paper-with-me

Papers

Two-stream Flow-guided Convolutional Attention Networks for Action Recognition

2017-08-30 · An Tran, Loong-Fah Cheong

This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the human foreground. We thus develop cross-link layers from the temporal network (trained on flows) to the spatial network (trained on RGB frames). These cross-link layers guide the spatial-stream to pay more attention to the human foreground areas and be less affected by background clutter. We obtain promising performances with our approach on the UCF101, HMDB51 and Hollywood2 datasets.

📄 PDF Abstract BibTeX arXiv:1708.09268

Code (1)

antran89/two-stream-fcan 공식 구현

Tasks

Action RecognitionAction Recognition In VideosTemporal Action LocalizationVocal Bursts Valence Prediction

Similar Papers 제목 키워드 기반

3D Convolutional with Attention for Action Recognition

2022-06-05 · Labina Shrestha, Shikha Dubey, Farrukh Olimov, Muhammad Aasim Rafique 외

Human action recognition is one of the challenging tasks in computer vision. The current action recognition methods use computationally expensive models for learning spatio-temporal dependencies of the action. Models uti…

Action RecognitionOptical Flow EstimationTemporal Action Localization

A Heterogeneous Two-Stream Framework for Video Action Recognition with Comparative Fusion Analysis

2026-04-25 · Md. Afzalur Rahaman, Tahmid Rahman arxiv

Most two-stream action recognition networks apply the same convolutional backbone to both RGB and optical flow streams, ignoring the fact that the two modalities have fundamentally different structural properties. Optica…

Action Recognition

Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition

2022-10-10 · Han Chen, Yifan Jiang, Hanseok Ko

Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based metho…

Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection

2022-10-06 · Runmin Cong, Qinwei Lin, Chen Zhang, Chongyi Li 외

Focusing on the issue of how to effectively capture and utilize cross-modality information in RGB-D salient object detection (SOD) task, we present a convolutional neural network (CNN) model, named CIR-Net, based on the …

Decoderobject-detectionObject DetectionRGB-D Salient Object Detection+1

Attention-guided super-resolution of 4D flow MRI in carotid arteries

2026-09-04 · Ali Mokhtari, Dominik Obrist arxiv

Four-dimensional (4D) flow magnetic resonance imaging (MRI) is a powerful non-invasive technique for visualizing and quantifying complex blood flow patterns in vivo. Despite its clinical promise, broader adoption is limi…