Alert button
Picture for Zhe Li

Zhe Li

Alert button

PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling

Apr 25, 2023
Zhe Li, Zerong Zheng, Yuxiao Liu, Boyao Zhou, Yebin Liu

Figure 1 for PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
Figure 2 for PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
Figure 3 for PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
Figure 4 for PoseVocab: Learning Joint-structured Pose Embeddings for Human Avatar Modeling
Viaarxiv icon

Track Anything: Segment Anything Meets Videos

Apr 24, 2023
Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, Feng Zheng

Figure 1 for Track Anything: Segment Anything Meets Videos
Figure 2 for Track Anything: Segment Anything Meets Videos
Figure 3 for Track Anything: Segment Anything Meets Videos
Figure 4 for Track Anything: Segment Anything Meets Videos
Viaarxiv icon

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Mar 23, 2023
Zhendong Yang, Ailing Zeng, Zhe Li, Tianke Zhang, Chun Yuan, Yu Li

Figure 1 for From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Figure 2 for From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Figure 3 for From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Figure 4 for From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
Viaarxiv icon

Balancing Privacy Protection and Interpretability in Federated Learning

Feb 16, 2023
Zhe Li, Honglong Chen, Zhichen Ni, Huajie Shao

Figure 1 for Balancing Privacy Protection and Interpretability in Federated Learning
Figure 2 for Balancing Privacy Protection and Interpretability in Federated Learning
Figure 3 for Balancing Privacy Protection and Interpretability in Federated Learning
Figure 4 for Balancing Privacy Protection and Interpretability in Federated Learning
Viaarxiv icon

MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

Feb 09, 2023
Zhe Li, Zhongwen Rao, Lujia Pan, Zenglin Xu

Figure 1 for MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing
Figure 2 for MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing
Figure 3 for MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing
Figure 4 for MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing
Viaarxiv icon

Ti-MAE: Self-Supervised Masked Time Series Autoencoders

Jan 21, 2023
Zhe Li, Zhongwen Rao, Lujia Pan, Pengyun Wang, Zenglin Xu

Figure 1 for Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Figure 2 for Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Figure 3 for Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Figure 4 for Ti-MAE: Self-Supervised Masked Time Series Autoencoders
Viaarxiv icon

Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space

Nov 17, 2022
Zhe Li, Man-Wai Mak, Helen Mei-Ling Meng

Figure 1 for Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
Figure 2 for Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
Figure 3 for Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
Figure 4 for Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space
Viaarxiv icon

Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability

Nov 17, 2022
Zhe Li, Man-Wai Mak

Figure 1 for Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
Figure 2 for Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
Figure 3 for Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
Figure 4 for Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability
Viaarxiv icon

Learning Dual-Fused Modality-Aware Representations for RGBD Tracking

Nov 15, 2022
Shang Gao, Jinyu Yang, Zhe Li, Feng Zheng, Aleš Leonardis, Jingkuan Song

Figure 1 for Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
Figure 2 for Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
Figure 3 for Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
Figure 4 for Learning Dual-Fused Modality-Aware Representations for RGBD Tracking
Viaarxiv icon