Papers › Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms
Baseline Method for the Sport Task of MediaEval 2022 with 3D CNNs using Attention Mechanisms
Pierre-Etienne Martin
This paper presents the baseline method proposed for the Sports Video task part of the MediaEval 2022 benchmark. This task proposes two subtasks: stroke classification from trimmed videos, and stroke detection from untrimmed videos. This baseline addresses both subtasks. We propose two types of 3D-CNN architectures to solve the two subtasks. Both 3D-CNNs use Spatio-temporal convolutions and attention mechanisms. The architectures and the training process are tailored to solve the addressed subtask. This baseline method is shared publicly online to help the participants in their investigation and alleviate eventually some aspects of the task such as video processing, training method, evaluation and submission routine. The baseline method reaches 86.4% of accuracy with our v2 model for the classification subtask. For the detection subtask, the baseline reaches a mAP of 0.131 and IoU of 0.515 with our v1 model.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Action Classification | TTStroke-21 ME22 | STCNN-V2 (Gaussian decision) | Acc | 0.864 | #2 of 2 | Archive leaderboard | report |
| Action Detection | TTStroke-21 ME22 | STCNN-V2 (Vote decision) | IoU | 0.515 | #1 of 2 | Archive leaderboard | report |
| Action Detection | TTStroke-21 ME22 | STCNN-V2 (Vote decision) | mAP | 0.131 | #1 of 2 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections