hulianyuyy,hulianyu,github

Hi👋, i'm a PhD candidate (2021.09-now) in Tianjin University, China. My major interests include video understanding, sign language understanding and multi-modal learning. I'd like to let the people benefit more from general computer vision techniques. For more information, please visit www.hulianyu.top. Feel free to contact me via [email protected].

✉ News:

We release CorrNet+, an unified model with superior performance on both continuous sign language recognition and sign language translation tasks by using only RGB inputs.
We release AdaptSign, a CSLR model powered by frozen pretrained image models with 18.5% & 18.8% WER on phoenix2014, 18.6% & 19.8% WER on phoenix2014-T, 26.7% & 26.3% WER on CSL-Daily.
We release DSTA-SLR, which performs sign language recognition (SLR) with pure skeleton inputs but ahcieves comparable accuracy and much faster speed than recognition with RGB inputs.

hulianyu's Projects

adabrowse

AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition (ACMMM2023 Oral)

adaptsign

Improving Continuous Sign Language Recognition with Adapted Image Models

comma

COMMA: Co-Articulated Multi-Modal Learning (AAAI2024)

corrnet

Continuous Sign Language Recognition with Correlation Network (CVPR 2023)

corrnet_plus

CorrNet+: Sign Language Recognition and Translation via Spatial-Temporal Correlation

dsta-slr

Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition (COLING2024)

hulianyuyy.github.io

AcadHomepage: A Modern and Responsive Academic Personal Homepage

minimal-mistakes

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

sen_cslr

Self-Emphasizing Network for Continuous Sign Language Recognition (AAAI2023 Oral)

Skeleton-Based Action Recognition with Local Dynamic Spatial-Temporal Aggregation (Expert Systems with Applications 2023) (Previous name: Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition)