Multiple Granularity Group Interaction Prediction
| Autor: | Xiaokang Yang, Huawei Wei, Bingbing Ni, Taiping Yao, Minsi Wang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
business.industry Feature extraction 02 engineering and technology 010501 environmental sciences computer.software_genre 01 natural sciences Motion (physics) Activity recognition Consistency (database systems) 0202 electrical engineering electronic engineering information engineering Task analysis Trajectory 020201 artificial intelligence & image processing Data mining Granularity Artificial intelligence Focus (optics) business computer 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2018.00239 |
| Popis: | Most human activity analysis works (i.e., recognition or prediction) only focus on a single granularity, i.e., either modelling global motion based on the coarse level movement such as human trajectories or forecasting future detailed action based on body parts' movement such as skeleton motion. In contrast, in this work, we propose a multi-granularity interaction prediction network which integrates both global motion and detailed local action. Built on a bidirectional LSTM network, the proposed method possesses between granularities links which encourage feature sharing as well as cross-feature consistency between both global and local granularity (e.g., trajectory or local action), and in turn predict long-term global location and local dynamics of each individual. We validate our method on several public datasets with promising performance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|