STAR++: Rethinking spatio-temporal cross attention transformer for video action recognition
Dasom Ahn, Sangwon Kim, Byoung Chul Ko
Topics & Concepts
Computer scienceTransformerEncoderSecurity tokenArtificial intelligenceRGB color modelBenchmark (surveying)Pattern recognition (psychology)VoltageComputer networkPhysicsGeographyGeodesyQuantum mechanicsOperating systemHuman Pose and Action RecognitionAnomaly Detection Techniques and ApplicationsHand Gesture Recognition Systems