AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting

2026-02-25

AI Summary

This work addresses the inefficiency and detail loss in existing video event localization methods, which uniformly process all frames and ignore spatiotemporal redundancy, often sacrificing critical spatial details through downsampling. To overcome these limitations, we propose AdaSpot, a novel framework that combines low-resolution global feature extraction with adaptive high-resolution focusing on informative local regions, thereby achieving both computational efficiency and fine-grained localization while preserving spatiotemporal consistency. The key innovation lies in an unsupervised, task-aware region selection mechanism that circumvents the training instability associated with learnable attention strategies. Experiments demonstrate that AdaSpot achieves state-of-the-art performance, improving mAP@0 by 3.96 and 2.26 on the Tennis and FineDiving datasets, respectively, while significantly reducing computational overhead.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Search and Optimization: Local Search
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

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 \textbf{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 \textbf{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: \href{https://github.com/arturxe2/AdaSpot}{https://github.com/arturxe2/AdaSpot}.

Problem

• Precise Event Spotting
• Temporal Localization
• Spatio-temporal Redundancy
• Computational Efficiency
• Fine-grained Details

Innovation

• AdaSpot
• adaptive region selection
• precise event spotting
• spatio-temporal consistency
• unsupervised task-aware strategy