Search Results for author: Shuaibing Wang

Found 6 papers, 2 papers with code

SMCD: High Realism Motion Style Transfer via Mamba-based Diffusion

no code implementations5 May 2024 Ziyun Qian, Zeyu Xiao, Zhenyi Wu, Dingkang Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Dongliang Kou, Lihua Zhang

To address these problems, we consider style motion as a condition and propose the Style Motion Conditioned Diffusion (SMCD) framework for the first time, which can more comprehensively learn the style features of motion.

Motion Style Transfer Style Transfer

Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities

no code implementations25 Apr 2024 Mingcheng Li, Dingkang Yang, Xiao Zhao, Shuaibing Wang, Yan Wang, Kun Yang, Mingyang Sun, Dongliang Kou, Ziyun Qian, Lihua Zhang

Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics.

Disentanglement Knowledge Distillation +1

Robust Emotion Recognition in Context Debiasing

no code implementations9 Mar 2024 Dingkang Yang, Kun Yang, Mingcheng Li, Shunli Wang, Shuaibing Wang, Lihua Zhang

Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias.

counterfactual Emotion Recognition in Context

CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space

1 code implementation16 Jul 2022 Shunli Wang, Shuaibing Wang, Bo Jiao, Dingkang Yang, Liuzhen Su, Peng Zhai, Chixiao Chen, Lihua Zhang

Considering that the pose estimator is sensitive to background interference, this paper proposes a counterfactual analysis framework named CASpaceNet to complete robust 6D pose estimation of the spaceborne targets under complicated background.

6D Pose Estimation Causal Inference +2

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