13.6.15 Mamba Models, Structured State Space Models

Gu, A.[Albert], Dao, T.[Tri],
Mamba: Linear-Time Sequence Modeling with Selective State Spaces,
2023.
DOI Link Structured state space models (SSMs). Foundation Models. BibRef 0000

Huang, L.B.[Ling-Bo], Chen, Y.S.[Yu-Shi], He, X.[Xin],
Spectral-Spatial Mamba for Hyperspectral Image Classification,
RS(16), No. 13, 2024, pp. 2449.
DOI Link 2407
BibRef

Liu, F.X.[Fei-Xiang], Wen, Y.[Yihan], Sun, J.Y.[Jia-Yi], Zhu, P.P.[Pei-Pei], Mao, L.[Liang], Niu, G.C.[Guan-Chong], Li, J.[Jie],
Iterative Mamba Diffusion Change-Detection Model for Remote Sensing,
RS(16), No. 19, 2024, pp. 3651.
DOI Link 2410
BibRef

Wang, H.Z.[Hong-Zhu], Ye, Z.[Zhaoyi], Xu, C.[Chuan], Mei, L.[Liye], Lei, C.[Cheng], Wang, D.[Du],
TTMGNet: Tree Topology Mamba-Guided Network Collaborative Hierarchical Incremental Aggregation for Change Detection,
RS(16), No. 21, 2024, pp. 4068.
DOI Link 2411
BibRef

Zhou, P.[Pengbo], An, L.[Li], Wang, Y.[Yong], Geng, G.H.[Guo-Hua],
MLGTM: Multi-Scale Local Geometric Transformer-Mamba Application in Terracotta Warriors Point Cloud Classification,
RS(16), No. 16, 2024, pp. 2920.
DOI Link 2408
BibRef

Li, S.[Sai], Huang, S.[Shuo],
AFA-Mamba: Adaptive Feature Alignment with Global-Local Mamba for Hyperspectral and LiDAR Data Classification,
RS(16), No. 21, 2024, pp. 4050.
DOI Link 2411
BibRef

Zhang, J.[Junyi], Chen, R.[Renwen], Liu, F.[Fei], Liu, H.[Hao], Zheng, B.[Boyu], Hu, C.Y.[Chen-Yu],
DC-Mamba: A Novel Network for Enhanced Remote Sensing Change Detection in Difficult Cases,
RS(16), No. 22, 2024, pp. 4186.
DOI Link 2412
BibRef

Zhu, Q.W.[Qi-Wei], Zhang, G.J.[Guo-Jing], Zou, X.C.[Xue-Chao], Wang, X.Y.[Xiao-Ying], Huang, J.Q.[Jian-Qiang], Li, X.[Xilai],
ConvMambaSR: Leveraging State-Space Models and CNNs in a Dual-Branch Architecture for Remote Sensing Imagery Super-Resolution,
RS(16), No. 17, 2024, pp. 3254.
DOI Link 2409
BibRef

Zhang, Q.[Qi], Geng, G.H.[Guo-Hua], Zhou, P.[Pengbo], Liu, Q.L.[Qing-Lin], Wang, Y.[Yong], Li, K.[Kang],
Link Aggregation for Skip Connection-Mamba: Remote Sensing Image Segmentation Network Based on Link Aggregation Mamba,
RS(16), No. 19, 2024, pp. 3622.
DOI Link 2410
BibRef

Hu, K.Q.[Kai-Qi], Xu, C.[Chudong],
LPAM: A lightweight medical segmentation network based on Mamba improved by prompt attention,
IET-IPR(18), No. 12, 2024, pp. 3545-3555.
DOI Link 2411
biomedical imaging, convolutional neural nets BibRef

Ding, H.[Hao], Xia, B.[Bo], Liu, W.L.[Wei-Lin], Zhang, Z.[Zekai], Zhang, J.L.[Jing-Lin], Wang, X.[Xing], Xu, S.[Sen],
A Novel Mamba Architecture with a Semantic Transformer for Efficient Real-Time Remote Sensing Semantic Segmentation,
RS(16), No. 14, 2024, pp. 2620.
DOI Link 2408
BibRef

Tang, W.[Wang], Qing, L.B.[Lin-Bo], Li, L.D.[Lin-Dong], Wang, Y.C.[Yu-Chen], Zhu, C.[Ce],
Progressive Graph Reasoning-Based Social Relation Recognition,
MultMed(26), 2024, pp. 6012-6024.
IEEE DOI 2404
Cognition, Visualization, Feature extraction, Psychology, Transformers, Task analysis, Iron, Social relation recognition BibRef

Tang, W.[Wang], Qing, L.B.[Lin-Bo], Wang, P.[Pingyu], Li, L.D.[Lin-Dong], Zhu, C.[Ce],
Hypergraph Mamba Reasoning-Based Social Relation Recognition,
IP(34), 2025, pp. 4814-4829.
IEEE DOI Code:
WWW Link. 2508
Cognition, Visualization, Computational modeling, Transformers, Semantics, Adaptation models, Accuracy, Hands, Data mining, Training, multi-level transformer BibRef

Chen, Y.[Yao], Wang, J.[Jiabao], Wang, P.[Peichao], Zhang, R.[Rui], Li, Y.[Yang],
Vision Mamba Distillation for Low-Resolution Fine-Grained Image Classification,
SPLetters(32), 2025, pp. 1965-1969.
IEEE DOI 2505
Training, Feature extraction, Accuracy, Image classification, Convolution, Visualization, Superresolution, Knowledge engineering, low-resolution BibRef

Salam, A.[Abdus], Mahmud, R.[Rasel], Islam, T.[Tohedul], Mukta, S.[Saddam], Shatabda, S.[Swakkhar],
A Comprehensive Survey on Mamba: Architectures, Challenges, and Opportunities,
Computer(58), No. 8, August 2025, pp. 64-76.
IEEE DOI 2509
Survey, Mamba. Blockchains, Taxonomy, Natural language processing, Computational modeling, Data models, Time series analysis, State-space methods BibRef

Xu, W.[Wei], Wan, Y.[Yi], Zhao, D.[Dong], Zhang, L.[Long],
Efficient Mamba: Overcoming the visual limitations of Mamba with innovative structures,
IVC(161), 2025, pp. 105569.
Elsevier DOI Code:
WWW Link. 2509
State Space Models (SSMs), Self-attention mechanisms, CNN attention, Mamba, Efficient Mamba model BibRef

Wang, F.[Feng], Wang, J.H.[Jia-Hao], Ren, S.[Sucheng], Wei, G.[Guoyizhe], Mei, J.[Jieru], Shao, W.[Wei], Zhou, Y.[Yuyin], Yuille, A.L.[Alan L.], Xie, C.[Cihang],
Mamba-Reg: Vision Mamba Also Needs Registers,
CVPR25(14944-14953)
IEEE DOI Code:
WWW Link. 2508
Accuracy, Semantic segmentation, Scalability, Transformers, Solids, Registers, Recycling BibRef

Lee, S.[Sanghyeok], Choi, J.[Joonmyung], Kim, H.W.J.[Hyun-Woo J.],
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality,
CVPR25(14923-14933)
IEEE DOI Code:
WWW Link. 2508
Training, Runtime, Image coding, Convolution, Neural networks, Throughput, Computational efficiency, Mixers, efficient dl, mamba, efficient and scalable vision BibRef

Wang, S.[Sen], Wang, L.[Le], Zhou, S.P.[San-Ping], Tian, J.Y.[Jing-Yi], Li, J.Y.[Jia-Yi], Sun, H.W.[Hao-Wen], Tang, W.[Wei],
FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation,
CVPR25(12176-12186)
IEEE DOI 2508
Adaptation models, Schedules, Solid modeling, Service robots, Computational modeling, Noise reduction, Dynamic scheduling, Mamba BibRef

Huang, Y.Z.[Yi-Zhou], Cheng, Y.H.[Yi-Hua], Wang, K.Z.[Ke-Zhi],
Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM,
CVPR25(12058-12067)
IEEE DOI 2508
Accuracy, Computational modeling, Predictive models, Transformers, Trajectory, Decoding, Computational efficiency, Vehicle dynamics, motion forecasting BibRef

Zhou, S.[Shiyang], Zeng, H.J.[Hai-Jin], Lu, Y.F.[Yun-Fan], Shao, T.[Tong], Tang, K.[Ke], Chen, Y.Y.[Yong-Yong], Liu, J.[Jie], Su, J.[Jingyong],
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing,
CVPR25(8817-8827)
IEEE DOI Code:
WWW Link. 2508
Performance evaluation, Visualization, Computational modeling, Vision sensors, Transformer cores, Transformers, Mamba BibRef

Bahri, A.[Ali], Yazdanpanah, M.[Moslem], Noori, M.[Mehrdad], Dastani, S.[Sahar], Cheraghalikhani, M.[Milad], Hakim, G.A.V.[Gustavo Adolfo Vargas], Osowiechi, D.[David], Beizaee, F.[Farzad], Ben Ayed, I.[Ismail], Desrosiers, C.[Christian],
Spectral Informed Mamba for Robust Point Cloud Processing,
CVPR25(11799-11809)
IEEE DOI Code:
WWW Link. 2508
Point cloud compression, Manifolds, Laplace equations, Shape, Computational modeling, Self-supervised learning BibRef

Yu, W.H.[Wei-Hao], Wang, X.C.[Xin-Chao],
MambaOut: Do We Really Need Mamba for Vision?*,
CVPR25(4484-4496)
IEEE DOI 2508
Visualization, Image segmentation, Computational modeling, Stacking, Complexity theory, Mixers, Image classification, cnn, Mamba, convolutional neural network BibRef

He, H.Y.[Hao-Yang], Zhang, J.N.[Jiang-Ning], Cai, Y.X.[Yu-Xuan], Chen, H.X.[Hong-Xu], Hu, X.B.[Xia-Bin], Gan, Z.[Zhenye], Wang, Y.B.[Ya-Biao], Wang, C.J.[Cheng-Jie], Wu, Y.S.[Yun-Sheng], Xie, L.[Lei],
MobileMamba: Lightweight Multi-Receptive Visual Mamba Network,
CVPR25(4497-4507)
IEEE DOI 2508
Training, Wavelet transforms, Performance evaluation, Visualization, Computational modeling, Transformers, Throughput, Testing BibRef

Zhang, K.W.[Kai-Wei], Zhu, D.D.[Dan-Dan], Min, X.K.[Xiong-Kuo], Zhai, G.T.[Guang-Tao],
Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes,
CVPR25(16219-16228)
IEEE DOI 2508
Geometry, Visualization, Adaptation models, Scalability, Predictive models, Reliability, Context modeling BibRef

Xie, F.[Fei], Nie, J.H.[Jia-Hao], Tan, Y.J.[Yu-Jin], Zhang, W.K.[Wen-Kang], Zhao, H.S.[Hong-Shen],
Mamba-Adaptor: State Space Model Adaptor for Visual Recognition,
CVPR25(20124-20134)
IEEE DOI 2508
Adaptation models, Visualization, Computational modeling, Transfer learning, Benchmark testing, Kernel, Context modeling BibRef

Dastani, S.[Sahar], Bahri, A.[Ali], Yazdanpanah, M.[Moslem], Noori, M.[Mehrdad], Osowiechi, D.[David], Hakim, G.A.V.[Gustavo Adolfo Vargas], Beizaee, F.[Farzad], Cheraghalikhani, M.[Milad], Mondal, A.K.[Arnab Kumar], Lombaert, H.[Herve], Desrosiers, C.[Christian],
Spectral State Space Model for Rotation-Invariant Visual Representation Learning,
CVPR25(23881-23890)
IEEE DOI Code:
WWW Link. 2508
Representation learning, Visualization, Laplace equations, Runtime, Pipelines, Transformers, Robustness, Biomedical imaging BibRef

Hatamizadeh, A.[Ali], Kautz, J.[Jan],
MambaVision: A Hybrid Mamba-Transformer Vision Backbone,
CVPR25(25261-25270)
IEEE DOI Code:
WWW Link. 2508
Representation learning, Visualization, Accuracy, Systematics, Semantic segmentation, Transformer cores, Transformers, Throughput, instance segmentation BibRef

Guo, H.[Hang], Guo, Y.[Yong], Zha, Y.H.[Yao-Hua], Zhang, Y.[Yulun], Li, W.B.[Wen-Bo], Dai, T.[Tao], Xia, S.T.[Shu-Tao], Li, Y.[Yawei],
MambaIRv2: Attentive State Space Restoration,
CVPR25(28124-28133)
IEEE DOI Code:
WWW Link. 2508
Technological innovation, Codes, Computational modeling, Semantics, Mathematical models, Image restoration, Computational efficiency, Mamba BibRef

Ham, S.[Seokil], Kim, H.S.[Hee-Seon], Woo, S.[Sangmin], Kim, C.[Changick],
Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation,
CVPR25(30106-30115)
IEEE DOI 2508
Adaptation models, Computational modeling, Transfer learning, Benchmark testing, Transformers, State-space methods, Tuning, mamba architecture BibRef

Wang, F.[Feng], Yang, T.[Timing], Yu, Y.D.[Yao-Dong], Ren, S.[Sucheng], Wei, G.[Guoyizhe], Wang, A.T.[Ang-Tian], Shao, W.[Wei], Zhou, Y.[Yuyin], Yuille, A.L.[Alan L.], Xie, C.[Cihang],
Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency,
CVPR25(30157-30166)
IEEE DOI Code:
WWW Link. 2508
Training, Visualization, Computational modeling, Predictive models, Transformers, Throughput, Complexity theory, Standards BibRef

Dang, T.D.Q.[Trung D.Q.], Nguyen, H.H.[Huy Hoang], Tiulpin, A.[Aleksei],
Log-VMAMBA: Local-global Vision Mamba for Medical Image Segmentation,
ACCV24(II: 222-240).
Springer DOI 2412
BibRef

Li, S.[Shufan], Singh, H.[Harkanwar], Grover, A.[Aditya],
Mamba-ND: Selective State Space Modeling for Multi-dimensional Data,
ECCV24(XXXIII: 75-92).
Springer DOI 2412
BibRef

Zhang, Z.[Zeyu], Liu, A.[Akide], Reid, I.D.[Ian D.], Hartley, R.I.[Richard I.], Zhuang, B.[Bohan], Tang, H.[Hao],
Motion Mamba: Efficient and Long Sequence Motion Generation,
ECCV24(I: 265-282).
Springer DOI 2412
BibRef

Yang, Y.[Yuhuan], Ma, C.F.[Chao-Fan], Yao, J.C.[Jiang-Chao], Zhong, Z.[Zhun], Zhang, Y.[Ya], Wang, Y.F.[Yan-Feng],
Remamber: Referring Image Segmentation with Mamba Twister,
ECCV24(X: 108-126).
Springer DOI 2412
BibRef

Lei, X.Y.[Xiao-Yan], zhang, W.L.[Wen-Long], Cao, W.F.[Wei-Feng],
DVMSR: Distillated Vision Mamba for Efficient Super-Resolution,
NTIRE24(6536-6546)
IEEE DOI Code:
WWW Link. 2410
Knowledge engineering, Convolution, Computational modeling, Source coding, Superresolution, Feature extraction, Vision Mamba BibRef

Hu, V.T.[Vincent Tao], Baumann, S.A.[Stefan Andreas], Gui, M.[Ming], Grebenkova, O.[Olga], Ma, P.[Pingchuan], Fischer, J.[Johannes], Ommer, B.[Björn],
ZIGMA: A DIT-Style Zigzag Mamba Diffusion Model,
ECCV24(XXI: 148-166).
Springer DOI 2412
BibRef

Guo, H.[Hang], Li, J.[Jinmin], Dai, T.[Tao], Ouyang, Z.H.[Zhi-Hao], Ren, X.D.[Xu-Dong], Xia, S.T.[Shu-Tao],
Mambair: A Simple Baseline for Image Restoration with State-space Model,
ECCV24(XVIII: 222-241).
Springer DOI 2412
BibRef

Yim, M.[Monyneath], Chiang, J.C.[Jui-Chiu],
Mamba-PCGC: Mamba-Based Point Cloud Geometry Compression,
ICIP24(3554-3560)
IEEE DOI 2411
Point cloud compression, Geometry, Image coding, Codecs, Computational modeling, Bit rate, Mamba BibRef

Tan, J.H.[Jun-Hao], Pei, S.W.[Song-Wen], Qin, W.[Wei], Fu, B.[Bo], Li, X.M.[Xi-Ming], Huang, L.[Libo],
Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement,
ACCV24(IV: 160-175).
Springer DOI 2412
BibRef

Tang, Y.J.[Yu-Jin], Dong, P.[Peijie], Tang, Z.[Zhenheng], Chu, X.W.[Xiao-Wen], Liang, J.W.[Jun-Wei],
VMRNN: Integrating Vision Mamba and LSTM for Efficient and Accurate Spatiotemporal Forecasting,
Precognition24(5663-5673)
IEEE DOI Code:
WWW Link. 2410
Recurrent neural networks, Accuracy, Computational modeling, Microprocessors, Predictive models, State Space Model BibRef

Li, K.C.[Kun-Chang], Li, X.H.[Xin-Hao], Wang, Y.[Yi], He, Y.[Yinan], Wang, Y.[Yali], Wang, L.M.[Li-Min], Qiao, Y.[Yu],
VideoMamba: State Space Model for Efficient Video Understanding,
ECCV24(XXVI: 237-255).
Springer DOI 2412
BibRef

Park, J.[Jinyoung], Kim, H.S.[Hee-Seon], Ko, K.[Kangwook], Kim, M.[Minbeom], Kim, C.[Changick],
Videomamba: Spatio-temporal Selective State Space Model,
ECCV24(XXV: 1-18).
Springer DOI 2412
BibRef

Lin, B.J.[Bai-Jiong], Jiang, W.S.[Wei-Sen], Chen, P.G.[Peng-Guang], Zhang, Y.[Yu], Liu, S.[Shu], Chen, Y.C.[Ying-Cong],
MTMAMBA: Enhancing Multi-Task Dense Scene Understanding by Mamba-based Decoders,
ECCV24(LXX: 314-330).
Springer DOI 2412
BibRef

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
General References for Matching .