Loading...
Please wait, while we are loading the content...
Similar Documents
Additional remarks on designing category-level attributes for discriminative visual recognition (2013)
| Content Provider | CiteSeerX |
|---|---|
| Author | Yu, Felix X. Cao, Liangliang Feris, Rogerio S. Smith, John R. Chang, Shih-Fu |
| Abstract | This is the supplementary material for Designing Category-Level Attributes for Discriminative Visual Recognition [3]. 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. 1 Overview of the Proposed Approach Figure 1 provides an overview of the proposed approach. In the offline phase, given a set of images with labels of pre-defined categories (a multiclass dataset), our approach automatically learns a category-attribute matrix, to define the category-level attributes. Then a set of attribute classifiers are learned based on the defined attributes (not shown in the figure). Unlike the previous work [2], in which both the attributes and the category-attribute matrix are pre-defined (as in the “manually defined attributes”), the proposed process is fully automatic. In the online phase, given an image from the novel categories, we can compute the designed category-level attributes. The computed values of three attributes (colored |
| File Format | |
| Language | English |
| Publisher Date | 2013-01-01 |
| Access Restriction | Open |
| Subject Keyword | Category-level Attribute Additional Remark Discriminative Visual Recognition Category-attribute Matrix Approach Figure Zero-shot Learning Supplementary Material Novel Category Semantic Aspect Automatic Attribute Design Computed Value Video Event Modeling Attribute Classifier Previous Work Offline Phase Pre-defined Category Online Phase Additional Experiment Multiclass Dataset Technical Report Attribute Design Algorithm |
| Content Type | Text |
| Resource Type | Technical Report |
