September 2026

Radar target recognition via high-resolution range profiles is conventionally closed-set, yet practical deployments must classify known targets while rejecting unseen classes. Toward this open-set obj

This letter proposes contrastive embedding multiplexing (CEM), which multiplexes users in semantic communication systems by designing the signal-space geometry of a shared embedding space instead of a

Low-light images usually suffer from spatially uneven illumination and exposure-dependent feature degradation, where weak structural and chromatic cues are easily masked by dominant intensity variatio

Severe noise in industrial environments often leads to distribution shifts, posing a critical challenge for deep learning-based bearing fault diagnosis. Models trained on clean data typically degrade

Speech emotion recognition (SER) is commonly formulated as direct utterance-to-label classification, leaving the acoustic and semantic evidence behind each prediction implicit. This letter proposes At

Channel estimation is a central bottleneck in BD-RIS-assisted MIMO systems. The richer inter-element coupling that enables large performance gains also makes training and hardware control substantiall

Residual learning-based single image detail enhancement methods often suffer from premature convergence to local optimum due to greedy search strategy. In circuit systems, current preferentially flows

Accurate detection of aircraft skin surface defects is critical for aviation safety. However, conventional networks suffer from high-frequency edge and texture degradation during downsampling when det

Variance stabilization with the generalized Anscombe transform (GAT) enables frozen Gaussian denoisers to process Poisson–Gaussian (PG) RAW noise, but its reliability depends on fitted shot/read-noise

  Maximum-likelihood expectation-maximization (MLEM) is a widely used statistical reconstruction method in computed tomography (CT), but under ill-posed acquisition it progressively amplifies high-fre