Nucleus segmentation plays a vital role in medical image analysis. However, existing segmentation methods frequently encounter hurdles, such as the loss of crucial image details during downsampling and issues like noise and spatial displacement. In this study, we propose NucleiFormer, where Haar wavelet transforms are employed in the encoder to replace conventional downsampling techniques. Additionally, we utilize an adaptive feature calibration module to align and calibrate features of different scales, reduce feature redundancy, suppress noise, and enhance the spatial awareness of the model. Extensive experiments validate our model’s superior segmentation performance in accurately delineating nucleus boundaries and minimizing errors.

Automated detection of cervical lesion cell clumps is crucial for cervical cancer screening. However, the dense packing and overlap of cells, caused by adhesion molecules, make detection challenging. To address this issue, we propose the Morphology-Aware Detector (MA-Det). Specifically, by innovatively employing Deformable Convolution, we propose the Dynamic Context Aggregation Module (DCAM) which dynamically captures contextual information, improving the feature representation of lesion cells. To enhance discrimination in high-density regions, we design the Distance-Weighted Interaction Module (DWIM) and Adaptive Morphology-Aware (AMA) loss into the detection head. These components improve spatial awareness by utilizing interactions between cell features and proposals. In particular, our method achieves state-of-the-art performance on the CDetector and CRIC datasets while significantly reducing parameters.

The automated detection of cervical cells plays a vital role in cervical cancer screening. Cancer cells typically exhibit more prominent edge features compared to normal cells. However, during the feature fusion process, blurred edges often lack precise high-frequency information, which hinders the model’s ability to accurately identify cancer cells. To address this challenge, we propose the Hybrid-Domain Feature Pyramid Network (HD-FPN), which enhances the model’s sensitivity to cellular edge information. Specifically, we propose the Frequency-Aware Sampling that preserves critical texture features by leveraging high-frequency decomposition using wavelet transform. Furthermore, we design a multi-domain feature fusion approach to progressively refine edge features and minimize background noise. Our method achieves state-of-the-art performance on the CDetector and CRIC datasets in terms of both detection accuracy and efficiency.

Learned video compression (LVC) methods typically align spatial-temporal transformation features with optical flow to perform motion compensation. However, existing LVC methods typically rely on a single reference feature to provide local detail features. This ignores global structural information, resulting in limited capabilities when dealing with fast motion or occlusion scenarios. In addition, with the encoding of P-frames, errors accumulate, leading to a degradation in reconstruction quality. To address these issues, we propose the Neighbor-Aware Feature-Driven Motion Compensation (NAFD-MC) that utilizes the spatial-temporal correlations of the neighboring features to explore the global structural information and the local detail information. Furthermore, we introduce the Synergy Filtering Module (SFM) to enhance inter-frame consistency and alleviate the error accumulation. Experimental results demonstrate that our method outperforms the H.266/VVC reference software VTM-13.2 in public benchmark datasets.

Dynamic point cloud-based human action recognition has garnered increasing attention due to its inherent advantages in privacy preservation and structural completeness. Current methods typically rely on nested point spatio-temporal convolutions to understand motion semantics in a bottom-up manner, which is intractable for capturing high-fidelity human dynamics disentangled from spatio-temporal interference. Motivated by this, designing a practical spatio-temporal factorization backbone is essential. However, the repeated coarsening of aggregated features along the spatial dimension often leads to the degradation of intrinsic geometric texture relations within point cloud data. Moreover, discretizing continuous visual data into isolated temporal hyperpoints significantly diminishes temporal continuity, resulting in the fragmentation of human action. To circumvent above limitations, we propose a novel Geometry-Prior Cross-Frequency Interactive Fusion Network (Geo-CF2Net). Specifically, we investigate a Spatial-Geometry Pose Prior (SGPP) module, which compensates for pose information loss during spatial downsampling by explicitly modeling geometric constraints among neighboring points. In addition, we elaborate on a Temporal Motion Unit Interactive Coordination (TMIC) module to track the interactive composite semantics of low-frequency steady-state venations and high-frequency transient-state details within a high-dimensional pose evolution flow. Extensive experiments on three public benchmarks substantiate the superiority of Geo-CF2Net over state-of-the-art methods.