DST-Mamba: Spatial–Temporal Adapter with Boundary-Aware Mamba for Video Temporal Action Detection
Big Data and Cognitive Computing · 09.07.2026 · 10 (7) · 231
DOI: 10.3390/bdcc10070231 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 09.07.2026. Verfasst von Yicheng Qiu und 1 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JSPS KAKENHI, JST CRONOS.
Abstract (Originalsprache)
Temporal Action Detection (TAD) localizes and classifies action instances within long videos and underlies many downstream video understanding applications. Transformer-based detectors scale poorly to long sequences due to quadratic self-attention, while existing SSM-based variants tend to dilute fine-grained boundary cues during global modeling. To address these limitations, we propose DST-Mamba, a Decoupled Spatial–Temporal Mamba Adapter inserted into a frozen video backbone for parameter-efficient end-to-end TAD. DST-Mamba decouples spatial and temporal modeling into two cooperating branches and explicitly fuses them through cross-branch interaction. Within the temporal branch, we introduce a Temporal Boundary-aware SSM (TB-SSM) with direction-specific forward/backward state-transition matrices, providing a stronger inductive bias for asymmetric action boundaries. Across multiple benchmarks, DST-Mamba consistently outperforms competitive Transformer- and SSM-based baselines while being more computationally efficient.
Förderung
- JSPS KAKENHI
- JST CRONOS
Zitieren
APA
Qiu, Y., & Yanai, K. (2026). DST-Mamba: Spatial–Temporal Adapter with Boundary-Aware Mamba for Video Temporal Action Detection. Big Data and Cognitive Computing, 10(7), 231. https://doi.org/10.3390/bdcc10070231
Vancouver
Qiu Y, Yanai K. DST-Mamba: Spatial–Temporal Adapter with Boundary-Aware Mamba for Video Temporal Action Detection. Big Data and Cognitive Computing. 2026;10(7):231. doi:10.3390/bdcc10070231
BibTeX
@article{Qiu2026,
author = {Qiu, Yicheng and Yanai, Keiji},
title = {DST-Mamba: Spatial–Temporal Adapter with Boundary-Aware Mamba for Video Temporal Action Detection},
journal = {Big Data and Cognitive Computing},
year = {2026},
volume = {10},
number = {7},
pages = {231},
doi = {10.3390/bdcc10070231}
}
EUVIMED