Recent advances in EEG-based visual decoding show potential for image generation and editing, yet limited neural data hinder robust representation learning. The exploration of methods to obtain robust EEG representations using self-supervised approaches is still relatively insufficient. This paper introduces a self-supervised masked learning framework SeqMAE - a masked autoencoder processing EEG-derived multiscale spatio-temporal features. By modeling high-level feature space representations, it learns abstract patterns capturing structural-semantic information crucial for image decoding. Unlike raw-data masking strategies, our method preserves temporal continuity while extracting robust high-level representations. Additionally, leveraging the CLIP image encoder as a bridge, the encoder is further optimized to align with the conditional encoding module of Stable Diffusion (SD), facilitating EEG-guided image generation. Experiments show enhanced accuracy and quality in low-cost neural decoding.

Robotic manipulation employs the object detection in images to create a scene awareness and locate an object's pose. In dynamic scenarios, fast multiobject detection and tracking are crucial. Many objects commonly found in household and industrial environments are represented by cylindrical shapes. Thus, it is available for robots to manipulate them through the real-time detection of elliptic shape primitives formed by the circular tops of these objects. We devise an efficient algorithm of the detection of elliptic shape primitives, which in turn enables robust and real-time robotic manipulations of such objects. The proposed algorithm incorporates the information of elliptic edge curvature, splits complex curves into arcs, classifies the arcs into different quadrants of a candidate elliptic shape, determines the quality of arc selection for ellipse fitting, and then retrieves the corresponding elliptic shape primitive. Our algorithm provides either faster or more accurate ellipse detection results than the current state-of-the-art methods, irrespective of challenging scenarios such as occluded or overlapping ellipses. This is verified by performance comparison with six state-of-the-art elliptic shape detection algorithms on four public image datasets. The algorithm has been integrated on robots to demonstrate the ability to carry out accurate robotic manipulations (tracking, grasping, and stacking) of cylindrical objects in real time. We show that the robotic manipulator, empowered by the elliptic shape primitive algorithm, performs well in complex manipulation experiments as well as dynamic scenarios.