TY  - CONF
AU  - Alejandro Cartas
AU  - Petia Radeva
AU  - Mariella Dimiccoli
A2  - ICPR
PY  - 2021//
TI  - Modeling long-term interactions to enhance action recognition
BT  - 25th International Conference on Pattern Recognition
SP  - 10351
EP  - 10358
N2  - In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach that takes as input a primary region roughly corresponding to the user hands and a set of secondary regions potentially corresponding to the interacting objects and calculates the action score through a CNN formulation. This information is then fed to a Hierarchical LongShort-Term Memory Network (HLSTM) that captures temporal dependencies between actions within and across shots. Ablation studies thoroughly validate the proposed approach, showing in particular that both levels of the HLSTM architecture contribute to performance improvement. Furthermore, quantitative comparisons show that the proposed approach outperforms the state-of-the-art in terms of action recognition on standard benchmarks,without relying on motion information
UR  - https://ieeexplore.ieee.org/document/9412148
N1  - MILAB;
ID  - Alejandro Cartas2021
ER  -