SOTAVerified

Action Classification

Image source: The Kinetics Human Action Video Dataset

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 251–300 of 457 papers

TitleStatusHype
ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked AutoencodersCode0
Weakly Supervised Action Localization by Sparse Temporal Pooling NetworkCode0
What makes ImageNet good for transfer learning?Code0
What Makes Training Multi-Modal Classification Networks Hard?Code0
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action RecognitionCode0
Multi-Modal Three-Stream Network for Action Recognition—0
Fine-grained Action Segmentation using the Semi-Supervised Action GAN—0
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition—0
Feature sampling and partitioning for visual vocabulary generation on large action classification datasets—0
FASTER Recurrent Networks for Efficient Video Classification—0
Natural Language Descriptions of Human Activities Scenes: Corpus Generation and Analysis—0
Representation Learning on Visual-Symbolic Graphs for Video Understanding—0
A Cause and Effect Analysis of Motion Trajectories for Modeling Actions—0
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision—0
FACTS: Fine-Grained Action Classification for Tactical Sports—0
Unsupervised Video Understanding by Reconciliation of Posture Similarities—0
Unsupervised View-Invariant Human Posture Representation—0
Actor-Director-Critic: A Novel Deep Reinforcement Learning Framework—0
Evolving Space-Time Neural Architectures for Videos—0
OmniVec2 - A Novel Transformer based Network for Large Scale Multimodal and Multitask Learning—0
OmniVec: Learning robust representations with cross modal sharing—0
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks—0
Ensembles of Deep Neural Networks for Action Recognition in Still Images—0
Enhancing Video Transformers for Action Understanding with VLM-aided Training—0
End-to-end Generative Pretraining for Multimodal Video Captioning—0
Open Vocabulary Multi-Label Video Classification—0
End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding—0
Optimizing Average Precision using Weakly Supervised Data—0
OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition—0
Egocentric Audio-Visual Noise Suppression—0
Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification—0
PERF-Net: Pose Empowered RGB-Flow Net—0
Activity Driven Weakly Supervised Object Detection—0
Point3D: tracking actions as moving points with 3D CNNs—0
ActionVLAD: Learning spatio-temporal aggregation for action classification—0
Pose is all you need: The pose only group activity recognition system (POGARS)—0
Efficient Optimization for Average Precision SVM—0
Predicting Action Tubes—0
PreViTS: Contrastive Pretraining with Video Tracking Supervision—0
Efficient Feature Extraction, Encoding and Classification for Action Recognition—0
Dual-Model Distillation for Efficient Action Classification with Hybrid Edge-Cloud Solution—0
VicTR: Video-conditioned Text Representations for Activity Recognition—0
Proposal-based Temporal Action Localization with Point-level Supervision—0
Dual coordinate solvers for large-scale structural SVMs—0
Proximal Control of UAVs with Federated Learning for Human-Robot Collaborative Domains—0
Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation—0
A^2-Nets: Double Attention Networks—0
Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition—0
What do 15,000 Object Categories Tell Us About Classifying and Localizing Actions?—0
R-CNNs for Pose Estimation and Action Detection—0
Show:102550
← PrevPage 6 of 10Next →

No leaderboard results yet.