Temporal Context Network for Activity Localization in Videos
arXiv:1708.02349
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 (6)
- Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
- Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge
- Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
- Modeling Context in Referring Expressions
- Finding Action Tubes
Cited by in corpus (22)
- Horizontal Pyramid Matching for Person Re-identification
- S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
- Tripping through time: Efficient Localization of Activities in Videos
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization
- Step-by-step Erasion, One-by-one Collection: A Weakly Supervised Temporal Action Detector
- Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
- Multi-granularity Generator for Temporal Action Proposal
- CTAP: Complementary Temporal Action Proposal Generation
- Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection
- LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
- Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
- WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos
- Decoupling Localization and Classification in Single Shot Temporal Action Detection
- Exploring Uncertainty in Conditional Multi-Modal Retrieval Systems
- Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization
- Improved Soccer Action Spotting using both Audio and Video Streams
- Class Semantics-based Attention for Action Detection
- Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
- Localizing the Common Action Among a Few Videos
- Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection
- Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
- TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition