Temporal Context Network for Activity Localization in Videos

Abstract

We present a Temporal Context Network (TCN) for precise temporal localization of human activities. Similar to the Faster-RCNN architecture, proposals are placed at equal intervals in a video which span multiple temporal scales. We propose a novel representation for ranking these proposals. Since pooling features only inside a segment is not sufficient to predict activity boundaries, we construct a representation which explicitly captures context around a proposal for ranking it. For each temporal segment inside a proposal, features are uniformly sampled at a pair of scales and are input to a temporal convolutional neural network for classification. After ranking proposals, non-maximum suppression is applied and classification is performed to obtain final detections. TCN outperforms state-of-the-art methods on the ActivityNet dataset and the THUMOS14 dataset.

To appear in ICCV 2017

References in corpus (4)

• Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge
• Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks
• Modeling Context in Referring Expressions
• Finding Action Tubes

Cited by in corpus (6)

• Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
• Decoupling Localization and Classification in Single Shot Temporal Action Detection
• Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
• Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection
• Localizing the Common Action Among a Few Videos
• TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition