HideAndSeg: an AI-based tool with automated prompting for octopus segmentation in natural habitats

Analyzing octopuses in their natural habitats is challenging due to their camouflage capability, rapid changes in skin texture and color, non-rigid body deformations, and frequent occlusions, all of which are compounded by variable underwater lighting and turbidity. Addressing the lack of large-scale annotated datasets, this paper introduces HideAndSeg, a novel, minimally supervised AI-based tool for segmenting videos of octopuses. It establishes a quantitative baseline for this task. HideAndSeg integrates SAM2 with a custom-trained YOLOv11 object detector. First, the user provides point coordinates to generate the initial segmentation masks with SAM2. These masks serve as training data for the YOLO model. After that, our approach fully automates the pipeline by providing a bounding box prompt to SAM2, eliminating the need for further manual intervention. We introduce two unsupervised metrics - temporal consistency $DICE_t$ and new component count $NC_t$ - to quantitatively evaluate segmentation quality and guide mask refinement in the absence of ground-truth data, i.e., real-world information that serves to train, validate, and test AI models. Results show that HideAndSeg achieves satisfactory performance, reducing segmentation noise compared to the manually prompted approach. Our method can re-identify and segment the octopus even after periods of complete occlusion in natural environments, a scenario in which the manually prompted model fails. By reducing the need for manual analysis in real-world scenarios, this work provides a practical tool that paves the way for more efficient behavioral studies of wild cephalopods.

FlowMotion: Target-Predictive Flow Matching for Realistic Text-Driven Human Motion Generation

Achieving highly diverse and perceptually consistent 3D character animations with natural motion and low computational costs remains a challenge in computer animation. Existing methods often struggle to provide the nuanced complexity of human movement, resulting in perceptual inconsistencies and motion artifacts. To tackle these issues, we introduce FlowMotion, a novel approach that leverages Conditional Flow Matching (CFM) for improved motion synthesis. FlowMotion incorporates an innovative training objective that more accurately predicts target motion, reducing the inherent jitter associated with CFM while enhancing stability, realism, and computational efficiency in generating animations. This direct prediction approach enhances the perceptual quality of animations by reducing erratic motion and aligning the training more closely with the dynamic characteristics of human movement. Our experimental results demonstrate that FlowMotion achieves higher balance between motion smoothness and generalization capability while maintaining the computational efficiency inherent in flow matching compared to state-of-the-art methods.