paper-with-me

Papers

Eigen Evolution Pooling for Human Action Recognition

2017-08-17 · Yang Wang, Vinh Tran, Minh Hoai

We introduce Eigen Evolution Pooling, an efficient method to aggregate a sequence of feature vectors. Eigen evolution pooling is designed to produce compact feature representations for a sequence of feature vectors, while maximally preserving as much information about the sequence as possible, especially the temporal evolution of the features over time. Eigen evolution pooling is a general pooling method that can be applied to any sequence of feature vectors, from low-level RGB values to high-level Convolutional Neural Network (CNN) feature vectors. We show that eigen evolution pooling is more effective than average, max, and rank pooling for encoding the dynamics of human actions in video. We demonstrate the power of eigen evolution pooling on UCF101 and Hollywood2 datasets, two human action recognition benchmarks, and achieve state-of-the-art performance.

📄 PDF Abstract BibTeX arXiv:1708.05465

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionTemporal Action Localization

Similar Papers 제목 키워드 기반

Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition

2023-01-01 · CVPR 2023 1 · Xinghan Wang, Xin Xu, Yadong Mu

Skeleton-based human action recognition is becoming increasingly important in a variety of fields. Most existing works train a CNN or GCN based backbone to extract spatial-temporal features, and use temporal average/…

Action RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Recognizing Human Actions as the Evolution of Pose Estimation Maps

2018-06-01 · CVPR 2018 6 · Mengyuan Liu, Junsong Yuan

Most video-based action recognition approaches choose to extract features from the whole video to recognize actions. The cluttered background and non-action motions limit the performances of these methods, since they lac…

Action RecognitionMultimodal Activity RecognitionPose EstimationSkeleton Based Action Recognition+1

High-order Tensor Pooling with Attention for Action Recognition

2021-10-11 · Lei Wang, Ke Sun, Piotr Koniusz

We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor. Tensor descriptors require a robust similarity…

Action RecognitionScene RecognitionVocal Bursts Intensity Prediction

Order-aware Convolutional Pooling for Video Based Action Recognition

2016-01-31 · Peng Wang, Lingqiao Liu, Chunhua Shen, Heng Tao Shen

Most video based action recognition approaches create the video-level representation by temporally pooling the features extracted at each frame. The pooling methods that they adopt, however, usually completely or partial…

Action RecognitionTemporal Action Localization

Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition

2020-06-28 · Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Human action recognition is one of the important fields of computer vision and machine learning. Although various methods have been proposed for 3D action recognition, some of which are basic and some use deep learning, …

3D Action RecognitionAction RecognitionFace RecognitionTemporal Action Localization