STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
Mamba: Linear-time sequence modeling with selective state spaces
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 7roles
background 2polarities
background 2representative citing papers
A Mamba-based interactive state space model with cross-modal local scanning achieves competitive guided depth super-resolution performance at linear computational cost.
Bilinear input modulation in coupled SSMs improves both memory and bilinear computation, with seq-BIM and p-BIM outperforming gated modulation and uniquely benefiting from larger state dimensions on pendulum and NARMA-10 tasks.
RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
The paper provides the first controllability and observability analysis for structured state-space models, enabling LMI-based controller synthesis via contraction theory and a separation principle for observers and state feedback.
Vision Mamba-based DETR with tailored FPN and token pruning achieves a better performance-efficiency balance than RT-DETR for maritime object detection.
Warp-tiled CUDA kernel for depthwise convolution delivers 3.26x runtime reduction versus naive baseline and 1.29x end-to-end training speedup using counter-free analysis in cloud settings.
citing papers explorer
-
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
STAR improves 1-shot action recognition by up to 8.1% on SSv2-Full through semantic-temporal alignment and Mamba-based prototype refinement.
-
Interactive State Space Model with Cross-Modal Local Scanning for Depth Super-Resolution
A Mamba-based interactive state space model with cross-modal local scanning achieves competitive guided depth super-resolution performance at linear computational cost.
-
Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation
Bilinear input modulation in coupled SSMs improves both memory and bilinear computation, with seq-BIM and p-BIM outperforming gated modulation and uniquely benefiting from larger state dimensions on pendulum and NARMA-10 tasks.
-
RSGMamba: Reliability-Aware Self-Gated State Space Model for Multimodal Semantic Segmentation
RSGMamba introduces a reliability-aware self-gated Mamba block for dynamic cross-modal feature selection in semantic segmentation, delivering state-of-the-art mIoU on RGB-D and RGB-T benchmarks with 48.6M parameters.
-
Controller Design for Structured State-space Models via Contraction Theory
The paper provides the first controllability and observability analysis for structured state-space models, enabling LMI-based controller synthesis via contraction theory and a separation principle for observers and state feedback.
-
Increasing the Efficiency of DETR for Maritime High-Resolution Images
Vision Mamba-based DETR with tailored FPN and token pruning achieves a better performance-efficiency balance than RT-DETR for maritime object detection.
-
CUDA Kernel Optimization and Counter-Free Performance Analysis for Depthwise Convolution in Cloud Environments
Warp-tiled CUDA kernel for depthwise convolution delivers 3.26x runtime reduction versus naive baseline and 1.29x end-to-end training speedup using counter-free analysis in cloud settings.