Text Detection and Character Recognition in Scene Images with Unsupervised Feature Learning
- Adam Coates, Blake Carpenter, A. Ng
- Computer ScienceIEEE International Conference on Document…
- 18 September 2011
This paper applies large-scale algorithms for learning the features automatically from unlabeled data to construct highly effective classifiers for both detection and recognition to be used in a high accuracy end-to-end system.
The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation
- Tao Wang, Yu Li, Jiashi Feng
- Computer Science, Environmental ScienceEuropean Conference on Computer Vision
- 23 July 2020
This work systematically investigates performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveils that a major cause is the inaccurate classification of object proposals.
Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables
- Tao Wang, Yong Li, Youliang Yan
- Computer ScienceIEEE International Conference on Computer Vision
- 19 August 2021
A novel real-time image enhancer via learnable spatial-aware 3dimentional lookup tables(3D LUTs), which well considers global scenario and local spatial information, and that outperforms SOTA image enhancement methods on public datasets both subjectively and objectively.
Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer
- Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, Wei Shi
- Computer ScienceAAAI Conference on Artificial Intelligence
- 5 December 2021
A transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components and selectively match non-occluded parts correspondingly, which performs favorably against state-of-the-art methods.
Ultra-High-Definition Image Dehazing via Multi-Guided Bilateral Learning
- Zhuoran Zheng, Wenqi Ren, Xiuyi Jia
- Computer ScienceComputer Vision and Pattern Recognition
- 1 June 2021
A novel network capable of real-time dehazing of 4K images on a single GPU, which consists of three deep CNNs that fuses the high-quality feature maps into a dehazed image.
PnP-DETR: Towards Efficient Visual Analysis with Transformers
- Tao Wang, Li Yuan, Yunpeng Chen, Jiashi Feng, Shuicheng Yan
- Computer ScienceIEEE International Conference on Computer Vision
- 15 September 2021
This work encapsulates the idea of reducing spatial redundancy into a novel poll and pool (PnP) sampling module, with which it is built an end-to-end PnP-DETR architecture that adaptively allocates its computation spatially to be more efficient.
Direct Multi-view Multi-person 3D Pose Estimation
- Tao Wang, Jianfeng Zhang, Yujun Cai, Shuicheng Yan, Jiashi Feng
- Computer ScienceNeural Information Processing Systems
- 7 November 2021
The proposed Multi-view Pose transformer (MvP) model is trained on 8 Nvidia RTX 2080 Ti GPUs, with a batch size of 1 per GPU and a totalbatch size of 8.
Pyramid Channel-based Feature Attention Network for image dehazing
- Xiaoqin Zhang, Tao Wang, Jinxin Wang, Guiying Tang, Li Zhao
- Computer ScienceComputer Vision and Image Understanding
- 1 August 2020
Effects of Natural Products on Fructose-Induced Nonalcoholic Fatty Liver Disease (NAFLD)
- Qian Chen, Tingting Wang, Tao Wang
- BiologyNutrients
- 31 January 2017
The natural products (e.g., curcumin, resveratrol, and (−)-epicatechin) and their mechanisms of ameliorating fructose-induced nonalcoholic fatty liver disease over the past years are reviewed to shed light on studies aiming to discover new drugs for NAFLD.
Hierarchical Feature Fusion With Mixed Convolution Attention for Single Image Dehazing
- Xiaoqin Zhang, Jinxin Wang, Tao Wang, Runhua Jiang
- Computer ScienceIEEE transactions on circuits and systems for…
- 18 March 2021
A network combining multi-scale hierarchical feature fusion and mixed convolution attention to progressively and adaptively enhance the dehazing performance is proposed and shows that the proposed method outperforms state-of-the-art haze removal algorithms.
...
...