From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation

• URL: http://arxiv.org/abs/2604.22839v1
• Date: Tue, 21 Apr 2026 06:43:04 GMT
• Title: From Skeletons to Pixels: Few-Shot Precise Event Spotting via Representation and Prediction Distillation
• Abstract summary: 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Precise Event Spotting (PES) is essential in fast-paced sports such as tennis, where fine-grained events occur within very short temporal windows. Accurate frame-level localization is challenging because of motion blur, subtle action differences, and limited annotated data. We study two complementary distillation strategies for few-shot PES: Adaptive Weight Distillation (AWD), a prediction-level method that adaptively weights teacher supervision on unlabeled data, and Annealed Multimodal Distillation for Few-Shot Event Detection (AMD-FED), a representation-level framework that transfers robust skeleton knowledge into visual modalities through annealed pseudo-labeling. Both methods use multimodal distillation to improve generalization under limited supervision. We evaluate them on F3Set-Tennis(sub) under few-shot k-clip settings, where they consistently outperform single-modality baselines and prior PES approaches. After observing the stronger performance of representation-level distillation on tennis, we further validate AMD-FED on a second sports dataset, Figure Skating, where it also shows robust performance in the k-clip scenario. These results highlight the effectiveness of multimodal distillation, especially representation-level transfer, for few-shot precise event spotting.

Related papers

• Temporal Feature Distillation for Label-Efficient Precise Event Spotting in Sports Videos [12.467078527345128]
  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.
  arXiv  Detail & Related papers  (2026-07-13T01:53:46Z)
• Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target Detection [37.53971188362724]
  Point supervision has become a scalable solution to address dense annotation for infrared small target detection.<n>But its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution and severe sample-distribution imbalance.<n>We propose a physics-induced annotation strategy that expands single-point labels into reliable pseudo-masks.
  arXiv  Detail & Related papers  (2026-05-20T06:08:11Z)
• Few-Shot Precise Event Spotting via Unified Multi-Entity Graph and Distillation [15.108898002423734]
  Event spotting is a key component of sports analytics.<n>Current methods rely on domain-specific, end-to-end training with large labeled datasets.<n>We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES.
  arXiv  Detail & Related papers  (2025-11-18T06:45:42Z)
• PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning [25.271901669843363]
  We propose Progressive Spatio-temporal Token Selection (PSTTS) for event data.<n>PSTTS exploits the temporal-temporal distribution characteristics embedded in raw event data to effectively identify and discard redundant tokens.<n>PSTTS reduces FLOPs by 29-43.6% and increases FPS by 21.6-41.3% the DailyDVS-200 dataset.
  arXiv  Detail & Related papers  (2025-09-26T15:30:00Z)
• AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification [51.525891360380285]
  AHDMIL is an Asymmetric Hierarchical Distillation Multi-Instance Learning framework.<n>It eliminates irrelevant patches through a two-step training process.<n>It consistently outperforms previous state-of-the-art methods in both classification performance and inference speed.
  arXiv  Detail & Related papers  (2025-08-07T07:47:16Z)
• Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression [46.25518274714238]
  Action Assessment (AQA) aims at automatic and fair evaluation of athletic performance.<n>Current methods focus on segmenting video into fixed frames, which disrupts the temporal continuity of sub-actions.<n>We propose a novel action quality assessment method through hierarchically pose-guided multi-stage contrastive regression.
  arXiv  Detail & Related papers  (2025-01-07T10:20:16Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation [61.33010904301476]
  Event cameras sense per-pixel intensity changes and produce asynchronous event streams with high dynamic range and less motion blur. We propose a novel approach, called bfEvDistill, to learn a student network on the unlabeled and unpaired event data. We show that EvDistill achieves significantly better results than the prior works and KD with only events and APS frames.
  arXiv  Detail & Related papers  (2021-11-24T08:48:16Z)
• Few-Shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning [51.03781020616402]
  Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications. We propose a few-shot fine-grained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class. Although progress has been made in coarse-grained actions, existing few-shot recognition methods encounter two issues handling fine-grained actions.
  arXiv  Detail & Related papers  (2021-08-15T02:21:01Z)
• RMS-Net: Regression and Masking for Soccer Event Spotting [52.742046866220484]
  We devise a lightweight and modular network for action spotting, which can simultaneously predict the event label and its temporal offset. When tested on the SoccerNet dataset and using standard features, our full proposal exceeds the current state of the art by 3 Average-mAP points.
  arXiv  Detail & Related papers  (2021-02-15T16:04:18Z)

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.