paper-with-me

홈 › Papers

Spatial-Temporal Alignment Network for Action Recognition and Detection

2020-12-04 · Junwei Liang, Liangliang Cao, Xuehan Xiong, Ting Yu, Alexander Hauptmann

This paper studies how to introduce viewpoint-invariant feature representations that can help action recognition and detection. Although we have witnessed great progress of action recognition in the past decade, it remains challenging yet interesting how to efficiently model the geometric variations in large scale datasets. This paper proposes a novel Spatial-Temporal Alignment Network (STAN) that aims to learn geometric invariant representations for action recognition and action detection. The STAN model is very light-weighted and generic, which could be plugged into existing action recognition models like ResNet3D and the SlowFast with a very low extra computational cost. We test our STAN model extensively on AVA, Kinetics-400, AVA-Kinetics, Charades, and Charades-Ego datasets. The experimental results show that the STAN model can consistently improve the state of the arts in both action detection and action recognition tasks. We will release our data, models and code.

📄 PDF Abstract BibTeX arXiv:2012.02426

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionAction Recognition

Similar Papers 제목 키워드 기반

On the Importance of Spatial Relations for Few-shot Action Recognition

2023-08-14 · Yilun Zhang, Yuqian Fu, Xingjun Ma, Lizhe Qi 외

Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been p…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionVideo Recognition

Spatial-Temporal Alignment Network for Action Recognition

2023-08-19 · Jinhui Ye, Junwei Liang

This paper studies introducing viewpoint invariant feature representations in existing action recognition architecture. Despite significant progress in action recognition, efficiently handling geometric variations in lar…

Action Recognition

TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition

2021-07-10 · Shuyuan Li, Huabin Liu, Rui Qian, Yuxi Li 외

Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarit…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionMetric Learning+1

Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition

2023-01-01 · ICCV 2023 1 · Xingyu Liu, Sanping Zhou, Le Wang, Gang Hua

Learning discriminative features from very few labeled samples to identify novel classes has received increasing attention in skeleton-based action recognition. Existing works aim to learn action-specific embeddings …

Action RecognitionFew-Shot Skeleton-Based Action RecognitionSkeleton Based Action Recognition

Action recognition in real-world videos

2020-04-22 · Waqas Sultani, Qazi Ammar Arshad, Chen Chen

The goal of human action recognition is to temporally or spatially localize the human action of interest in video sequences. Temporal localization (i.e. indicating the start and end frames of the action in a video) is re…

Action RecognitionTemporal Action LocalizationTemporal Localization