Picture for Mingfei Han

Mingfei Han

LongVLM: Efficient Long Video Understanding via Large Language Models

Add code
Apr 10, 2024
Viaarxiv icon

Video Recognition in Portrait Mode

Dec 21, 2023
Viaarxiv icon

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

Dec 19, 2023
Viaarxiv icon

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

Dec 04, 2023
Viaarxiv icon

Mask Propagation for Efficient Video Semantic Segmentation

Add code
Oct 29, 2023
Figure 1 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 2 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 3 for Mask Propagation for Efficient Video Semantic Segmentation
Figure 4 for Mask Propagation for Efficient Video Semantic Segmentation
Viaarxiv icon

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

Jul 21, 2022
Figure 1 for An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Figure 2 for An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Figure 3 for An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Figure 4 for An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
Viaarxiv icon

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

Add code
Apr 06, 2022
Figure 1 for Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Figure 2 for Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Figure 3 for Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Figure 4 for Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition
Viaarxiv icon