Recognizing and generating object-state compositions has been a challenging task, especially when generalizing to unseen compositions. In this paper, we study the task of …
Q Wang, L Liu, C Jing, H Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Compositional Zero-Shot Learning (CZSL) aims to train models to recognize novel compositional concepts based on learned concepts such as attribute-object combinations …
K Pham, C Huynh, SN Lim… - Proceedings of the …, 2024 - openaccess.thecvf.com
We study the visual semantic embedding problem for image-text matching. Most existing work utilizes a tailored cross-attention mechanism to perform local alignment across the two …
We study recognizing attributes for objects in visual scenes. We consider attributes to be any phrases that describe an object's physical and semantic properties, and its relationships with …
S Hao, K Han, KYK Wong - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Compositional zero-shot learning (CZSL) aims at learning visual concepts (ie, attributes and objects) from seen compositions and combining concept knowledge into unseen …
We aim to learn to temporally localize object state changes and the corresponding state- modifying actions by observing people interacting with objects in long uncurated web …
Compositional zero-shot learning (CZSL) aims to recognize unseen compositions with prior knowledge of known primitives (attribute and object). Previous works for CZSL often suffer …
In photo editing, it is common practice to remove visual distractions to improve the overall image quality and highlight the primary subject. However, manually selecting and removing …
We aim to learn to temporally localize object state changes and the corresponding state- modifying actions by observing people interacting with objects in long uncurated web …