# Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos

arXiv: https://arxiv.org/abs/2607.10998 · HTML: https://mlsanity.com/paper/2607.10998/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [Self-Supervised Learning for Videos: A Survey](https://mlsanity.com/paper/2207.00419/) (2022)
- [Gate-Shift Networks for Video Action Recognition](https://mlsanity.com/paper/1912.00381/) (2019)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Spotting Temporally Precise, Fine-Grained Events in Video](https://mlsanity.com/paper/2207.10213/) (2022)
- [Self-Supervised Learning for Semi-Supervised Temporal Action Proposal](https://mlsanity.com/paper/2104.03214/) (2021)
- [Multiview Pseudo-Labeling for Semi-supervised Learning from Video](https://mlsanity.com/paper/2104.00682/) (2021)
- [Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition](https://mlsanity.com/paper/2109.01305/) (2021)
- [VideoSSL: Semi-Supervised Learning for Video Classification](https://mlsanity.com/paper/2003.00197/) (2020)
- [Semi-Supervised Training to Improve Player and Ball Detection in Soccer](https://mlsanity.com/paper/2204.06859/) (2022)
- [T-DEED: Temporal-Discriminability Enhancer Encoder-Decoder for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2404.05392/) (2024)
- [End-to-End Semi-Supervised Learning for Video Action Detection](https://mlsanity.com/paper/2203.04251/) (2022)
- [ASTRA: An Action Spotting TRAnsformer for Soccer Videos](https://mlsanity.com/paper/2404.01891/) (2024)
- [Semi-Supervised Temporal Action Detection with Proposal-Free Masking](https://mlsanity.com/paper/2207.07059/) (2022)
- [Unifying Global and Local Scene Entities Modelling for Precise Action Spotting](https://mlsanity.com/paper/2404.09951/) (2024)
- [Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance](https://mlsanity.com/paper/2503.00147/) (2025)
- [Temporal DINO: A Self-supervised Video Strategy to Enhance Action Prediction](https://mlsanity.com/paper/2308.04589/) (2023)
- [Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation](https://mlsanity.com/paper/2511.14186/) (2025)
- [Multi-Focus Temporal Shifting for Precise Event Spotting in Sports Videos](https://mlsanity.com/paper/2507.07381/) (2025)

## Abstract (arXiv)

Precise Event Spotting (PES) requires distinguishing visually similar yet semantically distinct adjacent frames, making it fundamentally different from image classification and coarse action recognition. Although self-distillation methods such as DINO have shown strong representation learning ability in images, we find that directly applying them to PES is ineffective: without supervised guidance, subtle but crucial motion cues are often suppressed as noise, leading to representations that are insensitive to precise event boundaries. To address this, we propose Temporal Feature Distillation, a semi-supervised objective that aligns temporally informative backbone features, rather than projection-head outputs, to preserve motion-sensitive and boundary-aware cues for frame-level localization. A supervised warm-up with a ramp-up schedule further stabilizes training by ensuring that meaningful event cues are learned before unlabeled distillation begins. We also introduce Transformer Gate Shift, a multi-scale gated shifting module that injects motion-aware temporal information into Vision Transformers. Experiments on four fine-grained sports benchmarks show consistent improvements over fully supervised and semi-supervised baselines. Under 10% supervision on FSPerf, our method improves mAP by 4.54 points over the strongest competing approach, and with only 80% labeled data, it matches or surpasses the fully supervised 100% baseline on two of the four datasets.