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
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
This is the supplementary material for Designing Category-Level Attributes for Dis-criminative Visua...
Attribute-based representation has shown great promis-es for visual recognition due to its intuitive...
Attribute-based representation has shown great promises for visual recognition due to its intuitive ...
This thesis focuses on one of the most challenging problems in the field of computer vision, i.e. ge...
Attributes of objects such as "square", "metallic", and "red" allow a way for humans to explain or d...
textVisual object category recognition is one of the most challenging problems in computer vision. E...
Few-shot recognition aims to recognize novel categories under low-data regimes. Some recent few-shot...
textVisual object category recognition is one of the most challenging problems in computer vision. E...
Understanding image and video is one of the fundamental problems in the field of computer vision. Tr...
In this letter, we propose a novel approach for learning semantics-driven attributes, which are disc...
Recognition is a deep and fundamental question in computer vision. If approached correctly, object r...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
This is the supplementary material for Designing Category-Level Attributes for Dis-criminative Visua...
Attribute-based representation has shown great promis-es for visual recognition due to its intuitive...
Attribute-based representation has shown great promises for visual recognition due to its intuitive ...
This thesis focuses on one of the most challenging problems in the field of computer vision, i.e. ge...
Attributes of objects such as "square", "metallic", and "red" allow a way for humans to explain or d...
textVisual object category recognition is one of the most challenging problems in computer vision. E...
Few-shot recognition aims to recognize novel categories under low-data regimes. Some recent few-shot...
textVisual object category recognition is one of the most challenging problems in computer vision. E...
Understanding image and video is one of the fundamental problems in the field of computer vision. Tr...
In this letter, we propose a novel approach for learning semantics-driven attributes, which are disc...
Recognition is a deep and fundamental question in computer vision. If approached correctly, object r...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...
Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space be...