CERN: Confidence-Energy Recurrent Network for Group Activity Recognition
arXiv:1704.03058
Abstract
This work is about recognizing human activities occurring in videos at distinct semantic levels, including individual actions, interactions, and group activities. The recognition is realized using a two-level hierarchy of Long Short-Term Memory (LSTM) networks, forming a feed-forward deep architecture, which can be trained end-to-end. In comparison with existing architectures of LSTMs, we make two key contributions giving the name to our approach as Confidence-Energy Recurrent Network -- CERN. First, instead of using the common softmax layer for prediction, we specify a novel energy layer (EL) for estimating the energy of our predictions. Second, rather than finding the common minimum-energy class assignment, which may be numerically unstable under uncertainty, we specify that the EL additionally computes the p-values of the solutions, and in this way estimates the most confident energy minimum. The evaluation on the Collective Activity and Volleyball datasets demonstrates: (i) advantages of our two contributions relative to the common softmax and energy-minimization formulations and (ii) a superior performance relative to the state-of-the-art approaches.
Accepted to IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Energy-based Generative Adversarial Network
- Detecting events and key actors in multi-person videos
- Hierarchical Deep Temporal Models for Group Activity Recognition
- Structured Prediction Energy Networks
- Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition
- Visual Recognition by Counting Instances: A Multi-Instance Cardinality Potential Kernel