5 papers
TADoc: Robust Time-Aware Document Image Dewarping
Fangmin Zhao, Weichao Zeng, Zhenhang Li +2
Flattening curved, wrinkled, and rotated document images captured by portable photographing devices, termed document image dewarping, has become an increasingly important task with…
An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
Daiqing Wu, Dongbao Yang, Sicheng Zhao +2
The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm. This paradigm sidesteps the cost of m…
Specifying What You Know or Not for Multi-Label Class-Incremental Learning
Aoting Zhang, Dongbao Yang, Chang Liu +2
Existing class incremental learning is mainly designed for single-label classification task, which is ill-equipped for multi-label scenarios due to the inherent contradiction of le…
DCA: Dividing and Conquering Amnesia in Incremental Object Detection
Aoting Zhang, Dongbao Yang, Chang Liu +3
Incremental object detection (IOD) aims to cultivate an object detector that can continuously localize and recognize novel classes while preserving its performance on previous clas…
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
Gangyan Zeng, Yuan Zhang, Jin Wei +5
Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which r…