Mingfei Han

8

Papers

140

Total Citations

Papers (8)

LongVLM: Efficient Long Video Understanding via Large Language Models

RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation

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

Mining Inter-Video Proposal Relations for Video Object Detection

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

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

Video Recognition in Portrait Mode

Mask Propagation for Efficient Video Semantic Segmentation