Y Wei, S Tran, S Xu, B Kang… - Computational …, 2020 - Wiley Online Library
Taking time to identify expected products and waiting for the checkout in a retail store are common scenes we all encounter in our daily lives. The realization of automatic product …
Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training …
Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the …
S Reed, Z Akata, H Lee… - Proceedings of the IEEE …, 2016 - openaccess.thecvf.com
State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best …
We present a novel latent embedding model for learning a compatibility function between image and class embeddings, in the context of zero-shot classification. The proposed …
S Kazemzadeh, V Ordonez, M Matten… - Proceedings of the 2014 …, 2014 - aclanthology.org
In this paper we introduce a new game to crowd-source natural language referring expressions. By designing a two player game, we can both collect and verify referring …
Z Akata, S Reed, D Walter, H Lee… - Proceedings of the …, 2015 - openaccess.thecvf.com
Image classification has advanced significantly in recent years with the availability of large- scale image sets. However, fine-grained classification remains a major challenge due to the …
While 3D object representations are being revived in the context of multi-view object class detection and scene understanding, they have not yet attained wide-spread use in fine …
Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose …