Multi-region two-stream R-CNN for action detection

2016-09-17 · European Conference on Computer Vision (ECVV 2016) 2016 9 · Xiaojiang Peng, Cordelia Schmid

We propose a multi-region two-stream R-CNN model for action detection in realistic videos. We start from frame-level action detection based on faster R-CNN [1], and make three contributions: (1) we show that a motion region proposal network generates high-quality proposals , which are complementary to those of an appearance region proposal network; (2) we show that stacking optical flow over several frames significantly improves frame-level action detection; and (3) we embed a multi-region scheme in the faster R-CNN model, which adds complementary information on body parts. We then link frame-level detections with the Viterbi algorithm, and temporally localize an action with the maximum subarray method. Experimental results on the UCF-Sports, J-HMDB and UCF101 action detection datasets show that our approach outperforms the state of the art with a significant margin in both frame-mAP and video-mAP

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Action Detection Action RecognitionRegion ProposalSkeleton Based Action Recognition

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

RoIPool 설명 없음

Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

Improving Action Localization by Progressive Cross-stream Cooperation

2019-05-28 · CVPR 2019 6 · Rui Su, Wanli Ouyang, Luping Zhou, Dong Xu

Spatio-temporal action localization consists of three levels of tasks: spatial localization, action classification, and temporal segmentation. In this work, we propose a new Progressive Cross-stream Cooperation (PCSC) fr…

Action Classification Action Detection Action Localization Spatio-Temporal Action Localization+1

Assisted Refinement Network Based on Channel Information Interaction for Camouflaged and Salient Object Detection

2025-12-12 · Kuan Wang, Yanjun Qin, Mengge Lu, Liejun Wang 외 arxiv

Camouflaged Object Detection (COD) stands as a significant challenge in computer vision, dedicated to identifying and segmenting objects visually highly integrated with their backgrounds. Current mainstream methods have …

Salient Object Detection Object Localization Polyp Segmentation

Spectral-Spatial Synergistic Guided Network for Hyperspectral Salient Object Detection

2026-07-23 · Yanyan Peng, Tingfa Xu, Yao Xiao, Peifu Liu 외 arxiv

Hyperspectral salient object detection aims to identify visually salient regions from hyperspectral images. Existing methods often fail because they fundamentally misunderstand the data, confusing incidental spectral var…

Computational Efficiency Salient Object Detection

Label-Efficient Object Detection via Region Proposal Network Pre-Training

2022-11-16 · Nanqing Dong, Linus Ericsson, Yongxin Yang, Ales Leonardis 외

Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extrac…

Instance Segmentation Object object-detection Object Detection+2

Combining digital data streams and epidemic networks for real time outbreak detection

2025-11-10 · Ruiqi Lyu, Alistair Turcan, Bryan Wilder arxiv

Responding to disease outbreaks requires close surveillance of their trajectories, but outbreak detection is hindered by the high noise in epidemic time series. Aggregating information across data sources has shown great…

Interpretable Machine Learning