Search Results for author: Aimin Hao

Found 15 papers, 9 papers with code

A Plug-and-play Scheme to Adapt Image Saliency Deep Model for Video Data

1 code implementation2 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.

Video Saliency Detection

A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset

no code implementations7 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.

object-detection RGB Salient Object Detection +1

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection

1 code implementation7 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.

object-detection RGB-D Salient Object Detection +2

Recursive Multi-model Complementary Deep Fusion forRobust Salient Object Detection via Parallel Sub Networks

1 code implementation7 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.

object-detection RGB Salient Object Detection +1

Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection

1 code implementation7 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.

object-detection RGB-D Salient Object Detection +1

Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter

no code implementations10 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.

Object object-detection +3

From Semantic Categories to Fixations: A Novel Weakly-Supervised Visual-Auditory Saliency Detection Approach

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.

Video Saliency Detection

Knowledge-inspired 3D Scene Graph Prediction in Point Cloud

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.

Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception

1 code implementation27 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.

Video Saliency Detection

Synthetic Data Supervised Salient Object Detection

1 code implementation25 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.

Code Generation Object +3

Salient Object Detection via Dynamic Scale Routing

1 code implementation25 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.

Object object-detection +2

Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection

no code implementations13 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.

Active Learning Adversarial Attack +3

Sequential Texts Driven Cohesive Motions Synthesis with Natural Transitions

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.

WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learning

2 code implementations23 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.

Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey

no code implementations22 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.

Attribute Out-of-Distribution Generalization

Cannot find the paper you are looking for? You can Submit a new open access paper.