Abstract
Recent studies for similarity-based self-supervised representation learning tend to consider only fixed temporal coverage from a given video. However, this approach limits that a model learns temporally persistent representations since it cannot reflect spatial and temporal information gaps from resolution variations. To overcome the limitation, this paper proposes a Temporal Adaptive Teacher-Student (TATS) framework that encourages the trained model to be robust on spatio-temporal variations. Our key approach is optimizing similarity-based learning that utilizes several views with dynamic temporal resolutions. From a given video, TATS captures spatio-temporal invariant clues for temporally persistent representation with cross-resolution correspondence between local and global views. Extensive experiments show that our TATS achieves competitive downstream (action recognition and video retrieval) performances on benchmarks (UCF101 and HMDB51).
Original language | English |
---|---|
Title of host publication | AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
ISBN (Electronic) | 9781665463829 |
DOIs | |
Publication status | Published - 2022 |
Event | 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2022 - Virtual, Online, Spain Duration: 2022 Nov 29 → 2022 Dec 2 |
Publication series
Name | AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance |
---|
Conference
Conference | 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2022 |
---|---|
Country/Territory | Spain |
City | Virtual, Online |
Period | 22/11/29 → 22/12/2 |
Bibliographical note
Funding Information:This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2019-0-00079, Artificial Intelligence Graduate School Program(Korea University), No.B0101-15-0266, Development of High Performance Visual BigData Discovery Platform for Large-Scale Realtime Data Analysis).
Publisher Copyright:
© 2022 IEEE.
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Computer Vision and Pattern Recognition
- Information Systems and Management
- Media Technology