Results 11 to 20 of about 5,777,447 (338)
Review of Human Action Recognition Based on Deep Learning
Jisuanji kexue yu tansuo, 2021 Human action recognition is one of the important topics in video understanding. It is widely used in video surveillance, human-computer interaction, motion analysis, and video information retrieval.
QIAN Huifang, YI Jianping, FU Yunhu
doaj +2 more sources
Fusion Attention for Action Recognition: Integrating Sparse-Dense and Global Attention for Video Action Recognition [PDF]
SensorsConventional approaches to video action recognition perform global attention over the entire video patches, which may be ineffective due to the temporal redundancy of video frames. Recent works on masked video modeling adopt a high-ratio tube masking and
Hyun-Woo Kim, Yong-Suk Choi
doaj +2 more sources
Action recognition using Natural Action Structures [PDF]
BMC Neuroscience, 2012 Humans can detect, recognize, and classify natural actions in a very short time. How this is achieved by the visual system and how to make machines understand human actions have been the focus of neuro-scientific studies and computational modeling in the last several decades.
Zhu Xiaoyuan, Yang Zhiyong, Tsien Joe Z
doaj +3 more sources
Convolutional Block Attention Module–Multimodal Feature-Fusion Action Recognition: Enabling Miner Unsafe Action Recognition [PDF]
SensorsThe unsafe action of miners is one of the main causes of mine accidents. Research on underground miner unsafe action recognition based on computer vision enables relatively accurate real-time recognition of unsafe action among underground miners.
Yu Wang +3 more
doaj +2 more sources
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 Recognition in planning seeks to find agent intentions, goals or activities given a set of observations and a knowledge library (e.g. goal states, plans or domain theories). In this work we introduce the problem of Online Action Recognition. It consists in recognizing, in an open world, the planning action that best explains a partially observable ...
Suárez Hernández, Alejandro +3 more
openaire +7 more sources
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition [PDF]
IEEE International Conference on Computer Vision, 2021 Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition. In GCNs, graph topology dominates feature aggregation and therefore is the key to extracting representative features.
Yuxin Chen +5 more
semanticscholar +1 more source
AIM: Adapting Image Models for Efficient Video Action Recognition [PDF]
International Conference on Learning Representations, 2023 Recent vision transformer based video models mostly follow the ``image pre-training then finetuning"paradigm and have achieved great success on multiple video benchmarks.
Taojiannan Yang +5 more
semanticscholar +1 more source
Revisiting Skeleton-based Action Recognition [PDF]
Computer Vision and Pattern Recognition, 2021 Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt GCNs to extract features on top of human skeletons. Despite the positive results shown in
Haodong Duan +5 more
semanticscholar +1 more source
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning for Action Recognition [PDF]
Neural Information Processing Systems, 2022 Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine-tuning based task adaptation strategy becomes prohibitively ...
Junting Pan +4 more
semanticscholar +1 more source
Constructing Stronger and Faster Baselines for Skeleton-Based Action Recognition [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the recent State-Of-The-Art (SOTA) models for this task tends to be exceedingly sophisticated and ...
Yisheng Song +3 more
semanticscholar +1 more source