no code implementations • 22 Apr 2024 • Yonghao Dang, Jianqin Yin, Liyuan Liu, Yuan Sun, Yanzhu Hu, Pengxiang Ding
Multi-person pose estimation (MPPE) presents a formidable yet crucial challenge in computer vision.
1 code implementation • 10 Jan 2024 • Haobo Yue, Zhicheng Zhang, Da Mu, Yonghao Dang, Jianqin Yin, Jin Tang
Recently, 2D convolution has been found unqualified in sound event detection (SED).
2 code implementations • 23 Dec 2023 • Shaojie Zhang, Jianqin Yin, Yonghao Dang
Furthermore, to explicitly exploit the latent data distributions, we employ the attentive features to contrastive learning, which models the cross-sequence semantic relations by pulling together the features from the positive pairs and pushing away the negative pairs.
no code implementations • 17 Nov 2023 • Zhicheng Zhang, Xueyao Sun, Yonghao Dang, Jianqin Yin
On the challenging of COCO dataset, the proposed method enables the binary neural network to achieve 70. 8 mAP, which is better than most tested lightweight full-precision networks.
2 code implementations • 30 Aug 2023 • Shaojie Zhang, Jianqin Yin, Yonghao Dang, Jiajun Fu
Graph convolution networks (GCNs) have achieved remarkable performance in skeleton-based action recognition.
1 code implementation • 21 Jun 2023 • Chengxu Duan, Zhicheng Zhang, Xiaoli Liu, Yonghao Dang, Jianqin Yin
Specifically, we introduce a novel adaptable scheme that facilitates the attack to suit the scale of the target pose and two physical constraints to enhance the naturalness of the adversarial example.
no code implementations • 13 Mar 2023 • Jiajun Fu, Yonghao Dang, Ruoqi Yin, Shaojie Zhang, Feng Zhou, Wending Zhao, Jianqin Yin
This technical report describes our first-place solution to the pose estimation challenge at ECCV 2022 Visual Perception for Navigation in Human Environments Workshop.
1 code implementation • 11 Oct 2022 • Yuanyuan Jiang, Jianqin Yin, Yonghao Dang
In contrast to existing methods, we propose a novel video-level semantic consistency guidance network for the AVE localization task.
no code implementations • 22 Jul 2022 • Yonghao Dang, Jianqin Yin, Shaojie Zhang, Jiping Liu, Yanzhu Hu
In this work, we propose a plug-and-play kinematics modeling module (KMM) to explicitly model temporal correlations between joints across different frames by calculating their temporal similarity.
1 code implementation • 4 Apr 2022 • Jiajun Fu, Fuxing Yang, Yonghao Dang, Xiaoli Liu, Jianqin Yin
The key of DSTD-GC is constrained dynamic correlation modeling, which explicitly parameterizes the common static constraints as a spatial/temporal vanilla adjacency matrix shared by all frames/joints and dynamically extracts correspondence variances for each frame/joint with an adjustment modeling function.
1 code implementation • 8 Jul 2021 • Yonghao Dang, Jianqin Yin, Shaojie Zhang
Moreover, the JRE can infer invisible joints according to the relationship between joints, which is beneficial for the model to locate occluded joints.
no code implementations • 15 Mar 2020 • Jianqin Yin, Yanchun Wu, Huaping Liu, Yonghao Dang, Zhiyi Liu, Jun Liu
Our work features two-fold: 1) An important insight that deep features extracted for action recognition can well model the self-similarity periodicity of the repetitive action is presented.
no code implementations • 29 Aug 2019 • Yonghao Dang, Fuxing Yang, Jianqin Yin
We propose in this paper a deep-wide network (DWnet) which combines the deep structure with the broad learning system (BLS) to recognize actions.