Author

Taiyi Su

Observed name: Su, Taiyi

Institutions: Tongji University, Midea Group (China)

Observed institutions: Tongji University, Midea Group (China)

ORCID: 0000-0002-4357-1095

Observed ORCID: 0000-0002-4357-1095

OpenAlex ID: A5061219010

Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study

2020 · Wenhan Yang, Ye Yuan, et al. · IEEE Transactions on Image Processing · 347

Transductive Learning With Prior Knowledge for Generalized Zero-Shot Action Recognition

2023 · Taiyi Su, Hanli Wang, et al. · IEEE Transactions on Circuits and Systems for Video Technology · 31

Learning temporal information and object relation for zero-shot action recognition

2022 · Qiuping Qi, Hanli Wang, et al. · Displays · 17

Multi-Level Content-Aware Boundary Detection for Temporal Action Proposal Generation

2023 · Taiyi Su, Hanli Wang, et al. · IEEE Transactions on Image Processing · 10

2025 · Ran Chen, Taiyi Su, et al. · IEEE Transactions on Multimedia · 4

Memory-Based Contrastive Learning with Optimized Sampling for Incremental Few-Shot Semantic Segmentation

2024 · Yuxuan Zhang, Miaojing Shi, et al. · IEEE International Symposium on Circuits and Systems proceedings · 3

Learned Image Compression with Multi-Scale Spatial and Contextual Information Fusion

2022 · Ziyi Liu, Hanli Wang, et al. · Proceedings - International Conference on Image Processing · 3

WaveCL: Wavelet Calibration Learning for Referring Video Object Segmentation

2025 · Ran Chen, Taiyi Su, et al. · ACM International Conference on Multimedia (ACM MM) · 2

MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation

2026 · Huang, Zitai, Su, Taiyi, et al. · arXiv (Cornell University)

PDF

CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models

2026 · Liu, Tianbin, Zhu, Jian, et al. · arXiv (Cornell University)

PDF

JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent Representations

2026 · Liu, Tianbin, Zhu, Jian, et al. · arXiv (Cornell University)

PDF

DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulation

2026 · Zhu, Jian, Zhang, Jianjun, et al. · arXiv (Cornell University)

PDF

Learning 4D Geometric Priors for Inference-Efficient World Action Models

2026 · Zhang, Jianjun, Zhu, Jian, et al. · arXiv (Cornell University)

PDF

PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation

2026 · Ma, Chong, Su, Taiyi, et al. · arXiv (Cornell University)

PDF

DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation

2026 · Su, Taiyi, Zhu, Jian, et al. · arXiv (Cornell University)

PDF

Prompted Contrastive Learning for Skeleton-Based Action Recognition

2026 · Taiyi Su, Zheng Liu, et al. · IEEE Transactions on Circuits and Systems for Video Technology

Structure-Preserved Superpixel Perception for Referring Image Segmentation

2026 · Ran Chen, Taiyi Su, et al. · IEEE Transactions on Circuits and Systems for Video Technology

Towards High-Consistency Embodied World Model with Multi-View Trajectory Videos

2025 · Su, Taiyi, Zhu, Jian, et al. · arXiv (Cornell University)

PDF

Adaptive Token Excitation with Negative Selection for Video-Text Retrieval

2023 · Juntao Yu, Zhangkai Ni, et al. · Lecture notes in computer science

Works count: 22

Citation count: 417

H-index: 4

I10-index: 4