{"ID":2838194,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17929","arxiv_id":"2511.17929","title":"MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection","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.","short_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 oth...","url_abs":"https://arxiv.org/abs/2511.17929","url_pdf":"https://arxiv.org/pdf/2511.17929v2","authors":"[\"Hui Lu\",\"Yi Yu\",\"Shijian Lu\",\"Deepu Rajan\",\"Boon Poh Ng\",\"Alex C. Kot\",\"Xudong Jiang\"]","published":"2025-11-22T06:04:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}