# SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization

arXiv: https://arxiv.org/abs/2510.20189 · HTML: https://mlsanity.com/paper/2510.20189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 30 references that are in the map.
- First posted on arXiv 23 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [R-C3D: Region Convolutional 3D Network for Temporal Activity Detection](https://mlsanity.com/paper/1703.07814/) (2017)
- [End-to-end Temporal Action Detection with Transformer](https://mlsanity.com/paper/2106.10271/) (2021)
- [TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals](https://mlsanity.com/paper/1703.06189/) (2017)
- [Fast Learning of Temporal Action Proposal via Dense Boundary Generator](https://mlsanity.com/paper/1911.04127/) (2019)
- [SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity](https://mlsanity.com/paper/1506.02594/) (2015)
- [Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction](https://mlsanity.com/paper/2002.08945/) (2020)
- [Identifying Coordinated Accounts on Social Media through Hidden Influence and Group Behaviours](https://mlsanity.com/paper/2008.11308/) (2020)
- [Early Rumor Detection Using Neural Hawkes Process with a New Benchmark Dataset](https://mlsanity.com/paper/2306.02597/) (2023)
- [Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning](https://mlsanity.com/paper/2308.15169/) (2023)

## Abstract (arXiv)

Temporal Intention Localization (TIL) is crucial for video surveillance, focusing on identifying varying levels of suspicious intentions to improve security monitoring. However, existing discrete classification methods fail to capture the continuous nature of suspicious intentions, limiting early intervention and explainability. In this paper, we propose the Suspicion Progression Analysis Network (SPAN), which shifts from discrete classification to continuous regression, enabling the capture of fluctuating and evolving suspicious intentions. We reveal that suspicion exhibits long-term dependencies and cumulative effects, similar to Temporal Point Process (TPP) theory. Based on these insights, we define a suspicion score formula that models continuous changes while accounting for temporal characteristics. We also introduce Suspicion Coefficient Modulation, which adjusts suspicion coefficients using multimodal information to reflect the varying impacts of suspicious actions. Additionally, the Concept-Anchored Mapping method is proposed to link suspicious actions to predefined intention concepts, offering insights into both the actions and their potential underlying intentions. Extensive experiments on the HAI dataset show that SPAN significantly outperforms existing methods, reducing MSE by 19.8% and improving average mAP by 1.78%. Notably, SPAN achieves a 2.74% mAP gain in low-frequency cases, demonstrating its superior ability to capture subtle behavioral changes. Compared to discrete classification systems, our continuous suspicion modeling approach enables earlier detection and proactive intervention, greatly enhancing system explainability and practical utility in security applications.