✨ News
- [2025.11] Happy to announce that our paper X-SAM is accepted by AAAI 2026.
|
|
|
X-SAM: From Segment Anything to Any Segmentation
Hao Wang,
Limeng Qiao,
Zequn Jie,
Zhijian Huang,
Chengjian Feng,
Qingfang Zheng,
Lin Ma,
Xiangyuan Lan,
Xiaodan Liang,
AAAI, 2026
Project
/
Paper
/
A novel unified multimodal large language model (MLLM) framework, which extends the segmentation
from segment
anything to any segmentation, enhancing pixel-level perceptual understanding.
|
|
|
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective
Fusion
Hao Wang,
Pengzhen Ren,
Zequn Jie,
Xiao Dong,
Chengjian Feng,
Yinlong Qian,
Lin Ma,
Dongmei Jiang,
Yaowei Wang,
Xiangyuan Lan,
Xiaodan Liang,
arXiv Preprint, 2024
Project
/
Paper
/
A novel unified open-vocabulary detection method, which is pre-trained on
diverse
large-scale datasets with language-aware selective fusion in a unified
framework.
|
|
|
TMANet: Temporal Memory Attention for Video Semantic Segmentation
Hao Wang,
Weining Wang,
Jing Liu,
ICIP, 2021
Project
/
Paper
/
A novel self-attention and temporal memory mechanism to capture long-range temporal relations
between frames, avoiding the computational cost of optical flow prediction.
|
|
|
WL-MSR: Watch and Listen for Multimodal Subtitle Recognition
Jiawei Liu,
Hao Wang,
Weining Wang,
Xingjian He,
Jing Liu,
ICASSP, 2023
Paper
A framework that fuses OCR and ASR information using a Transformer model with mask/crop strategies
and multi-level identity embeddings to generate comprehensive video subtitles.
|
💼 Experience
- 2021.05 - 2021.08
Application research intern in Tencent AI Platform Department.
- 2019.09 - 2020.07
Application project intern in Huawei Photo Processing Department.
|
🎓 Education
- 2022.09 - Present
Ph.D. student in the School of Intelligent Systems Engineering, SYSU, and Pengcheng Laboratory,
co-supervised
by
Prof. Xiaodan Liang and Associate Prof. Xiangyuan
Lan.
- 2019.09 - 2022.06
Master student in the School of Artificial Intelligence, UCAS, and the Institute of Automation, CAS,
supervised by Prof. Jing
Liu.
- 2015.09 - 2019.06
Bachelor student in the School of Electronic and Information Engineering, BJTU.
|
🌈 Services
- Reviewer for conferences: AAAI2026, ICCV2023, ECCV2024.
|
|