Video Self-Stitching Graph Network for Temporal Action Localization
By Chen Zhao, Ali K. Thabet, Bernard Ghanem. 2020
183 citations recorded by the source corpus.
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion in the datasets, but tend to have the lowest performance. In this paper, we confront the challenge of short actions and propose a multi-level cross-scale solution dubbed as video self-stitching graph network (VSGN). We have two key components in VSGN: video self-stitching (VSS) and cross-scale graph pyramid network (xGPN). In VSS, we focus on a short period of a video and magnify it along the temporal dimension to obtain a larger scale. We stitch the original clip and its magnified counterpart in one input sequence to take advantage of the complementary properties of both scales. The xGPN component further exploits the cross-scale correlations by a pyramid of cross-scale graph networks, each containing a hybrid module to aggregate features from across scales as well as within the same scale. Our VSGN not only enhances the feature representations, but also generates more positive anchors for short actions and more short training samples. Experiments demonstrate that VSGN obviously improves the localization performance of short actions as well as achieving the state-of-the-art overall performance on THUMOS-14 and ActivityNet-v1.3. VSGN code is available at https://github.com/coolbay/VSGN.
Subfields: Computer Vision and Pattern Recognition, Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Kristen Grauman
- Luc Van Gool
- Jitendra Malik
- Trevor Darrell
- Andrew Zisserman
- Dacheng Tao
- Cordelia Schmid
- Ming-Hsuan Yang
In Graph Learning
- Bernard Ghanem
- Antonio Torralba
- Chen Zhao
- Lorenzo Torresani
- Dhruv Batra
- Kristen Grauman
- Christoph Feichtenhofer
- Yanghao Li
Citations in the corpus
- Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Finally, MQ can be seen as activity detection [141, 229, 237] but for the activities of the camera wearer.”
- Egocentric Video-Language Pretraining (2022, methodology): “We extract video features and provide them as input to the VSGN model [49].”