SOTAVerified

Action Recognition In Videos

Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 124 papers

TitleStatusHype
Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action RecognitionCode0
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action RecognitionCode1
The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks—0
Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in VideosCode1
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
Deep Learning Approaches for Human Action Recognition in Video Data—0
HaltingVT: Adaptive Token Halting Transformer for Efficient Video RecognitionCode0
A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton ModalitiesCode1
DVANet: Disentangling View and Action Features for Multi-View Action RecognitionCode0
CAST: Cross-Attention in Space and Time for Video Action RecognitionCode1
Show:102550
← PrevPage 1 of 13Next →
All datasetsJester (Gesture Recognition)PKU-MMDUCF101Something-Something V2Kinetics 400AVA v2.2FS-Something-Something V2-FullFS-Something-Something V2-SmallSports-1MTHUMOS14ActivityNetAVA v2.1

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LSTM + Pretrained on YT-8MmAP75.6—Unverified