Research map / Video / Action recognition
Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
Yunqing Liu, Nan Zhang, Fangjun Wang, Kengo Murata, Takuma Yamamoto, Osafumi Nakayama, Genta Suzuki, Zhiming Tan
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces MOGO, an end-to-end video action detection framework built entirely on Mamba, with a decoder that works with just one Mamba layer.
Problem
Efficient video action detection, seeking a lightweight alternative to Transformer-based models with near-linear complexity.
Approach
An end-to-end video action detector built entirely on the Mamba architecture, with a newly designed Mamba-based decoder that needs only a single Mamba layer to perform action detection.
Experimental setup
Builds on: Mamba
Closest papers by meaning
- Backtrace Mamba: Reviving Critical Temporal Contexts via Hierarchical Memory Compression for Online Action Detection (AAAI 2026 · similarity 0.89)
- End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames (CVPR 2024 · similarity 0.85)
- MobileMamba: Lightweight Multi-Receptive Visual Mamba Network (CVPR 2025 · similarity 0.84)
- MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025 · similarity 0.84)
- Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection? (NeurIPS 2024 · similarity 0.84)
- Context-Enhanced Memory-Refined Transformer for Online Action Detection (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
