Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
arXiv:1707.06750
Abstract
In this notebook paper, we describe our approach in the submission to the temporal action proposal (task 3) and temporal action localization (task 4) of ActivityNet Challenge hosted at CVPR 2017. Since the accuracy in action classification task is already very high (nearly 90% in ActivityNet dataset), we believe that the main bottleneck for temporal action localization is the quality of action proposals. Therefore, we mainly focus on the temporal action proposal task and propose a new proposal model based on temporal convolutional network. Our approach achieves the state-of-the-art performances on both temporal action proposal task and temporal action localization task.
4 pages, Presented at ActivityNet Large Scale Activity Recognition Challenge workshop at CVPR 2017
References in corpus (6)
- Temporal Action Detection with Structured Segment Networks
- CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
- A Pursuit of Temporal Accuracy in General Activity Detection
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
- Cascaded Boundary Regression for Temporal Action Detection
- ActivityNet Challenge 2017 Summary
Cited by in corpus (20)
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation
- Video Action Understanding
- BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
- Multi-granularity Generator for Temporal Action Proposal
- CTAP: Complementary Temporal Action Proposal Generation
- ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
- YH Technologies at ActivityNet Challenge 2018
- DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
- Boundary Content Graph Neural Network for Temporal Action Proposal Generation
- Deep Concept-wise Temporal Convolutional Networks for Action Localization
- Diagnosing Error in Temporal Action Detectors
- Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos
- Learning to Localize Actions from Moments
- Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
- Multi-Level Temporal Pyramid Network for Action Detection
- vireoJD-MM at Activity Detection in Extended Videos
- BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization
- Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2
- Gaussian Temporal Awareness Networks for Action Localization