Chenyu Liu

Shuhang Liu, Zhenrong Zhang, Pengfei Hu et al.

In the digital era, the ability to understand visually rich documents that integrate text, complex layouts, and imagery is critical. Traditional Key Information Extraction (KIE) methods primarily rely on Optical Character Recognition (OCR), which often introduces significant latency, computational overhead, and errors. Current advanced image-to-text approaches, which bypass OCR, typically yield plain text outputs without corresponding vision grounding. In this paper, we introduce STNet (See then Tell Net), a novel end-to-end model designed to deliver precise answers with relevant vision grounding. Distinctively, STNet utilizes a unique <see> token to observe pertinent image areas, aided by a decoder that interprets physical coordinates linked to this token. Positioned at the outset of the answer text, the <see> token allows the model to first see-observing the regions of the image related to the input question-and then tell-providing articulated textual responses. To enhance the model's seeing capabilities, we collect extensive structured table recognition datasets. Leveraging the advanced text processing prowess of GPT-4, we develop the TVG (TableQA with Vision Grounding) dataset, which not only provides text-based Question Answering (QA) pairs but also incorporates precise vision grounding for these pairs. Our approach demonstrates substantial advancements in KIE performance, achieving state-of-the-art results on publicly available datasets such as CORD, SROIE, and DocVQA. The code will also be made publicly available.

Chunxia Qin, Zhenrong Zhang, Pengfei Hu et al.

Table structure recognition (TSR) aims to parse the inherent structure of a table from its input image. The `"split-and-merge" paradigm is a pivotal approach to parse table structure, where the table separation line detection is crucial. However, challenges such as wireless and deformed tables make it demanding. In this paper, we adhere to the "split-and-merge" paradigm and propose SEMv3 (SEM: Split, Embed and Merge), a method that is both fast and robust for detecting table separation lines. During the split stage, we introduce a Keypoint Offset Regression (KOR) module, which effectively detects table separation lines by directly regressing the offset of each line relative to its keypoint proposals. Moreover, in the merge stage, we define a series of merge actions to efficiently describe the table structure based on table grids. Extensive ablation studies demonstrate that our proposed KOR module can detect table separation lines quickly and accurately. Furthermore, on public datasets (e.g. WTW, ICDAR-2019 cTDaR Historical and iFLYTAB), SEMv3 achieves state-of-the-art (SOTA) performance. The code is available at https://github.com/Chunchunwumu/SEMv3.

Yuting Tang, Weibang Jiang, Shanglin Li et al.

Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due to the volume and variable quality of EEG data. In this work, we introduce EEG-DLite, a data distillation framework that enables more efficient pre-training by selectively removing noisy and redundant samples from large EEG datasets. EEG-DLite begins by encoding EEG segments into compact latent representations using a self-supervised autoencoder, allowing sample selection to be performed efficiently and with reduced sensitivity to noise. Based on these representations, EEG-DLite filters out outliers and minimizes redundancy, resulting in a smaller yet informative subset that retains the diversity essential for effective foundation model training. Through extensive experiments, we demonstrate that training on only 5 percent of a 2,500-hour dataset curated with EEG-DLite yields performance comparable to, and in some cases better than, training on the full dataset across multiple downstream tasks. To our knowledge, this is the first systematic study of pre-training data distillation in the context of EEG foundation models. EEG-DLite provides a scalable and practical path toward more effective and efficient physiological foundation modeling. The code is available at https://github.com/t170815518/EEG-DLite.

Chenyu Liu, Wangbin Ding, Lei Li et al.

Delineating the brain tumor from magnetic resonance (MR) images is critical for the treatment of gliomas. However, automatic delineation is challenging due to the complex appearance and ambiguous outlines of tumors. Considering that multi-modal MR images can reflect different tumor biological properties, we develop a novel multi-modal tumor segmentation network (MMTSN) to robustly segment brain tumors based on multi-modal MR images. The MMTSN is composed of three sub-branches and a main branch. Specifically, the sub-branches are used to capture different tumor features from multi-modal images, while in the main branch, we design a spatial-channel fusion block (SCFB) to effectively aggregate multi-modal features. Additionally, inspired by the fact that the spatial relationship between sub-regions of tumor is relatively fixed, e.g., the enhancing tumor is always in the tumor core, we propose a spatial loss to constrain the relationship between different sub-regions of tumor. We evaluate our method on the test set of multi-modal brain tumor segmentation challenge 2020 (BraTs2020). The method achieves 0.8764, 0.8243 and 0.773 dice score for whole tumor, tumor core and enhancing tumor, respectively.

Zhen Zhang, Chenyu Liu, Wangbin Ding et al.

Multi-sequence of cardiac magnetic resonance (CMR) images can provide complementary information for myocardial pathology (scar and edema). However, it is still challenging to fuse these underlying information for pathology segmentation effectively. This work presents an automatic cascade pathology segmentation framework based on multi-modality CMR images. It mainly consists of two neural networks: an anatomical structure segmentation network (ASSN) and a pathological region segmentation network (PRSN). Specifically, the ASSN aims to segment the anatomical structure where the pathology may exist, and it can provide a spatial prior for the pathological region segmentation. In addition, we integrate a denoising auto-encoder (DAE) into the ASSN to generate segmentation results with plausible shapes. The PRSN is designed to segment pathological region based on the result of ASSN, in which a fusion block based on channel attention is proposed to better aggregate multi-modality information from multi-modality CMR images. Experiments from the MyoPS2020 challenge dataset show that our framework can achieve promising performance for myocardial scar and edema segmentation.