The field of computer vision is witnessing significant advancements in human modeling and gait recognition. Researchers are focusing on developing innovative methods to improve the accuracy and robustness of gait recognition systems, particularly in wild datasets where spatio-temporal distribution inconsistencies are prevalent. Another area of research is the reconstruction of personalized 3D human avatars with realistic animation from few images, which has the potential to revolutionize various applications such as video games, film, and virtual reality. Furthermore, there is a growing interest in reconstructing simulation-ready garments with intricate appearance, which can be used for simulating garments on novel poses and garment relighting. Noteworthy papers in this area include DAGait, which proposes a skeleton-guided silhouette alignment strategy for gait recognition, and FRESA, which presents a novel method for reconstructing personalized 3D human avatars with realistic animation from few images. Additionally, PGC introduces a physics-based approach to reconstruct simulation-ready garments, and Reconstructing Humans with a Biomechanically Accurate Skeleton presents a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. These papers demonstrate significant improvements over state-of-the-art methods and have the potential to advance the field of computer vision.