# AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting

arXiv: https://arxiv.org/abs/2602.22073 · HTML: https://mlsanity.com/paper/2602.22073/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 64 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 30 of 50)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Human Action Recognition and Prediction: A Survey](https://mlsanity.com/paper/1806.11230/) (2018)
- [TriDet: Temporal Action Detection with Relative Boundary Modeling](https://mlsanity.com/paper/2303.07347/) (2023)
- [SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition](https://mlsanity.com/paper/1904.04289/) (2019)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [AR-Net: Adaptive Frame Resolution for Efficient Action Recognition](https://mlsanity.com/paper/2007.15796/) (2020)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [Gate-Shift Networks for Video Action Recognition](https://mlsanity.com/paper/1912.00381/) (2019)
- [Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition](https://mlsanity.com/paper/1907.13369/) (2019)
- [FrameExit: Conditional Early Exiting for Efficient Video Recognition](https://mlsanity.com/paper/2104.13400/) (2021)
- [Mind the Pad -- CNNs can Develop Blind Spots](https://mlsanity.com/paper/2010.02178/) (2020)
- [Spotting Temporally Precise, Fine-Grained Events in Video](https://mlsanity.com/paper/2207.10213/) (2022)
- [AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition](https://mlsanity.com/paper/2112.14238/) (2021)
- [TTNet: Real-time temporal and spatial video analysis of table tennis](https://mlsanity.com/paper/2004.09927/) (2020)
- [Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players](https://mlsanity.com/paper/2008.04524/) (2020)
- [Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection](https://mlsanity.com/paper/2106.14447/) (2021)
- [Temporally Precise Action Spotting in Soccer Videos Using Dense Detection Anchors](https://mlsanity.com/paper/2205.10450/) (2022)
- [OCSampler: Compressing Videos to One Clip with Single-step Sampling](https://mlsanity.com/paper/2201.04388/) (2022)

## Built on by (most cited first, 2 of 2)

- [Towards Athlete Fatigue Assessment from Association Football Videos](https://mlsanity.com/paper/2604.05636/) (2026)
- [SoccerNet 2026 Challenges Results](https://mlsanity.com/paper/2607.07320/) (2026)

## Abstract (arXiv)

Precise Event Spotting aims to localize fast-paced actions or events in videos with high temporal precision, a key task for applications in sports analytics, robotics, and autonomous systems. Existing methods typically process all frames uniformly, overlooking the inherent spatio-temporal redundancy in video data. This leads to redundant computation on non-informative regions while limiting overall efficiency. To remain tractable, they often spatially downsample inputs, losing fine-grained details crucial for precise localization. To address these limitations, we propose AdaSpot, a simple yet effective framework that processes low-resolution videos to extract global task-relevant features while adaptively selecting the most informative region-of-interest in each frame for high-resolution processing. The selection is performed via an unsupervised, task-aware strategy that maintains spatio-temporal consistency across frames and avoids the training instability of learnable alternatives. This design preserves essential fine-grained visual cues with a marginal computational overhead compared to low-resolution-only baselines, while remaining far more efficient than uniform high-resolution processing. Experiments on standard PES benchmarks demonstrate that AdaSpot achieves state-of-the-art performance under strict evaluation metrics (eg, +3.96 and +2.26 mAP@0 frames on Tennis and FineDiving), while also maintaining strong results under looser metrics. Code is available at: hrefhttps://github.com/arturxe2/AdaSpothttps://github.com/arturxe2/AdaSpot.