{"ID":2871433,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.11394","arxiv_id":"2509.11394","title":"MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation","abstract":"We present MixANT, a novel architecture for stochastic long-term dense anticipation of human activities. While recent State Space Models (SSMs) like Mamba have shown promise through input-dependent selectivity on three key parameters, the critical forget-gate ($\\textbf{A}$ matrix) controlling temporal memory remains static. We address this limitation by introducing a mixture of experts approach that dynamically selects contextually relevant $\\textbf{A}$ matrices based on input features, enhancing representational capacity without sacrificing computational efficiency. Extensive experiments on the 50Salads, Breakfast, and Assembly101 datasets demonstrate that MixANT consistently outperforms state-of-the-art methods across all evaluation settings. Our results highlight the importance of input-dependent forget-gate mechanisms for reliable prediction of human behavior in diverse real-world scenarios.","short_abstract":"We present MixANT, a novel architecture for stochastic long-term dense anticipation of human activities. While recent State Space Models (SSMs) like Mamba have shown promise through input-dependent selectivity on three key parameters, the critical forget-gate ($\\textbf{A}$ matrix) controlling temporal memory remains st...","url_abs":"https://arxiv.org/abs/2509.11394","url_pdf":"https://arxiv.org/pdf/2509.11394v1","authors":"[\"Syed Talal Wasim\",\"Hamid Suleman\",\"Olga Zatsarynna\",\"Muzammal Naseer\",\"Juergen Gall\"]","published":"2025-09-14T19:07:24Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Mixture of Experts\"]","has_code":false}