paper-with-me

Papers

PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition

2020-06-09 · Yuecong Xu, Haozhi Cao, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See

Long-range spatiotemporal dependencies capturing plays an essential role in improving video features for action recognition. The non-local block inspired by the non-local means is designed to address this challenge and have shown excellent performance. However, the non-local block brings significant increase in computation cost to the original network. It also lacks the ability to model regional correlation in videos. To address the above limitations, we propose Pyramid Non-Local (PNL) module, which extends the non-local block by incorporating regional correlation at multiple scales through a pyramid structured module. This extension upscales the effectiveness of non-local operation by attending to the interaction between different regions. Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83.09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.

📄 PDF Abstract BibTeX arXiv:2006.05091

Code (0)

등록된 구현이 없습니다.

Tasks

Action Recognition

Methods 이 논문이 사용한 방법론

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Non-Local Operation A Non-Local Operation is a component for capturing long-range dependencies with deep neural networks. It is a generalization of the classical non-local mean operation in…
Non-Local Block A Non-Local Block is an image block module used in neural networks that wraps a non-local operation. We can define a…

Similar Papers 제목 키워드 기반

An Enhanced Pyramid Feature Network Based on Long-Range Dependencies for Multi-Organ Medical Image Segmentation

2025-09-29 · Dayu Tan, Cheng Kong, Yansen Su, Hai Chen 외 arxiv

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of…

Medical Image Segmentation

Pyramid-based Mamba Multi-class Unsupervised Anomaly Detection

2025-04-04 · Nasar Iqbal, Niki Martinel

Recent advances in convolutional neural networks (CNNs) and transformer-based methods have improved anomaly detection and localization, but challenges persist in precisely localizing small anomalies. While CNNs face limi…

Anomaly DetectionAnomaly LocalizationMambaMulti-class Anomaly Detection+1

STC-Flow: Spatio-temporal Context-aware Optical Flow Estimation

2020-03-01 · Xiaolin Song, Yuyang Zhao, Jingyu Yang

In this paper, we propose a spatio-temporal contextual network, STC-Flow, for optical flow estimation. Unlike previous optical flow estimation approaches with local pyramid feature extraction and multi-level correlation,…

Optical Flow Estimation

Learning Pyramid-structured Long-range Dependencies for 3D Human Pose Estimation

2025-06-03 · IEEE Transactions on Multimedia 2025 1 · Mingjie Wei, Xuemei Xie, Yutong Zhong, Guangming Shi

Action coordination in human structure is indispensable for the spatial constraints of 2D joints to recover 3D pose. Usually, action coordination is represented as a long-range dependence among body parts. However, there…

3D Human Pose EstimationGraph AttentionPose Estimation

PPMamba: A Pyramid Pooling Local Auxiliary SSM-Based Model for Remote Sensing Image Semantic Segmentation

2024-09-10 · Yin Hu, Xianping Ma, Jialu Sui, Man-on Pun

Semantic segmentation is a vital task in the field of remote sensing (RS). However, conventional convolutional neural network (CNN) and transformer-based models face limitations in capturing long-range dependencies or ar…

MambaSemantic Segmentation