SOTAVerified

Action Classification

Image source: The Kinetics Human Action Video Dataset

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 457 papers

TitleStatusHype
SkeleTR: Towards Skeleton-based Action Recognition in the Wild—0
Hierarchical Explanations for Video Action RecognitionCode0
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language ModelsCode2
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation LearningCode1
Learning Video Representations from Large Language ModelsCode2
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video LearningCode1
InternVideo: General Video Foundation Models via Generative and Discriminative LearningCode4
Self-supervised and Weakly Supervised Contrastive Learning for Frame-wise Action Representations—0
Spatio-Temporal Crop Aggregation for Video Representation Learning—0
Post-Processing Temporal Action DetectionCode1
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation LearningCode1
Hand Guided High Resolution Feature Enhancement for Fine-Grained Atomic Action Segmentation within Complex Human Assemblies—0
3d human motion generation from the text via gesture action classification and the autoregressive model—0
AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked AutoencodersCode1
EVA: Exploring the Limits of Masked Visual Representation Learning at ScaleCode0
MARLIN: Masked Autoencoder for facial video Representation LearnINgCode2
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization TasksCode0
Egocentric Audio-Visual Noise Suppression—0
Adversarial Domain Adaptation for Action Recognition Around the Clock—0
Turbo Training with Token Dropout—0
Application-Driven AI Paradigm for Human Action Recognition—0
RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical FlowCode0
Self-supervised Learning for Unintentional Action Prediction—0
Global Semantic Descriptors for Zero-Shot Action RecognitionCode0
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormerCode2
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks—0
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action RecognitionCode0
ViA: View-invariant Skeleton Action Representation Learning via Motion RetargetingCode1
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in VideosCode0
Temporal Action Localization with Multi-temporal Scales—0
Two-person Graph Convolutional Network for Skeleton-based Human Interaction RecognitionCode0
Frozen CLIP Models are Efficient Video LearnersCode1
Expanding Language-Image Pretrained Models for General Video RecognitionCode3
Class-Difficulty Based Methods for Long-Tailed Visual RecognitionCode1
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action RecognitionCode1
MAR: Masked Autoencoders for Efficient Action RecognitionCode1
Is an Object-Centric Video Representation Beneficial for Transfer?—0
ReAct: Temporal Action Detection with Relational QueriesCode1
Revisiting Classifier: Transferring Vision-Language Models for Video RecognitionCode2
ST-Adapter: Parameter-Efficient Image-to-Video Transfer LearningCode1
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action VideosCode1
Context-aware Proposal Network for Temporal Action Detection—0
Stand-Alone Inter-Frame Attention in Video ModelsCode1
MLP-3D: A MLP-like 3D Architecture with Grouped Time MixingCode0
temporal driver action Localization using action classifications methodCode0
Spatial-temporal Concept based Explanation of 3D ConvNetsCode0
A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action DetectorCode1
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D VideosCode1
Do we really need temporal convolutions in action segmentation?Code0
Handcrafted localized phase features for human action recognition—0
Show:102550
← PrevPage 3 of 10Next →

No leaderboard results yet.