Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks20 from public data
- Qwen2.5-VL Technical Report6,169
This work introduces Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities, and maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.
- Qwen3-VL Technical Report2,675
Qwen3-VL is introduced, the most capable vision-language model in the Qwen series to date, achieving superior performance across a broad range of multimodal benchmarks, and three key upgrades are introduced, including an enhanced interleaved-MRoPE for stronger spatial-temporal modeling across images and video.
- On classification of distorted images with deep convolutional neural networks124
The results suggest that, under certain conditions, fine-tuning with noisy images can alleviate much effect due to distorted inputs, and is more practical than re-training.
- Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding113
Hulu-Med is introduced, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture, and outperforms proprietary systems such as GPT-4o on 16 benchmarks.
- OMNIPARSER: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition107
A universal model, called OmniParser, which can simultaneously handle three typical visually-situated text parsing tasks: text spotting, key information extraction, and table recognition is devised, which achieves state-of-the-art or highly competitive performances on 7 datasets for the three visually-situated text parsing tasks, despite its unified, concise design.
- 79
- Egocentric activity recognition with multimodal fisher vector47
A novel strategy to extract temporal trajectory-like features from sensor data and propose to apply the Fisher Kernel framework to fuse video and temporal enhanced sensor features to enhance information-rich video data is presented.
- Activity Recognition in Egocentric Life-Logging Videos43
This work builds an egocentric video dataset dubbed LENA (Life-logging EgoceNtric Activities) which includes egOCentric videos of 13 fine-grained activity categories, recorded under diverse situations and environments using the Google Glass and evaluates state-of-the-art activity recognition using LENA in detail and also analyzes the performance of popular descriptors in Egocentric activity recognition.
- Vision-Language Pre-Training for Boosting Scene Text Detectors42
This paper proposes to learn contextualized, joint representations through vision-language pretraining, for the sake of enhancing the performance of scene text detectors, and devise a pre-training architecture with an image encoder, a text encoder and a cross-modal encoder.
- Modeling Entities as Semantic Points for Visual Information Extraction in the Wild29
Extensive experiments on standard benchmarks in this field as well as the proposed dataset demonstrate that the proposed method can achieve significantly enhanced performance on entity labeling and linking, compared with previous state-of-the-art models.
- Saak Transform-Based Machine Learning for Light-Sheet Imaging of Cardiac Trabeculation27
A machine learning framework with augmented kernels based on the Karhunen-Loeve Transform (KLT) to preserve linearity and reversibility of rectification and create a data-driven machine learning for 3-D quantification of cardiac ultra-structure.
- OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models24
OmniParser V2 is introduced, a universal model that unifies VsTP typical tasks, including text spotting, key information extraction, table recognition, and layout analysis, into a unified framework, and central to the proposed Structured-Points-of-Thought prompting schemas, which improves model performance across diverse scenarios.
- 20
- Deep Adaptive Temporal Pooling for Activity Recognition18
A learnable and differentiable module: Deep Adaptive Temporal Pooling (DATP), which applies a self-attention mechanism to adaptively pool the classification scores of different video segments to improve training of frame-level feature extractor.
- 17
- CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making6
A novel large-scale RL framework for Med-VLMs, Consistency-Aware Preference Optimization (CAPO), which integrates rewards to ensure fidelity between perception and reasoning, consistency in reasoning-to-answer derivation, and rule-based accuracy for final responses is proposed.
- Generative compositor for few-shot visual information extraction3
A novel generative model, named Generative Compositor, is proposed to address the challenge of few-shot VIE, a hybrid pointer-generator network that emulates the operations of a compositor by retrieving words from the source text and assembling them based on the provided prompts.
- 1
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.