Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks34 from public data
- Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following248
Point-LLM is presented, the first 3D large language model (LLM) following 3D multi-modal instructions, which injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi- modal question-answering capacity.
- 119
- 90
- 81
- Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding72
A unified framework to disentangle the style factor and the fog factor separately, and then the dual-factor from images in different domains is devised, which achieves the state-of-the-art performance on three benchmarks and shows generalization ability in rainy and snowy scenes.
- 62
- 58
- CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation56
The first vision foundation model for RSDG semantic segmentation, CrossEarth, is introduced, demonstrating strong cross-domain generalization through a specially designed data-level Earth-Style Injection pipeline and a model-level Multi-Task Training pipeline.
- 55
- Rainy WCity: A Real Rainfall Dataset with Diverse Conditions for Semantic Driving Scene Understanding50
A real, comprehensive, and well-annotated scene understanding dataset under rainy weather, named Rainy WCity is pioneer, which covers various rain patterns and their bring-in negative visual effects and an unsupervised contrastive learning network for real image deraining and the final rainy scene semantic segmentation via multi-task joint optimization is designed.
- When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models49
This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data, and examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue.
- Unifying Image Processing as Visual Prompting Question Answering44
Inspired by NLP question answering techniques, PromptGIP treats the input-output image pair as a structured question-answer sentence, thereby reprogramming the image processing task as a prompting QA problem, eliminating the need for task-specific finetuning.
- 36
- FMRNet: Image Deraining via Frequency Mutual Revision34
This work proposes to investigate the potential relationships among rain-free and residue components at the frequency domain, forming a frequency mutual revision network (FMRNet) for image deraining, and explores the mutual representation of rain residue and background components at frequency domain.
- Real-Time Imaging of Intracellular Glutathione Levels Based on a Ratiometric Fluorescent Probe with Extremely Fast Response33
RP-2 was expected to serve as a new fluorescent imaging tool to understand the function of intracellular GSH in the future and had both the largest forward and reverse rate constants thus far.
- 22
- Parsing All Adverse Scenes: Severity-Aware Semantic Segmentation with Mask-Enhanced Cross-Domain Consistency19
The unified framework, named PASS (Parsing All adverSe Scenes), achieves significant performance improvements over state-of-the-art methods on widely-used benchmarks for all adverse scenes, and is superior to Semi-Unified models and even surpasses weather-specific models.
- 16
- 15
- Desalination of Groundwater from a Well in Puglia Region (Italy) by Al2O3-Doped Silica and Polymeric Nanofiltration Membranes12
The objective of this study is to evaluate the performance of the recently reported alumina-doped silica nanofiltration membranes for water potabilization, and to provide a possible solution to improve the groundwater quality in the Puglia Region while maintaining a low energy-footprint.
- Surfactant-Assisted Fabrication of Alumina-Doped Amorphous Silica Nanofiltration Membranes with Enhanced Water Purification Performances12
Surfactant-templated 5 mol% Al2O3-doped silica membranes nanofiltration membranes were synthesized via the sol-gel method, and afterward, were optimized, and tested with respect to the permeability and rejection rate.
- 11
- Train One, Generalize to All: Generalizable Semantic Segmentation from Single-Scene to All Adverse Scenes11
The proposed STA model is based on UDA and employs one source domain, one target domain, and one introduced domain to achieve generalization to all adverse conditions by training on a single-scene dataset and achieves state-of-the-art performance in the Foggy Driving benchmark.
- REMOTE: Reinforced Motion Transformation Network for Semi-supervised 2D Pose Estimation in Videos11
A semi-supervised REinforced MOtion Transformation nEtwork (REMOTE) to leverage a few labeled frames and temporal pose variations in videos, which enables effective learning of 2D pose estimation in sparsely annotated videos.
- Combined Nanofiltration and Thermocatalysis for the Simultaneous Degradation of Micropollutants, Fouling Mitigation and Water Purification10
The development of a new strategy for water purification, which combines a novel and recently developed Al2O3-doped silica nanofiltration membrane with a thermocatalytic perovskite, namely cerium- doped strontium ferrate (CSF), which has a potential to be used in degradation of micropollutants in water treatment.
- 9
- Informative Classes Matter: Towards Unsupervised Domain Adaptive Nighttime Semantic Segmentation9
An Online Informative Class Sampling (OICS) strategy to adaptively mine informative classes from the target nighttime domain according to the corresponding spectrogram mean and the class frequency via the authors' Informative Mixture of Experts framework, which outperforms state-of-the-art UDA-NSS methods by large margins on three widely-used benchmarks.
- Do 3D Large Language Models Really Understand 3D Spatial Relationships?7
Real-3DQA is introduced, a more rigorous evaluation benchmark that filters out easy-to-guess questions and introduces a structured taxonomy to assess various aspects of 3D reasoning, and a 3D-reweighted training objective that guides model to rely more on 3D visual clues, substantially enhancing 3D-LLMs performance in spatial reasoning tasks.
- When Masked Image Modeling Meets Source-free Unsupervised Domain Adaptation: Dual-Level Masked Network for Semantic Segmentation7
A novel Dual-Level Masked Consistency method, which explicitly encourages the model to learn comprehensive context relations, i.e. patch-wise context and channel-wisecontext, on the target domain, to enhance discriminability towards target samples with masked image modeling.
- 5
- –
- –
- –
- –
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. 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.