1 code implementation • 2 Aug 2020 • Yunxiao Li, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
With the rapid development of deep learning techniques, image saliency deep models trained solely by spatial information have occasionally achieved detection performance for video data comparable to that of the models trained by both spatial and temporal information.
no code implementations • 7 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
Compared with the conventional hand-crafted approaches, the deep learning based methods have achieved tremendous performance improvements by training exquisitely crafted fancy networks over large-scale training sets.
1 code implementation • 7 Aug 2020 • Xuehao Wang, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is to take full advantage of their complementary nature, aiming for a much-improved SOD performance than that of using either of them solely.
1 code implementation • 7 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
Finally, all these complementary multi-model deep features will be selectively fused to make high-performance salient object detections.
1 code implementation • 7 Aug 2020 • Xuehao Wang, Shuai Li, Chenglizhao Chen, Yuming Fang, Aimin Hao, Hong Qin
Existing RGB-D salient object detection methods treat depth information as an independent component to complement its RGB part, and widely follow the bi-stream parallel network architecture.
no code implementations • 10 Aug 2020 • Zhen-Yu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
In sharp contrast to the state-of-the-art (SOTA) methods that focus on learning pixel-wise saliency in "single image" using perceptual clues mainly, our method has investigated the "object-level semantic ranks between multiple images", of which the methodology is more consistent with the real human attention mechanism.
1 code implementation • CVPR 2021 • Guotao Wang, Chenglizhao Chen, Deng-Ping Fan, Aimin Hao, Hong Qin
Thanks to the rapid advances in the deep learning techniques and the wide availability of large-scale training sets, the performances of video saliency detection models have been improving steadily and significantly.
no code implementations • NeurIPS 2021 • Shoulong Zhang, Shuai Li, Aimin Hao, Hong Qin
Unlike conventional methods that learn knowledge embedding and regular patterns from encoded visual information, we propose to suppress the misunderstandings caused by appearance similarities and other perceptual confusion.
1 code implementation • 27 Dec 2021 • Guotao Wang, Chenglizhao Chen, Deng-Ping Fan, Aimin Hao, Hong Qin
Moreover, we distill knowledge from these regions to obtain complete new spatial-temporal-audio (STA) fixation prediction (FP) networks, enabling broad applications in cases where video tags are not available.
1 code implementation • 25 Oct 2022 • Zhenyu Wu, Lin Wang, Wei Wang, Tengfei Shi, Chenglizhao Chen, Aimin Hao, Shuo Li
In this paper, we propose a novel yet effective method for SOD, coined SODGAN, which can generate infinite high-quality image-mask pairs requiring only a few labeled data, and these synthesized pairs can replace the human-labeled DUTS-TR to train any off-the-shelf SOD model.
1 code implementation • 25 Oct 2022 • Zhenyu Wu, Shuai Li, Chenglizhao Chen, Hong Qin, Aimin Hao
First, instead of using the vanilla convolution with fixed kernel sizes for the encoder design, we propose the dynamic pyramid convolution (DPConv), which dynamically selects the best-suited kernel sizes w. r. t.
no code implementations • 13 Dec 2022 • Zhenyu Wu, Lin Wang, Wei Wang, Qing Xia, Chenglizhao Chen, Aimin Hao, Shuo Li
This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset.
no code implementations • ICCV 2023 • Shuai Li, Sisi Zhuang, Wenfeng Song, Xinyu Zhang, Hejia Chen, Aimin Hao
At the technical level, we explore the local-to-global semantic features of previous and current texts to extract relevant information.
2 code implementations • 23 May 2023 • Guotao Wang, Chenglizhao Chen, Aimin Hao, Hong Qin, Deng-Ping Fan
The main reason is that there always exist "blind zooms" when using HMD to collect fixations since the users cannot keep spinning their heads to explore the entire panoptic scene all the time.
no code implementations • 22 Jan 2024 • Zhenyu Wu, Fengmao Lv, Chenglizhao Chen, Aimin Hao, Shuo Li
Colorectal polyp segmentation (CPS), an essential problem in medical image analysis, has garnered growing research attention.