7 papers
SFA: Scan, Focus, and Amplify toward Guidance-aware Answering for Video TextVQA
Haibin He, Qihuang Zhong, Juhua Liu +3
Video text-based visual question answering (Video TextVQA) task aims to answer questions about videos by leveraging the visual text appearing within the videos. This task poses sig…
Rethink Sparse Signals for Pose-guided Text-to-image Generation
Wenjie Xuan, Jing Zhang, Juhua Liu +2
Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-imag…
Resolving Knowledge Conflicts in Domain-specific Data Selection: A Case Study on Medical Instruction-tuning
Qihuang Zhong, Liang Ding, Fei Liao +3
Domain-specific instruction-tuning has become the defacto standard for improving the performance of large language models (LLMs) in specialized applications, e.g., medical question…
Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?
Haibin He, Maoyuan Ye, Jing Zhang +4
Large Multimodal Models (LMMs) have become increasingly versatile, accompanied by impressive Optical Character Recognition (OCR) related capabilities. Existing OCR-related benchmar…
GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
Haibin He, Jing Zhang, Maoyuan Ye +3
Video text spotting (VTS) extends image text spotting (ITS) by adding text tracking, significantly increasing task complexity. Despite progress in VTS, existing methods still fall…
Adapting Segment Anything Model for Power Transmission Corridor Hazard Segmentation
Hang Chen, Maoyuan Ye, Peng Yang +3
Power transmission corridor hazard segmentation (PTCHS) aims to separate transmission equipment and surrounding hazards from complex background, conveying great significance to mai…