用于体育视频中标签高效精确事件定位的时间特征蒸馏
Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos
浏览论文内容
中文总结 AI 辅助
研究体育视频中精确事件定位问题，提出时间特征蒸馏半监督目标及Transformer Gate Shift模块，通过对齐主干特征保留关键线索，实验显示在多数据集上相比基线有显著提升，减少标注数据仍能取得良好效果。
中文摘要 AI 辅助
精确事件定位（PES）需要区分视觉上相似但语义上不同的相邻帧，这与图像分类和粗略动作识别有根本区别。虽然像DINO这样的自蒸馏方法在图像中显示出强大的表示学习能力，但直接应用于PES是无效的。我们提出了时间特征蒸馏，一种半监督目标，对齐时间信息丰富的主干特征而非投影头输出，以保留对帧级定位的运动敏感和边界感知线索。监督热身进一步稳定训练。还引入了Transformer Gate Shift模块。实验表明该方法优于完全监督和半监督基线。
英文摘要
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.
发表机构
- Deakin University（迪肯大学）
- Champion Data（冠军数据公司）
- Paralympics Australia（澳大利亚残奥委员会）
机构由 AI 辅助整理，请以论文原文为准。
