6 papers · 1 filter
AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
Yonghui Wang, Wengang Zhou, Hao Feng +1
Over the past few years, the advancement of Multimodal Large Language Models (MLLMs) has captured the wide interest of researchers, leading to numerous innovations to enhance MLLMs…
LaneTCA: Enhancing Video Lane Detection with Temporal Context Aggregation
Keyi Zhou, Li Li, Wengang Zhou +3
In video lane detection, there are rich temporal contexts among successive frames, which is under-explored in existing lane detectors. In this work, we propose LaneTCA to bridge th…
RoFIR: Robust Fisheye Image Rectification Framework Impervious to Optical Center Deviation
Zhaokang Liao, Hao Feng, Shaokai Liu +2
Fisheye images are categorized fisheye into central and deviated based on the optical center position. Existing rectification methods are limited to central fisheye images, while t…
Progressive Multi-modal Conditional Prompt Tuning
Xiaoyu Qiu, Hao Feng, Yuechen Wang +2
Pre-trained vision-language models (VLMs) have shown remarkable generalization capabilities via prompting, which leverages VLMs as knowledge bases to extract information beneficial…
TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
Bozhi Luan, Hao Feng, Hong Chen +3
The advent of Large Multimodal Models (LMMs) has sparked a surge in research aimed at harnessing their remarkable reasoning abilities. However, for understanding text-rich images,…
DeepEraser: Deep Iterative Context Mining for Generic Text Eraser
Hao Feng, Wendi Wang, Shaokai Liu +3
In this work, we present DeepEraser, an effective deep network for generic text removal. DeepEraser utilizes a recurrent architecture that erases the text in an image via iterative…