Mining Mid-level Features for Action Recognition Based on Effective Skeleton Representation
Recently, mid-level features have shown promising performance in computer vision. Mid-level features learned by incorporating class-level information are potentially more discriminative than traditional low-level local features. In this paper, an effective method is proposed to extract mid-level features from Kinect skeletons for 3D human action recognition. Firstly, the orientations of limbs connected by two skeleton joints are computed and each orientation is encoded into one of the 27 states indicating the spatial relationship of the joints. Secondly, limbs are combined into parts and the limb's states are mapped into part states. Finally, frequent pattern mining is employed to mine the most frequent and relevant (discriminative, representative and non-redundant) states of parts in continuous several frames. These parts are referred to as Frequent Local Parts or FLPs. The FLPs allow us to build powerful bag-of-FLP-based action representation. This new representation yields state-of-the-art results on MSR DailyActivity3D and MSR ActionPairs3D.
Code (0)
등록된 구현이 없습니다.
Tasks
3D Action RecognitionAction RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Action2Activity: Recognizing Complex Activities from Sensor Data
As compared to simple actions, activities are much more complex, but semantically consistent with a human's real life. Techniques for action recognition from sensor generated data are mature. However, there has been rela…
Action RecognitionActivity RecognitionMulti-Task LearningTemporal Action LocalizationInteraction Part Mining: A Mid-Level Approach for Fine-Grained Action Recognition
Modeling human-object interactions and manipulating motions lies in the heart of fine-grained action recognition. Previous methods heavily rely on explicit detection of the object being interacted, which requires intensi…
Action RecognitionFine-grained Action RecognitionHuman-Object Interaction DetectionObject+1Multi-Granularity Mutual Refinement Network for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i…
Zero-Shot LearningIntra- and Inter-Action Understanding via Temporal Action Parsing
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard be…
Action ParsingAction RecognitionAction UnderstandingExamining Interpretable Feature Relationships in Deep Networks for Action recognition
A number of recent methods to understand neural networks have focused on quantifying the role of individual features. One such method, NetDissect identifies interpretable features of a model using the Broden dataset of …
Action Recognition