activity
20182020
most citedSee Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

100 citations · 108 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CV20208 cited

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

Tao Hu, Lichao Huang, Han Shen

Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to gro…

cs.CV2019

Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network

Tao Hu, Lichao Huang, Xianming Liu +1

More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevent…

cs.CV2019

Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion

Tao Hu, Zhizhong Han, Abhinav Shrivastava +1

We propose a novel approach for 3D shape completion by synthesizing multi-view depth maps. While previous work for shape completion relies on volumetric representations, meshes, or…

cs.CV2019100 cited

See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification

Tao Hu, Honggang Qi, Qingming Huang +1

Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augm…

cs.CV2018

Weakly Supervised Bilinear Attention Network for Fine-Grained Visual Classification

Tao Hu, Jizheng Xu, Cong Huang +3

For fine-grained visual classification, objects usually share similar geometric structure but present variant local appearance and different pose. Therefore, localizing and extract…

cs.CV2018

Facial Landmarks Detection by Self-Iterative Regression based Landmarks-Attention Network

Tao Hu, Honggang Qi, Jizheng Xu +1

Cascaded Regression (CR) based methods have been proposed to solve facial landmarks detection problem, which learn a series of descent directions by multiple cascaded regressors se…