activity
20182026
most citedStatic and Dynamic Fusion for Multi-modal Cross-ethnicity Face Anti-spoofing

10 citations · 19 across the 24 of their papers we have counts for

collaborators

23 papers

cs.CV2026

MotionPhys: Detecting AI-Generated Videos via Physical Consistency of Optical-Flow Trajectories

Haojin He, Hao Tan, Zichang Tan +2

Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does not necessarily imply physica…

cs.CV2026

Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking

Liying Yang, Hao Mo, Jialun Liu +7

Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacking kinematic coherence and f…

cs.CV2026

PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification

Xinxing Yu, Liying Yang, Hao Mo +4

High-curvature regions in 3D point clouds encapsulate critical fine-grained geometric semantics yet exhibit a distinct long-tail sparsity in their spatial distribution. The inheren…

cs.CV2026

Veritas++: Value-aware On-Policy Distillation for Perception-Enhanced AIGI Detection

Hao Tan, Jun Lan, Zichang Tan +7

The growing capability of image generation models has made synthetic images a routine presence in open media, making robust and generalizable AI-Generated Image (AIGI) detection in…

cs.CV2026

Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction

Tianshun Han, Ziyu Shi, Lijian Liu +7

Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenarios. They often produce unstabl…

cs.CV2026

CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detection

Haoyuan Zhang, Xiangyu Zhu, Li Gao +3

Presentation Attack Detection (PAD) serves as a crucial safeguard for face recognition systems against presentation attacks such as printed photos, replayed videos, and 3D masks. D…