Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image
Demirel B, Ozkan H. 2024. Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image. 2024 IEEE International Conference on Image Processing. ICIP: International Conference on Image Processing, 977–983.
Download (ext.)
Conference Paper
| Published
| English
Author
Demirel, BerkerISTA;
Ozkan, Huseyin
Corresponding author has ISTA affiliation
Department
Abstract
Group Activity Recognition (GAR) aims to detect the activity performed by multiple actors in a scene. Prior works model the spatio-temporal features based on the RGB, optical flow or keypoint data types. On the contrary, our hypothesis is that by only using the RGB data without temporality, the performance can be maintained with a negligible loss in accuracy. To that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches. In the visual branch, it extracts the features using attention pooling. In the coordinate branch, it considers the configuration of the players and extracts the spatial information from the box coordinates. Moreover, we analyzed the Volleyball dataset that the recent literature is mostly based on, and systematically reannotated it to emphasize the group concept. Experimental results demonstrated the effectiveness of the proposed model DECOMPL, which delivered the best/second best GAR performance with the reannotations/original annotations among the comparable state-of-the-art methods. Code and new annotations are available at GitHub: https://github.com/berkerdemirel/decompl
Publishing Year
Date Published
2024-11-01
Proceedings Title
2024 IEEE International Conference on Image Processing
Publisher
IEEE
Page
977-983
Conference
ICIP: International Conference on Image Processing
Conference Location
Abu Dhabi, United Arab Emirates
Conference Date
2024-10-27 – 2024-10-30
eISSN
IST-REx-ID
Cite this
Demirel B, Ozkan H. Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image. In: 2024 IEEE International Conference on Image Processing. IEEE; 2024:977-983. doi:10.1109/icip51287.2024.10647499
Demirel, B., & Ozkan, H. (2024). Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image. In 2024 IEEE International Conference on Image Processing (pp. 977–983). Abu Dhabi, United Arab Emirates: IEEE. https://doi.org/10.1109/icip51287.2024.10647499
Demirel, Berker, and Huseyin Ozkan. “Decompl: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image.” In 2024 IEEE International Conference on Image Processing, 977–83. IEEE, 2024. https://doi.org/10.1109/icip51287.2024.10647499.
B. Demirel and H. Ozkan, “Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image,” in 2024 IEEE International Conference on Image Processing, Abu Dhabi, United Arab Emirates, 2024, pp. 977–983.
Demirel B, Ozkan H. 2024. Decompl: Decompositional learning with attention pooling for group activity recognition from a single volleyball image. 2024 IEEE International Conference on Image Processing. ICIP: International Conference on Image Processing, 977–983.
Demirel, Berker, and Huseyin Ozkan. “Decompl: Decompositional Learning with Attention Pooling for Group Activity Recognition from a Single Volleyball Image.” 2024 IEEE International Conference on Image Processing, IEEE, 2024, pp. 977–83, doi:10.1109/icip51287.2024.10647499.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level

Export
Marked PublicationsOpen Data ISTA Research Explorer
Sources
arXiv 2303.06439