Hanli Wang

Prof. Hanli Wang


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2017 in Neurocomputing
Verified
Journal Article
Closed access
PTPengjie Tang
Pengjie Tang
HWHanli Wang
Hanli Wang
SKSam Kwong
Sam Kwong

8 January 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
BZBowen Zhang
Bowen Zhang
LWLimin Wang
Limin Wang
ZWZhe Wang
Zhe Wang
YQYu Qiao
Yu Qiao
HWHanli Wang
Hanli Wang
The two-stream CNNs prove very successful for video-based action recognition. However, the classical two-stream CNNs are time costly, mainly due to the bottleneck of calculating optical flows (OFs). In this paper, we propose a two-stream-based real-time action recognition approach by using motion vector (MV) to replace OF. MVs are encoded in video stream and can be extracted directly without extra calculation. However, directly training CNN with MVs degrades accuracy severely due to the noise and the lack of fine details in MVs. In order to relieve this problem, we propose four training strategies which leverage the knowledge learned from OF CNN to enhance the accuracy of MV CNN. Our insight is that MV and OF share inherent similar structures which allow us to transfer knowledge from one domain to another. To fully utilize the knowledge learned in OF domain, we develop deeply transferred MV CNN. Experimental results on various datasets show the effectiveness of our training strategies. Our approach is significantly faster than OF based approaches and achieves processing speed of 390.7 frames per second, surpassing real-time requirement. We release our model and code to facilitate further research.

15 May 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
DYDongjie Ye
Dongjie Ye
ZNZhangkai Ni
Zhangkai Ni
HWHanli Wang
Hanli Wang
JZJian Zhang
Jian Zhang
SWShiqi Wang
Shiqi Wang
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
Convolutional Neural Networks (CNNs) dominate image processing but suffer from local inductive bias, which is addressed by the transformer framework with its inherent ability to capture global context through self-attention mechanisms. However, how to inherit and integrate their advantages to improve compressed sensing is still an open issue. This paper proposes CSformer, a hybrid framework to explore the representation capacity of local and global features. The proposed approach is well-designed for end-to-end compressive image sensing, composed of adaptive sampling and recovery. In the sampling module, images are measured block-by-block by the learned sampling matrix. In the reconstruction stage, the measurements are projected into an initialization stem, a CNN stem, and a transformer stem. The initialization stem mimics the traditional reconstruction of compressive sensing but generates the initial reconstruction in a learnable and efficient manner. The CNN stem and transformer stem are concurrent, simultaneously calculating fine-grained and long-range features and efficiently aggregating them. Furthermore, we explore a progressive strategy and window-based transformer block to reduce the parameters and computational complexity. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing, which achieves superior performance compared to state-of-the-art methods on different datasets. Our codes is available at: https://github.com/Lineves7/CSformer.

11 June 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
MCMeng Cheng
Meng Cheng
HWHanli Wang
Hanli Wang
YLYu Long
Yu Long
Recent years have witnessed meaningful progress in the task of few-shot object detection. However, most of the existing models are not capable of incremental learning with a few samples, i.e. , the detector can’t detect novel-class objects by using only a few samples of novel classes (without revisiting the original training samples) while maintaining the performances on base classes. This is largely because of catastrophic forgetting, which is a general phenomenon in few-shot learning that the incorporation of the unseen information ( e.g. , novel-class objects) will lead to a serious loss of the knowledge learnt before ( e.g. , base-class objects). In this paper, a new model is proposed for incremental few-shot object detection, which takes CenterNet as the fundamental framework and redesigns it by introducing a novel meta-learning method to make the model adapted to unseen knowledge while overcoming forgetting to a great extent. Specifically, a meta-learner is trained with the base-class samples, providing the object locator of the proposed model with a good weight initialization, and thus the proposed model can be fine-tuned easily with few novel-class samples. On the other hand, the filters correlated to base classes are preserved when fine-tuning the proposed model with the few samples of novel classes, which is a simple but effective solution to mitigate the problem of forgetting. The experiments on the benchmark MS COCO and PASCAL VOC datasets demonstrate that the proposed model outperforms the state-of-the-art methods by a large margin in the detection performances on base classes and all classes while achieving best performances when detecting novel-class objects in most cases. The project page can be found in https://mic.tongji.edu.cn/e6/d5/c9778a190165/page.htm .

17 August 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZTZhisen Tang
Zhisen Tang
HWHanli Wang
Hanli Wang
XYXiaokai Yi
Xiaokai Yi
Yun ZhangYun Zhang
Yun Zhang
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
CKC.-C. Jay Kuo
C.-C. Jay Kuo
Recent deep image compression methods have achieved prominent progress by using nonlinear modeling and powerful representation capabilities of neural networks. However, most existing learning-based image compression approaches employ customized convolutional neural network (CNN) to utilize visual features by treating all pixels equally, neglecting the effect of local key features. Meanwhile, the convolutional filters in CNN usually express the local spatial relationship within the receptive field and seldom consider the long-range dependencies from distant locations. This results in the long-range dependencies of latent representations not being fully compressed. To address these issues, an end-to-end image compression method is proposed by integrating graph attention and asymmetric convolutional neural network (ACNN). Specifically, ACNN is used to strengthen the effect of local key features and reduce the cost of model training. Graph attention is introduced into image compression to address the bottleneck problem of CNN in modeling long-range dependencies. Meanwhile, regarding the limitation that existing attention mechanisms for image compression hardly share information, we propose a self-attention approach which allows information flow to achieve reasonable bit allocation. The proposed self-attention approach is in compliance with the perceptual characteristics of human visual system, as information can interact with each other via attention modules. Moreover, the proposed self-attention approach takes into account channel-level relationship and positional information to promote the compression effect of rich-texture regions. Experimental results demonstrate that the proposed method achieves state-of-the-art rate-distortion performances after being optimized by MS-SSIM compared to recent deep compression models on the benchmark datasets of Kodak and Tecnick. The project page with the source code can be found in https://mic.tongji.edu.cn.

16 March 2020 in IEEE Transactions on Broadcasting
Verified
Journal Article
Closed access
TTTao Tian
Tao Tian
HWHanli Wang
Hanli Wang
LZLingxuan Zuo
Lingxuan Zuo
CKC.-C. Jay Kuo
C.-C. Jay Kuo
KWONG Tak Wu SamKWONG Tak Wu Sam
KWONG Tak Wu Sam
A perceptual image compression framework is proposed in this work, including an adaptive picture-level just noticeable difference (PJND) prediction model and a perceptual coding scheme. Specifically speaking, a convolutional neural network (CNN) model is designed with the existing subjective image database to predict the PJND label for a given image. Then, the support vector regression model is utilized to determine the number of PJND levels. After that, a just noticeable difference generation algorithm is developed to compute the corresponding quality factor for each PJND level. Moreover, an effective perceptual coding scheme is devised for perceptual image compression. Finally, the accuracy of the proposed PJND prediction model and the performance of the proposed perceptual coding scheme are evaluated. The experimental results show that the proposed CNN based PJND prediction model achieves good prediction accuracy and the proposed perceptual coding scheme produces state-of-the-art rate distortion performances.