This is the supplementary material for Designing Category-Level Attributes for Discriminative Visual Recognition. We first provide an overview of the proposed approach in Section 1. The proof of the theorem is shown in Section 2. Additional remarks of the proposed attribute design algorithm are provided in Section 3. We show additional experiments and applications of the designed attributes for zero-shot learning and video event modeling in Section 4. Finally, we discuss the semantic aspects of automatic attribute design in Section 5. All the figures in this technical report are best viewed in color.
展开▼
