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

• URL: http://arxiv.org/abs/2607.10998v1
• Date: Mon, 13 Jul 2026 01:53:46 GMT
• Title: Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos
• Abstract summary: We propose Temporal Feature Distillation to preserve motion-sensitive and boundary-aware cues for frame-level localization.<n>We also introduce Transformer Gate Shift, a multi-scale gated shifting module that injects motion-aware temporal information into Vision Transformers.
• Score: 12.467078527345128
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• See the Change, Keep the Flow: Unsupervised Action Segmentation via Spectral-Temporal Representation Learning [28.808122183182576]
  SpecT-OT is a spectral-temporal representation learning framework built upon an unbalanced optimal transport pseudo-labeling concept.<n>We show that SpecT-OT achieves the best results on 13 of 15 metrics, including 4.1-point MoF and 7.4-point F1 gains over the baseline on Breakfast and Desktop Assembly.
  arXiv  Detail & Related papers  (2026-08-30T07:04:28Z)
• On-Policy Self-Distillation in Diffusion Models [89.32656931795293]
  Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change.<n>We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries.<n>Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators.
  arXiv  Detail & Related papers  (2026-08-25T14:55:24Z)
• Spectral Guidance for Flexible and Efficient Control of Diffusion Models [25.912824880444262]
  We introduce Spectral Guidance, a framework for controlling diffusion models by leveraging the intrinsic geometry of the generative process.<n>We characterize them as the singular functions of a conditional expectation operator and show that they can be learned via a self-supervised objective.
  arXiv  Detail & Related papers  (2026-05-27T15:11:09Z)
• MSACT: Multistage Spatial Alignment for Stable Low-Latency Fine Manipulation [4.439585594082787]
  Real-world fine manipulation, particularly in bimanual manipulation, requires low-latency control and stable visual localization.<n>Existing approaches make different trade-offs: action-chunking policies such as ACT enable low-latency execution and data efficiency but rely on dense visual features without explicit spatial consistency.<n>We introduce a multistage spatial attention module that extracts stable 2D attention points and jointly predicts future attention sequences with a temporal alignment loss.
  arXiv  Detail & Related papers  (2026-05-01T07:35:15Z)
• From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation [0.0]
  We study two complementary distillation strategies for few-shot precise event spotting.<n> Adaptive Weight Distillation (AWD) and Annealed Multimodal Distillation for Few-Shot Event Detection (AMD-FED) are evaluated.
  arXiv  Detail & Related papers  (2026-04-21T06:43:04Z)
• MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning [66.53533434848369]
  We propose a motion-guided self-learning framework that learns densely consistent representations.<n>We improve state-of-the-art by 1% to 6% on six image and video datasets and four evaluation benchmarks.
  arXiv  Detail & Related papers  (2025-06-10T11:20:32Z)
• MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking [58.719310295870024]
  This paper presents an event-based framework for tracking any point.<n>To resolve ambiguities caused by event sparsity, a motion-guidance module incorporates kinematic vectors into the local matching process.<n>The method improves the $Survival_50$ metric by 17.9% over event-only tracking of any point baseline.
  arXiv  Detail & Related papers  (2024-12-02T09:13:29Z)
• FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition [57.17966905865054]
  Real-life applications of action recognition often require a fine-grained understanding of subtle movements. Existing semi-supervised action recognition has mainly focused on coarse-grained action recognition. We propose an Alignability-Verification-based Metric learning technique to effectively discriminate between fine-grained action pairs.
  arXiv  Detail & Related papers  (2024-09-02T20:08:06Z)
• UIA-ViT: Unsupervised Inconsistency-Aware Method based on Vision Transformer for Face Forgery Detection [52.91782218300844]
  We propose a novel Unsupervised Inconsistency-Aware method based on Vision Transformer, called UIA-ViT. Due to the self-attention mechanism, the attention map among patch embeddings naturally represents the consistency relation, making the vision Transformer suitable for the consistency representation learning.
  arXiv  Detail & Related papers  (2022-10-23T15:24:47Z)
• SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery [74.82821342249039]
  We present SatMAE, a pre-training framework for temporal or multi-spectral satellite imagery based on Masked Autoencoder (MAE) To leverage temporal information, we include a temporal embedding along with independently masking image patches across time.
  arXiv  Detail & Related papers  (2022-07-17T01:35:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.