MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection

• URL: http://arxiv.org/abs/2511.17929v1
• Date: Sat, 22 Nov 2025 06:04:29 GMT
• Title: MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
• Authors: Hui Lu, Yi Yu, Shijian Lu, Deepu Rajan, Boon Poh Ng, Alex C. Kot, Xudong Jiang,
• Abstract summary: This paper presents MambaTAD, a new state-space TAD model that introduces long-range modeling and global feature detection capabilities.<n>MambaTAD achieves superior TAD performance consistently across multiple public benchmarks.
• Score: 94.12444452690329
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models such as Mamba have demonstrated potential in TAD due to their long-range modeling capability and linear computational complexity. On the other hand, structured state-space models often face two key challenges in TAD, namely, decay of temporal context due to recursive processing and self-element conflict during global visual context modeling, which become more severe while handling long-span action instances. Additionally, traditional methods for TAD struggle with detecting long-span action instances due to a lack of global awareness and inefficient detection heads. This paper presents MambaTAD, a new state-space TAD model that introduces long-range modeling and global feature detection capabilities for accurate temporal action detection. MambaTAD comprises two novel designs that complement each other with superior TAD performance. First, it introduces a Diagonal-Masked Bidirectional State-Space (DMBSS) module which effectively facilitates global feature fusion and temporal action detection. Second, it introduces a global feature fusion head that refines the detection progressively with multi-granularity features and global awareness. In addition, MambaTAD tackles TAD in an end-to-end one-stage manner using a new state-space temporal adapter(SSTA) which reduces network parameters and computation cost with linear complexity. Extensive experiments show that MambaTAD achieves superior TAD performance consistently across multiple public benchmarks.

Related papers

• DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving [47.573692944838115]
  DriveMamba is a Task-Centric Scalable paradigm for efficient E2E-AD.<n>It integrates sequential task relation modeling, implicit correspondence learning and long-term temporal fusion into a single-stage Unified Mamba decoder.<n>Extensive experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superiority, generalizability and great efficiency of DriveMamba.
  arXiv  Detail & Related papers  (2026-02-09T11:48:29Z)
• AR-MOT: Autoregressive Multi-object Tracking [56.09738000988466]
  We propose a novel autoregressive paradigm that formulates MOT as a sequence generation task within a large language model (LLM) framework.<n>This design enables the model to output structured results through flexible sequence construction, without requiring any task-specific heads.<n>To enhance region-level visual perception, we introduce an Object Tokenizer based on a pretrained detector.
  arXiv  Detail & Related papers  (2026-01-05T09:17:28Z)
• TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition [59.99922360648663]
  TSkel-Mamba is a hybrid Transformer-Mamba framework that effectively captures both spatial and temporal dynamics.<n>The MTI module employs multi-scale Cycle operators to capture cross-channel temporal interactions, a critical factor in action recognition.
  arXiv  Detail & Related papers  (2025-12-12T11:55:16Z)
• High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation [34.450956424316196]
  Modeling high-resolutiontemporal representations is essential for video-based human pose estimation.<n>Current state-of-the-art methods typically have difficulties in balancing global and local dynamic modeling.<n>We present a framework that extends Mamba contexts to separately learn global and local high-resolution representations for VHPE.
  arXiv  Detail & Related papers  (2025-10-13T05:18:27Z)
• StateSpaceDiffuser: Bringing Long Context to Diffusion World Models [52.92249035412797]
  We introduce StateSpaceDiffuser, where a diffusion model is enabled to perform long-context tasks by integrating features from a state-space model.<n>This design restores long-term memory while preserving the high-fidelity synthesis of diffusion models.
  arXiv  Detail & Related papers  (2025-05-28T11:27:54Z)
• MDDFNet: Mamba-based Dynamic Dual Fusion Network for Traffic Sign Detection [0.081585306387285]
  We propose a novel object detection network, Mamba-based Dynamic Dual Fusion Network (MDDFNet) for traffic sign detection.<n>The network integrates a dynamic dual fusion module and a Mamba-based backbone to simultaneously tackle the aforementioned issues.<n>Extensive experiments conducted on the TT100K (Tsinghua-Tencent 100K) datasets demonstrate that MDDFNet outperforms other state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-05-02T14:53:25Z)
• A Deep Learning Framework for Sequence Mining with Bidirectional LSTM and Multi-Scale Attention [11.999319439383918]
  This paper addresses the challenges of mining latent patterns and modeling contextual dependencies in complex sequence data.<n>A sequence pattern mining algorithm is proposed by integrating Bidirectional Long Short-Term Memory (BiLSTM) with a multi-scale attention mechanism.<n>BiLSTM captures both forward and backward dependencies in sequences, enhancing the model's ability to perceive global contextual structures.
  arXiv  Detail & Related papers  (2025-04-21T16:53:02Z)
• MS-Temba : Multi-Scale Temporal Mamba for Efficient Temporal Action Detection [11.534493974662304]
  Temporal Action Detection (TAD) in untrimmed videos requires models that can efficiently process long-duration videos.<n>We propose Multi-Scale Temporal Mamba (MS-Temba), the first Mamba-based architecture specifically designed for densely labeled TAD tasks.<n>MS-Temba achieves state-of-the-art performance on long-duration videos, remains competitive on shorter segments, and reduces model complexity by 88%.
  arXiv  Detail & Related papers  (2025-01-10T17:52:47Z)
• STNMamba: Mamba-based Spatial-Temporal Normality Learning for Video Anomaly Detection [48.997518615379995]
  Video anomaly detection (VAD) has been extensively researched due to its potential for intelligent video systems.<n>Most existing methods based on CNNs and transformers still suffer from substantial computational burdens.<n>We propose a lightweight and effective Mamba-based network named STNMamba to enhance the learning of spatial-temporal normality.
  arXiv  Detail & Related papers  (2024-12-28T08:49:23Z)
• SIGMA: Selective Gated Mamba for Sequential Recommendation [56.85338055215429]
  Mamba, a recent advancement, has exhibited exceptional performance in time series prediction.<n>We introduce a new framework named Selective Gated Mamba ( SIGMA) for Sequential Recommendation.<n>Our results indicate that SIGMA outperforms current models on five real-world datasets.
  arXiv  Detail & Related papers  (2024-08-21T09:12:59Z)
• MambaVT: Spatio-Temporal Contextual Modeling for robust RGB-T Tracking [51.28485682954006]
  We propose a pure Mamba-based framework (MambaVT) to fully exploit intrinsic-temporal contextual modeling for robust visible-thermal tracking. Specifically, we devise the long-range cross-frame integration component to globally adapt to target appearance variations. Experiments show the significant potential of vision Mamba for RGB-T tracking, with MambaVT achieving state-of-the-art performance on four mainstream benchmarks.
  arXiv  Detail & Related papers  (2024-08-15T02:29:00Z)

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.