Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge
arXiv:1607.01979
Abstract
Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.
arXiv comment3 pages, Presented at ActivityNet Large Scale Activity Recognition Challenge workshop at CVPR 2016, Second position in ActivityNet Detection challenge 2016
References in corpus (1)
Cited by in corpus (33)
- Temporal Action Detection with Structured Segment Networks
- A Pursuit of Temporal Accuracy in General Activity Detection
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
- BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation
- Temporal Context Network for Activity Localization in Videos
- Weakly Supervised Action Localization by Sparse Temporal Pooling Network
- Graph Convolutional Networks for Temporal Action Localization
- Rethinking the Faster R-CNN Architecture for Temporal Action Localization
- G-TAD: Sub-Graph Localization for Temporal Action Detection
- BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
- Temporal Action Proposal Generation with Transformers
- Action Shuffling for Weakly Supervised Temporal Localization
- Temporal Context Aggregation Network for Temporal Action Proposal Refinement
- Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
- AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
- Video Self-Stitching Graph Network for Temporal Action Localization
- Deep Concept-wise Temporal Convolutional Networks for Action Localization
- Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
- Budget-Aware Activity Detection with A Recurrent Policy Network
- Learning to Localize Actions from Moments
- Two-Stream Region Convolutional 3D Network for Temporal Activity Detection
- Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
- Temporal Action Localization by Structured Maximal Sums
- Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
- Multi-Level Temporal Pyramid Network for Action Detection
- Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
- Temporal Action Localization using Long Short-Term Dependency
- Learning Temporal Action Proposals With Fewer Labels
- Graph Convolutional Module for Temporal Action Localization in Videos
- Online Spatiotemporal Action Detection and Prediction via Causal Representations
- Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
- Gaussian Temporal Awareness Networks for Action Localization