Action Anticipation with RBF Kernelized Feature Mapping RNN
We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature mapping RNN. Our novel RNN architecture builds upon three effective principles of machine learning, namely parameter sharing, Radial Basis Function kernels and adversarial training. Using only some of the earliest frames of a video, the feature mapping RNN is able to generate future features with a fraction of the parameters needed in traditional RNN. By feeding these future features into a simple multi-layer perceptron facilitated with an RBF kernel layer, we are able to accurately predict the action in the video. In our experiments, we obtain 18% improvement on JHMDB-21 dataset, 6% on UCF101-24 and 13% improvement on UT-Interaction datasets over prior state-of-the-art for action anticipation.
Code (0)
등록된 구현이 없습니다.
Tasks
Action AnticipationSimilar Papers 제목 키워드 기반
Design, Mapping, and Contact Anticipation with 3D-printed Whole-Body Tactile and Proximity Sensors
Robots operating in dynamic and shared environments benefit from anticipating contact before it occurs. We present GenTact-Prox, a fully 3D-printed artificial skin that integrates tactile and proximity sensing for contac…
Contact DetectionUncertainty-aware Action Decoupling Transformer for Action Anticipation
Human action anticipation aims at predicting what people will do in the future based on past observations. In this paper we introduce Uncertainty-aware Action Decoupling Transformer (UADT) for action anticipation. Un…
Action AnticipationPredicting the Future: A Jointly Learnt Model for Action Anticipation
Inspired by human neurological structures for action anticipation, we present an action anticipation model that enables the prediction of plausible future actions by forecasting both the visual and temporal future. In co…
Action AnticipationGenerative Adversarial NetworkLearning Image Descriptors with the Boosting-Trick
In this paper we apply boosting to learn complex non-linear local visual feature representations, drawing inspiration from its successful application to visual object detection. The main goal of local fea…
object-detectionObject DetectionAnticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
Although human action anticipation is a task which is inherently multi-modal, state-of-the-art methods on well known action anticipation datasets leverage this data by applying ensemble methods and averaging scores of un…
Action Anticipation