2 code implementations • 23 Apr 2024 • Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin
Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network.
1 code implementation • 21 Apr 2024 • Kang You, Kai Liu, Li Yu, Pan Gao, Dandan Ding
Despite considerable progress being achieved in point cloud geometry compression, there still remains a challenge in effectively compressing large-scale scenes with sparse surfaces.
2 code implementations • 10 Apr 2024 • Kang You, Pan Gao, Zhan Ma
In this paper, we propose PoLoPCAC, an efficient and generic lossless PCAC method that achieves high compression efficiency and strong generalizability simultaneously.
no code implementations • 26 Dec 2023 • Ruoqing Zhao, Xi Wang, Hongliang Dai, Pan Gao, Piji Li
Automated radiology report generation has the potential to improve radiology reporting and alleviate the workload of radiologists.
1 code implementation • 12 Dec 2023 • Jinsong Shi, Pan Gao, Jie Qin
We first train a model on a large-scale synthetic dataset by SCL (no image subjective score is required) to extract degradation features of images with various distortion types and levels.
1 code implementation • 6 Oct 2023 • Qingguo Liu, Pan Gao, Kang Han, Ningzhong Liu, Wei Xiang
In particular, we integrate both CNN and Transformer components into the SR network, where we first use the CNN modulated by the degradation information to extract local features, and then employ the degradation-aware Transformer to extract global semantic features.
1 code implementation • 15 Sep 2023 • Yao Yuan, Pan Gao, Xiaoyang Tan
To overcome these, we propose the M$^3$Net, i. e., the Multilevel, Mixed and Multistage attention network for Salient Object Detection (SOD).
Ranked #2 on RGB Salient Object Detection on HKU-IS
no code implementations • 30 Jul 2023 • Pan Gao, Haoyue Tian, Jie Qin
Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity.
1 code implementation • 30 Jul 2023 • Chenyi Zhuang, Pan Gao, Aljosa Smolic
We then prove that StylePrompter lies in a more disentangled $\mathcal{W^+}$ and show the controllability of SMART.
1 code implementation • 16 May 2023 • Jinsong Shi, Pan Gao, Aljosa Smolic
Specifically, we firstly generate the predicted error map by pre-training one model consisting of a Transformer encoder and decoder, in which the objective difference between the distorted and the reference images is used as supervision.
Blind Image Quality Assessment No-Reference Image Quality Assessment +1
1 code implementation • 27 Apr 2023 • Zihao Li, Pan Gao, Hui Yuan, Ran Wei, Manoranjan Paul
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Ranked #1 on 3D Object Classification on ModelNet40
no code implementations • 15 Mar 2023 • Pan Gao, Xinlang Chen, Rong Quan, Wei Xiang
We employ a recurrent neural network among adjacent prediction stages to model their correlations, and exploit a discriminator at the end of each stage to supervise the output saliency map.
1 code implementation • CVPR 2023 • Shanshan Li, Pan Gao, Xiaoyang Tan, Mingqiang Wei
Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies.
1 code implementation • 3 Feb 2023 • Pan Gao, Donghong Han, Rui Zhou, Xuejiao Zhang, Zikun Wang
For behavior, we use appropriate dialogue acts to guide the dialogue generation to enhance the empathy expression.
1 code implementation • 7 Jan 2023 • Zihao Li, Pan Gao, Hui Yuan, Ran Wei
Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.
1 code implementation • 6 Dec 2022 • Lihua Fu, Haoyue Tian, Xiangping Bryce Zhai, Pan Gao, Xiaojiang Peng
Semantic segmentation usually benefits from global contexts, fine localisation information, multi-scale features, etc.
Ranked #378 on Image Classification on ImageNet
1 code implementation • 25 Nov 2022 • Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li
On the more challenging ADE20K dataset, our best model yields a single-scale mIoU of 50. 18, and a multi-scale mIoU of 51. 8, which is on-par with the current state-of-art model, while we drastically cut the number of FLOPs by 53. 5%.
1 code implementation • 4 Aug 2022 • Kang You, Pan Gao, Qing Li
Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc.
1 code implementation • 3 Aug 2022 • Wentao Shi, Jing Xu, Pan Gao
It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks.
no code implementations • 8 Jul 2022 • Xiaojiang Peng, Xiaomao Fan, Qingyang Wu, Jieyan Zhao, Pan Gao
Moreover, we present a new Coarse-to-fine Deep Smoky vehicle detection (CoDeS) framework for efficient smoky vehicle detection.
1 code implementation • 25 Apr 2022 • Haoyue Tian, Pan Gao, Xiaojiang Peng
In order to solve this problem, we revisit the deformable convolution for video interpolation, which can break the fixed grid restrictions on the kernel region, making the distribution of reference points more suitable for the shape of the object, and thus warp a more accurate interpolation frame.
1 code implementation • 11 Feb 2022 • Haoyue Tian, Pan Gao, Ran Wei, Manoranjan Paul
Motion estimation and motion compensation are indispensable parts of inter prediction in video coding.
no code implementations • 10 Dec 2021 • Qing Li, Xiaojiang Peng, Chuan Yan, Pan Gao, Qi Hao
In SEN, a student network is kept in a collaborative manner with supervised learning and self-supervised learning, and a teacher network conducts temporal consistency to learn useful representations and ensure the quality of point clouds reconstruction.
1 code implementation • 18 Oct 2021 • Kang You, Pan Gao
Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently.
no code implementations • 25 Jun 2021 • Cheng Zhang, Pan Gao
Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent.
no code implementations • ICML Workshop AML 2021 • Cheng Zhang, Pan Gao
We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification.