K
Keze Wang
Researcher at University of California, Los Angeles
Publications - 58
Citations - 2363
Keze Wang is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Convolutional neural network & Computer science. The author has an hindex of 20, co-authored 57 publications receiving 1704 citations. Previous affiliations of Keze Wang include Hong Kong Polytechnic University & Sun Yat-sen University.
Papers
More filters
Journal ArticleDOI
Cost-Effective Active Learning for Deep Image Classification
TL;DR: This paper proposes a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner and incorporates deep convolutional neural networks into AL.
Proceedings ArticleDOI
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
TL;DR: Flow guided recurrent neural encoder (FGRNE) is presented, an accurate and end-to-end learning framework for video salient object detection that significantly outperforms state-of-the-art methods on the public benchmarks of DAVIS and FBMS.
Journal ArticleDOI
Active Self-Paced Learning for Cost-Effective and Progressive Face Identification
TL;DR: A novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals by naturally combining two recently rising techniques: active learning and self-paced learning, capable of automatically annotating new instances and incorporating them into training under weak expert recertification.
Proceedings ArticleDOI
Recurrent 3D Pose Sequence Machines
TL;DR: A Recurrent 3D Pose Sequence Machine (RPSM) is presented to automatically learn the image-dependent structural constraint and sequence-dependent temporal context by using a multi-stage sequential refinement.
Journal ArticleDOI
A Deep Structured Model with Radius---Margin Bound for 3D Human Activity Recognition
TL;DR: A novel deep structured model, which adaptively decomposes an activity instance into temporal parts using the convolutional neural networks, and incorporates latent temporal structure into the deep model, accounting for large temporal variations of diverse human activities.