Developing Motion Code Embedding for Action Recognition in Videos
원문 초록
In this work, we propose a motion embedding strategy known as motion codes, which is a vectorized representation of motions based on a manipulation's salient mechanical attributes. These motion codes provide a robust motion representation, and they are obtained using a hierarchy of features called the motion taxonomy. We developed and trained a deep neural network model that combines visual and semantic features to identify the features found in our motion taxonomy to embed or annotate videos with motion codes. To demonstrate the potential of motion codes as features for machine learning tasks, we integrated the extracted features from the motion embedding model into the current state-of-the-art action recognition model. The obtained model achieved higher accuracy than the baseline model for the verb classification task on egocentric videos from the EPIC-KITCHENS dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
DeepSTEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans
OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
토론
이 논문과 연결된 포럼 글이 아직 없습니다.