi Biparva , John Tsotsos

Attention mechanisms have made significant strides in graph learning, yet they still exhibit notable limitations: local attention faces challenges in capturing long-range information due to the inherent problems of the message-passing…

机器学习 · 计算机科学 2023-10-10 Siyuan Huang , Yunchong Song , Jiayue Zhou , Zhouhan Lin

Intra-class variations in the open world lead to various challenges in classification tasks. To overcome these challenges, fine-grained classification was introduced, and many approaches were proposed. Some rely on locating and using…

计算机视觉与模式识别 · 计算机科学 2023-02-10 Salwa Al Khatib , Mohamed El Amine Boudjoghra , Jameel Hassan

We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…

计算机视觉与模式识别 · 计算机科学 2021-07-27 Eslam Mohamed , Ahmad El-Sallab

We address representation learning for large-scale instance-level image retrieval. Apart from backbone, training pipelines and loss functions, popular approaches have focused on different spatial pooling and attention mechanisms, which are…

计算机视觉与模式识别 · 计算机科学 2021-07-19 Chull Hwan Song , Hye Joo Han , Yannis Avrithis

Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial…

计算机视觉与模式识别 · 计算机科学 2023-04-13 Cheng Tan , Zhangyang Gao , Lirong Wu , Yongjie Xu , Jun Xia , Siyuan Li , Stan Z. Li

Fine-grained action detection is an important task with numerous applications in robotics and human-computer interaction. Existing methods typically utilize a two-stage approach including extraction of local spatio-temporal features…

计算机视觉与模式识别 · 计算机科学 2019-11-11 Khoi-Nguyen C. Mac , Dhiraj Joshi , Raymond A. Yeh , Jinjun Xiong , Rogerio S. Feris , Minh N. Do

For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extracting discriminative local features play a crucial role in…

计算机视觉与模式识别 · 计算机科学 2019-03-01 Tao Hu , Jizheng Xu , Cong Huang , Honggang Qi , Qingming Huang , Yan Lu