Mingfei Han

Mingfei Han

Monash University

H-index: 6

Oceania-Australia

About Mingfei Han

Mingfei Han, With an exceptional h-index of 6 and a recent h-index of 6 (since 2020), a distinguished researcher at Monash University, specializes in the field of Video-Text Understanding, Video Object Perception, Action Recognition.

His recent articles reflect a diverse array of research interests and contributions to the field:

LongVLM: Efficient Long Video Understanding via Large Language Models

Progressive Frame-Proposal Mining for Weakly Supervised Video Object Detection

Mask propagation for efficient video semantic segmentation

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition

Video Recognition in Portrait Mode

HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

Mingfei Han Information

University

Position

; Shenzhen Institute of Advanced Technology Chinese Academy of Sciences

Citations(all)

276

Citations(since 2020)

276

Cited By

23

hIndex(all)

6

hIndex(since 2020)

6

i10Index(all)

5

i10Index(since 2020)

5

Email

University Profile Page

Google Scholar

Mingfei Han Skills & Research Interests

Video-Text Understanding

Video Object Perception

Action Recognition

Top articles of Mingfei Han

LongVLM: Efficient Long Video Understanding via Large Language Models

arXiv preprint arXiv:2404.03384

2024/4/4

Progressive Frame-Proposal Mining for Weakly Supervised Video Object Detection

IEEE Transactions on Image Processing

2024/2/15

Mask propagation for efficient video semantic segmentation

NeurIPS 2023

2023

Shot2Story20K: A New Benchmark for Comprehensive Understanding of Multi-shot Videos

arXiv preprint arXiv:2312.10300

2023/12/19

Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition

arXiv preprint arXiv:2312.02226

2023/12/4

Video Recognition in Portrait Mode

arXiv preprint arXiv:2312.13746

2023/12

HTML: Hybrid Temporal-scale Multimodal Learning Framework for Referring Video Object Segmentation

2023

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

2022/7/21

Generalizable memory-driven transformer for multivariate long sequence time-series forecasting

arXiv preprint arXiv:2207.07827

2022/7/16

Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition

2022

Mining inter-video proposal relations for video object detection

2020

See List of Professors in Mingfei Han University(Monash University)

Co-Authors

academic-engine