activity
20192022
most citedOvercoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

8 citations · 16 across the 3 of their papers we have counts for

collaborators

8 papers

cs.CV20222 cited

PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision

Kehong Gong, Bingbing Li, Jianfeng Zhang +5

Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior…

cs.CV2020

Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes

Li Yuan, Yichen Zhou, Shuning Chang +6

Detecting and recognizing human action in videos with crowded scenes is a challenging problem due to the complex environment and diversity events. Prior works always fail to deal w…

cs.CV20208 cited

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Yu Li, Tao Wang, Bingyi Kang +4

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide th…

cs.CV2019

Classification Calibration for Long-tail Instance Segmentation

Tao Wang, Yu Li, Bingyi Kang +5

Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balance…

cs.CV2019

Revisiting Knowledge Distillation via Label Smoothing Regularization

Li Yuan, Francis E. H. Tay, Guilin Li +2

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged info…

cs.CV2019

Distilling Object Detectors with Fine-grained Feature Imitation

Tao Wang, Li Yuan, Xiaopeng Zhang +1

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowle…