no code implementations • 7 Mar 2024 • Yao Jiang, Xinyu Yan, Ge-Peng Ji, Keren Fu, Meijun Sun, Huan Xiong, Deng-Ping Fan, Fahad Shahbaz Khan
This paper endeavors to evaluate the competency of popular LVLMs in specialized and general tasks, respectively, aiming to offer a comprehensive understanding of these novel models.
no code implementations • 4 Mar 2024 • Xin Zhang, Tao Xiao, GePeng Ji, Xuan Wu, Keren Fu, Qijun Zhao
The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner.
no code implementations • 16 Feb 2024 • Xin Zhang, Keren Fu, Qijun Zhao
To facilitate the seamless integration of global classification features with the finely detailed local features selected by DPSM, we introduce a novel feature blending module (FBM).
no code implementations • 30 Dec 2023 • Xianjie Liu, Keren Fu, Qijun Zhao
We have high expectations regarding whether SAM, as a foundation model, can be improved towards highly accurate object segmentation, which is known as dichotomous image segmentation (DIS).
2 code implementations • 24 Oct 2023 • Ao Mou, Yukang Lu, Jiahao He, Dingyao Min, Keren Fu, Qijun Zhao
Ablation experiments were performed on both pseudo and realistic RGB-D video datasets to demonstrate the advantages of individual modules as well as the necessity of introducing realistic depth.
no code implementations • 9 May 2023 • Bo Yuan, Yao Jiang, Keren Fu, Qijun Zhao
To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features.
1 code implementation • 8 Aug 2022 • Wenbo Zhang, Keren Fu, Zhuo Wang, Ge-Peng Ji, Qijun Zhao
Inspired by the fact that depth quality is a key factor influencing the accuracy, we propose an efficient depth quality-inspired feature manipulation (DQFM) process, which can dynamically filter depth features according to depth quality.
2 code implementations • 12 Feb 2022 • Yukang Lu, Dingyao Min, Keren Fu, Qijun Zhao
However, existing video salient object detection (VSOD) methods only utilize spatiotemporal information and seldom exploit depth information for detection.
1 code implementation • 5 Nov 2021 • Ge-Peng Ji, Lei Zhu, Mingchen Zhuge, Keren Fu
Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e. g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest.
1 code implementation • ICCV 2021 • Ge-Peng Ji, Deng-Ping Fan, Keren Fu, Zhe Wu, Jianbing Shen, Ling Shao
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
Ranked #7 on Video Polyp Segmentation on SUN-SEG-Hard (Unseen)
1 code implementation • 5 Jul 2021 • Wenbo Zhang, Ge-Peng Ji, Zhuo Wang, Keren Fu, Qijun Zhao
To tackle this dilemma and also inspired by the fact that depth quality is a key factor influencing the accuracy, we propose a novel depth quality-inspired feature manipulation (DQFM) process, which is efficient itself and can serve as a gating mechanism for filtering depth features to greatly boost the accuracy.
1 code implementation • 5 Apr 2021 • Wenbo Zhang, Yao Jiang, Keren Fu, Qijun Zhao
Depth information has been proved beneficial in RGB-D salient object detection (SOD).
Ranked #2 on RGB-D Salient Object Detection on DES
1 code implementation • 25 Jan 2021 • Qian Chen, Ze Liu, Yi Zhang, Keren Fu, Qijun Zhao, Hongwei Du
The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams.
1 code implementation • 4 Nov 2020 • Qian Chen, Keren Fu, Ze Liu, Geng Chen, Hongwei Du, Bensheng Qiu, LingShao
Finally, we propose an effective layer-wise aggregation module to fuse the features extracted from the enhanced depth maps and RGB images for the accurate detection of salient objects.
1 code implementation • 10 Oct 2020 • Keren Fu, Yao Jiang, Ge-Peng Ji, Tao Zhou, Qijun Zhao, Deng-Ping Fan
Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, from which insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models, are achieved.
2 code implementations • 26 Aug 2020 • Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao, Jianbing Shen, Ce Zhu
Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.
Ranked #3 on RGB-D Salient Object Detection on STERE
1 code implementation • CVPR 2020 • Keren Fu, Deng-Ping Fan, Ge-Peng Ji, Qijun Zhao
This paper proposes a novel joint learning and densely-cooperative fusion (JL-DCF) architecture for RGB-D salient object detection.
Ranked #6 on RGB-D Salient Object Detection on NLPR
no code implementations • 28 Nov 2019 • Ye Lin, Keren Fu, Shenggui Ling, Cheng Peng
To improve the image quality, we propose an effective many-to-many mapping framework for unsupervised multi-domain image-to-image translation.
no code implementations • 20 Sep 2015 • Fanghui Liu, Tao Zhou, Keren Fu, Irene Y. H. Gu, Jie Yang
It utilizes both the foreground and background information, and imposes a local coordinate constraint, where the basis matrix is sparse matrix from the linear combination of candidates with corresponding nonnegative coefficient vectors.
no code implementations • CVPR 2015 • Chen Gong, DaCheng Tao, Wei Liu, Stephen J. Maybank, Meng Fang, Keren Fu, Jie Yang
In the teaching-to-learn step, a teacher is designed to arrange the regions from simple to difficult and then assign the simplest regions to the learner.