no code implementations • ECCV 2020 • Baojie Fan, Wei Chen, Yang Cong, Jiandong Tian
Due to the complex underwater environment, underwater imaging often encounters some problems such as blur, scale variation, color shift, and texture distortion.
no code implementations • 9 Apr 2024 • Baojie Fan, Wuyang Zhou, Kai Wang, Shijun Zhou, Fengyu Xu, Jiandong Tian
Most of 3D single object trackers (SOT) in point clouds follow the two-stream multi-stage 3D Siamese or motion tracking paradigms, which process the template and search area point clouds with two parallel branches, built on supervised point cloud backbones.
no code implementations • 11 Jan 2024 • Weibo Jiang, Weihong Ren, Jiandong Tian, Liangqiong Qu, Zhiyong Wang, Honghai Liu
In this work, we propose to explore Self- and Cross-Triplet Correlations (SCTC) for HOI detection.
Human-Object Interaction Detection Knowledge Distillation +2
no code implementations • 17 Dec 2023 • Jingwen Zhang, Zikun Zhou, Guangming Lu, Jiandong Tian, Wenjie Pei
Considering that, we propose to construct a synthetic target representation composed of dense and complete point clouds depicting the target shape precisely by shape completion for robust 3D tracking.
1 code implementation • 16 Dec 2023 • Wenjie Pei, Tongqi Xia, Fanglin Chen, Jinsong Li, Jiandong Tian, Guangming Lu
Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which represents an input image as a flattened sequence of token embeddings and then learns a set of unordered parameterized tokens prefixed to the sequence representation as the visual prompts for task adaptation of large vision models.
1 code implementation • 3 Dec 2023 • Wenjie Pei, Qizhong Tan, Guangming Lu, Jiandong Tian
In particular, we devise the anisotropic Deformable Spatio-Temporal Attention module as the core component of D$^2$ST-Adapter, which can be tailored with anisotropic sampling densities along spatial and temporal domains to learn spatial and temporal features specifically in corresponding pathways, allowing our D$^2$ST-Adapter to encode features in a global view in 3D spatio-temporal space while maintaining a lightweight design.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2023 • Jiawei Liu, Qiang Wang, Huijie Fan, Jiandong Tian, Yandong Tang
Thus, our network ensures the fidelity of nonshadow areas and restores the light intensity of shadow areas through three-branch collaboration.
no code implementations • 2 Dec 2022 • Dianwen Mei, Wei Zhuo, Jiandong Tian, Guangming Lu, Wenjie Pei
To circumvent these two challenges, we propose to activate the discriminability of novel classes explicitly in both the feature encoding stage and the prediction stage for segmentation.
no code implementations • 25 Jul 2022 • Wenjie Pei, Shuang Wu, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu
In this work we design a novel knowledge distillation framework to guide the learning of the object detector and thereby restrain the overfitting in both the pre-training stage on base classes and fine-tuning stage on novel classes.
1 code implementation • 22 Jul 2022 • Shuang Wu, Wenjie Pei, Dianwen Mei, Fanglin Chen, Jiandong Tian, Guangming Lu
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and transferred implicitly from base classes with abundant samples to novel classes with limited samples via such a two-stage training strategy.
no code implementations • 18 Jul 2020 • Weihong Ren, Xinchao Wang, Jiandong Tian, Yandong Tang, Antoni B. Chan
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors.
no code implementations • ICCV 2017 • Jiandong Tian, Zachary Murez, Tong Cui, Zhen Zhang, David Kriegman, Ravi Ramamoorthi
First, we present a new single image restoration algorithm which removes backscatter and attenuation from images better than existing methods, and apply it to each view in the light field.
no code implementations • CVPR 2017 • Weihong Ren, Jiandong Tian, Zhi Han, Antoni Chan, Yandong Tang
The existing snow/rain removal methods often fail for heavy snow/rain and dynamic scene.
3 code implementations • CVPR 2017 • Liangqiong Qu, Jiandong Tian, Shengfeng He, Yandong Tang, Rynson W. H. Lau
Two levels of features are derived from the global network and transferred to two parallel networks.
no code implementations • 12 Jul 2016 • Liangqiong Qu, Shengfeng He, Jiawei Zhang, Jiandong Tian, Yandong Tang, Qingxiong Yang
Numerous efforts have been made to design different low level saliency cues for the RGBD saliency detection, such as color or depth contrast features, background and color compactness priors.
Ranked #25 on RGB-D Salient Object Detection on NJU2K
no code implementations • 30 Jun 2014 • Liangqiong Qu, Jiandong Tian, Zhi Han, Yandong Tang
In this paper, we propose a novel, effective and fast method to obtain a color illumination invariant and shadow-free image from a single outdoor image.