Papers › Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors

Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors

20 May 2022arXiv:2205.10450archive 2025-07-28

João V. B. Soares, Avijit Shah, Topojoy Biswas

We present a model for temporally precise action spotting in videos, which uses a dense set of detection anchors, predicting a detection confidence and corresponding fine-grained temporal displacement for each anchor. We experiment with two trunk architectures, both of which are able to incorporate large temporal contexts while preserving the smaller-scale features required for precise localization: a one-dimensional version of a u-net, and a Transformer encoder (TE). We also suggest best practices for training models of this kind, by applying Sharpness-Aware Minimization (SAM) and mixup data augmentation. We achieve a new state-of-the-art on SoccerNet-v2, the largest soccer video dataset of its kind, with marked improvements in temporal localization. Additionally, our ablations show: the importance of predicting the temporal displacements; the trade-offs between the u-net and TE trunks; and the benefits of training with SAM and mixup.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yahoo/spivak officialmentioned on GitHubtf report

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

Action SpottingData AugmentationTemporal Localization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEConcatenated Skip ConnectionConvolutionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMax PoolingMixupMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSharpness-Aware MinimizationSoftmaxTransformerU-Net

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