SOTAVerified

Action Classification

Image source: The Kinetics Human Action Video Dataset

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–400 of 457 papers

TitleStatusHype
Video Classification with Channel-Separated Convolutional NetworksCode0
VideoBERT: A Joint Model for Video and Language Representation LearningCode0
Activity Driven Weakly Supervised Object Detection—0
StartNet: Online Detection of Action Start in Untrimmed Videos—0
Saliency Tubes: Visual Explanations for Spatio-Temporal ConvolutionsCode0
DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition—0
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network—0
D3D: Distilled 3D Networks for Video Action RecognitionCode0
Multi-Level Sequence GAN for Group Activity Recognition—0
Long-Term Feature Banks for Detailed Video UnderstandingCode0
A^2-Nets: Double Attention NetworksCode0
Graph-Based Global Reasoning NetworksCode0
Evolving Space-Time Neural Architectures for Videos—0
A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos—0
Informed Democracy: Voting-based Novelty Detection for Action Recognition—0
A^2-Nets: Double Attention Networks—0
Representation Flow for Action RecognitionCode0
A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity ModelingCode0
Predicting Action Tubes—0
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification—0
A Short Note about Kinetics-600Code0
Multi-Fiber Networks for Video Recognition—0
Actor-Centric Relation Network—0
Spatio-Temporal Channel Correlation Networks for Action Classification—0
Modality Distillation with Multiple Stream Networks for Action RecognitionCode0
Videos as Space-Time Region Graphs—0
VideoCapsuleNet: A Simplified Network for Action Detection—0
Action Verb Corpus—0
ECO: Efficient Convolutional Network for Online Video UnderstandingCode0
Rethinking the Faster R-CNN Architecture for Temporal Action Localization—0
Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture RecognitionCode0
M-PACT: An Open Source Platform for Repeatable Activity Classification ResearchCode0
Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks—0
End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding—0
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal LocalizationCode0
Actionable Email Intent Modeling with Reparametrized RNNs—0
Weakly Supervised Action Localization by Sparse Temporal Pooling NetworkCode0
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video ClassificationCode0
Compressed Video Action RecognitionCode0
Graph Distillation for Action Detection with Privileged ModalitiesCode0
Highly Efficient Human Action Recognition with Quantum Genetic Algorithm Optimized Support Vector Machine—0
Hierarchical Video Generation from Orthogonal Information: Optical Flow and TextureCode0
Appearance-and-Relation Networks for Video ClassificationCode0
Temporal Relational Reasoning in VideosCode0
Attend and Interact: Higher-Order Object Interactions for Video Understanding—0
Flip-Invariant Motion Representation—0
Learning Gating ConvNet for Two-Stream based Methods in Action RecognitionCode0
Action Classification and Highlighting in Videos—0
Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification—0
Unsupervised Video Understanding by Reconciliation of Posture Similarities—0
Show:102550
← PrevPage 8 of 10Next →

No leaderboard results yet.