105 citations · 133 across the 9 of their papers we have counts for
9 papers
Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama
Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains importance for large-scale applications, with large number of object classes, since, collec…
Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama
In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insuffic…
Generalized Zero-Shot Recognition based on Visually Semantic Embedding
Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama
We propose a novel Generalized Zero-Shot learning (GZSL) method that is agnostic to both unseen images and unseen semantic vectors during training. Prior works in this context prop…
Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
Hanxiao Wang, Venkatesh Saligrama, Stan Sclaroff +1
We consider the problem of fine-grained classification on an edge camera device that has limited power. The edge device must sparingly interact with the cloud to minimize communica…
Person Re-Identification in Identity Regression Space
Hanxiao Wang, Xiatian Zhu, Shaogang Gong +1
Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size, and Inadaptability over…
Zero-Shot Detection
Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama
As we move towards large-scale object detection, it is unrealistic to expect annotated training data, in the form of bounding box annotations around objects, for all object classes…
Deep Reinforcement Learning Attention Selection for Person Re-Identification
Xu Lan, Hanxiao Wang, Shaogang Gong +1
Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping. This…
Highly Efficient Regression for Scalable Person Re-Identification
Hanxiao Wang, Shaogang Gong, Tao Xiang
Existing person re-identification models are poor for scaling up to large data required in real-world applications due to: (1) Complexity: They employ complex models for optimal pe…
Human-In-The-Loop Person Re-Identification
Hanxiao Wang, Shaogang Gong, Xiatian Zhu +1
Current person re-identification (re-id) methods assume that (1) pre-labelled training data are available for every camera pair, (2) the gallery size for re-identification is moder…