{"total":18,"rows":[{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328,"area":"ssm"},{"id":"2403.09626","title":"Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding","created":"2024-03-14","cited_by_count":108,"area":"ssm"},{"id":"2303.14526","title":"Selective Structured State-Spaces for Long-Form Video Understanding","created":"2023-03-25","cited_by_count":105,"area":"ssm"},{"id":"2404.16112","title":"Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges","created":"2024-04-24","cited_by_count":64,"area":"ssm"},{"id":"2407.08476","title":"VideoMamba: Spatio-Temporal Selective State Space Model","created":"2024-07-11","cited_by_count":25,"area":"ssm"},{"id":"2502.19090","title":"EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training","created":"2025-02-26","cited_by_count":11,"area":"ssm"},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"area":"ssm"},{"id":"2407.04184","title":"QueryMamba: A Mamba-Based Encoder-Decoder Architecture with a Statistical Verb-Noun Interaction Module for Video Action Forecasting @ Ego4D Long-Term Action Anticipation Challenge 2024","created":"2024-07-04","cited_by_count":4,"area":"ssm"},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2511.17929","title":"MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection","created":"2025-11-22","cited_by_count":4,"area":"ssm"},{"id":"2411.00151","title":"NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs","created":"2024-10-31","cited_by_count":3,"area":"ssm"},{"id":"2503.12332","title":"VideoMAP: Toward Scalable Mamba-based Video Autoregressive Pretraining","created":"2025-03-16","cited_by_count":3,"area":"ssm"},{"id":"2512.01383","title":"PointNet4D: A Lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications","created":"2025-12-01","cited_by_count":1,"area":"ssm"},{"id":"2408.17081","title":"Stochastic Layer-Wise Shuffle for Improving Vision Mamba Training","created":"2024-08-30","cited_by_count":0,"area":"ssm"},{"id":"2503.20258","title":"Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos","created":"2025-03-26","cited_by_count":0,"area":"ssm"},{"id":"2509.18691","title":"An overview of neural architectures for self-supervised audio representation learning from masked spectrograms","created":"2025-09-23","cited_by_count":0,"area":"ssm"},{"id":"2607.14711","title":"VideoSEMA: a scalable and efficient Mamba-like attention for video understanding","created":"2026-07-16","cited_by_count":0,"area":"ssm"},{"id":"2610.12868","title":"Selective Spatio-Temporal Fruit Inspector (S$^2$FI): A Mamba-based Framework for Rotational Fruit Quality Assessment","created":"2026-10-09","cited_by_count":0,"area":"ssm"}],"next_cursor":null}