We propose a novel adaptive pipeline for continuous collision detection in cloth simulation. The pipeline consists of four components: bounding volume hierarchy (BVH) update, BVH traversal, a skipping frame session, and elementary test processing. The skipping frame session is activated adaptively for skipping both BVH update and BVH traversal during the process of collision detection. The proposed method improves the performance of collision detection in simulating cloth models comparing to some existing feature-based collision detection techniques, as indicated from experimental results.