The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
The paper introduces Multi-task Disentangling Fusion Mamba (MDF-Mamba), a framework for spectral-temporal unmixing of MODIS time series. It uses a disentangling architecture that pairs per-channel spectral experts with a bidirectional Mamba temporal branch, and integrates their outputs via a manifold-constrained hyper-connection (mHCFusion). The method also models endmember variability with pixel-wise learnable weights and employs a multi-task training objective combining supervised abundance estimation, self-supervised spectral reconstruction, and endmember regularization, achieving top performance on most evaluation metrics for Alberta and Saskatchewan datasets.
arXiv:2608. 08207v1 Announce Type: cross Abstract: Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient.
The paper introduces variational decomposition autoencoding (VDA), a framework that biases signal decomposition into latent representations. VDA is realized as variational decomposition autoencoders (DecVAEs), encoder-only networks that learn multiple latent subspaces aligned with time‑frequency characteristics. Experiments on simulated data and three speech datasets show that DecVAEs outperform traditional VAEs in disentanglement quality and robustness, producing factor‑specific latent subspaces when generative factors have distinct spectral signatures.
InfMasking introduces a unified multimodal learning framework that uses Infinite Masking to encourage fusion modules to capture synergistic information across modalities. By randomly masking modality features before fusion and enforcing consistency with an unmasked reference, the method discourages reliance on dominant or shared signals and promotes meaningful cross‑modal interactions. The approach models masked fused representations as Gaussian, optimizing closed‑form variational bounds, and demonstrates improved predictive performance and higher synergy metrics on benchmark datasets.
ChorusTIC is a training‑free foundation model for multivariate time‑series classification that works across heterogeneous channel configurations without updating task‑specific parameters. It uses Random Subchannel Slot Concatenation and a shared dual‑axis encoder to capture temporal and cross‑channel interactions, mapping variable channel counts into a fixed‑width representation. The model is pretrained on synthetic episodes and achieves strong performance on the UEA‑30 and UCR‑128 archives, handling both full‑context and low‑label scenarios without fitting a target‑specific classifier.
Multispectral aerial object detection aims to exploit spectral-spatial cues to address object detection challenges in complex aerial scenes. Existing methods mainly focus on spectral-spatial decouplin...