Pu-Hua Chen

SoccerNet 2026 Challenges Results

Each task and its evaluation protocol is described, the challenge leaderboards are presented, and the leading submissions are summarized, with the aim of documenting the current state of each task as measured on held-out challenge data.

G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification

G2D is proposed, a training-free framework that uses a generative VLM to verify CLIP-retrieved candidates against the image and transfers to DCLIP, WaffleCLIP, and CuPL, supporting a practical interface between discriminative proposal and generative visual reasoning.

Privacy-preserving video anomaly detection via federated learning