ViLab

祝贺实验室一项科研成果被 ESWA'25 录用！

Wed, 01 Oct 2025 18:00:00 +0000

祝贺实验室两项科研成果被 MM'25 录用！

Wed, 01 Oct 2025 18:00:00 +0000

祝贺实验室一项科研成果被 AIME'25 录用！

Mon, 01 Sep 2025 18:00:00 +0000

祝贺实验室一项科研成果被 ICIP'25 录用！

Mon, 01 Sep 2025 18:00:00 +0000

祝贺实验室一项科研成果被 TNNLS 录用！

Fri, 01 Aug 2025 18:00:00 +0000

Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

DASH: 4D Hash Encoding with Self-Supervised Decomposition for Real-Time Dynamic Scene Rendering. In Proceedings of the IEEE/CVF International Conference on Computer Vision

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Dome-DETR: DETR with density-oriented feature-query manipulation for efficient tiny object detection

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Efficient Spiking Point Mamba for Point Cloud Analysis

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Egvd: Event-guided video deraining

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Enhancing Visual Question Answering Via Clustered In-Context Sequence Configuration

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Enhancing Visual Tracking by Leveraging High-frequency Information within Event Signals

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Entropy-Adapter-Based Deep Image Compression for User-Generated Content with Knowledge Distillation

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Event-Enhanced Blurry Video Super-Resolution

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Flow-anchored consistency models

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Hierarchical Task-aware Temporal Modeling and Matching for few-shot action recognition

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Hybrid Vision Transformer and Convolutional Neural Network for Super-Resolution Image Quality Assessment

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model. In Proceedings of the Computer Vision and Pattern Recognition Conference

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

MeDKCoOp: Dual Knowledge-guided Graph Prompt Learning for Biomedical Vision-Language Models

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

MMSupcon: An image fusion-based multi-modal supervised contrastive method for brain tumor diagnosis

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Spiking point transformer for point cloud classification

Tue, 01 Jul 2025 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

实验室欢送2025届毕业生，祝同学们前程似锦！

Sun, 01 Jun 2025 08:00:00 +0000

祝贺实验室一项科研成果被 Neurocomputing 录用！

Tue, 01 Apr 2025 18:00:00 +0000

祝贺实验室三项科研成果被 AAAI'25 录用！

Tue, 01 Apr 2025 18:00:00 +0000

祝贺实验室一项科研成果被 DCC 录用！

Sat, 01 Mar 2025 18:00:00 +0000

2025年新年聚餐

Wed, 01 Jan 2025 19:00:00 +0000

祝贺实验室一项科研成果被 BMVC'25 录用！

Wed, 01 Jan 2025 18:00:00 +0000

祝贺实验室一项科研成果被 CVPR'25 录用！

Wed, 01 Jan 2025 18:00:00 +0000

祝贺实验室一项科研成果被 IEEE TCSVT 录用！

Wed, 01 Jan 2025 18:00:00 +0000

祝贺实验室两项科研成果被 ICCV'25 录用！

Wed, 01 Jan 2025 18:00:00 +0000

2024年年终总结

Tue, 10 Dec 2024 14:00:00 +0000

A micro-expression recognition system with event cameras

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Anatomical consistency distillation and inconsistency synthesis for brain tumor segmentation with missing modalities

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

D-FINE: Redefine regression task in DETRs as fine-grained distribution refinement.

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Deep multi-threshold spiking-UNet for image processing

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Ee-mllm: A data-efficient and compute-efficient multimodal large language model

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Estme: Event-driven spatio-temporal motion enhancement for micro-expression recognition

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Event-assisted low-light video object segmentation

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Event-based head pose estimation: Benchmark and method

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Event-based stereo depth estimation by temporal-spatial context learning

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

EvTexture: event-driven texture enhancement for video super-resolution

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Feature Compression With 3D Sparse Convolution

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

GRACE: GRadient-based Active Learning with Curriculum Enhancement for Multimodal Sentiment Analysis

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Image captioning with multi-context synthetic data

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Multi-modal Diffusion Network with Controllable Variability for Medical Image Segmentation

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Multi-modal generative embedding model

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Optimized Decoupled Structure with Non-Local Attention for Deep Image Compression

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Perceptual Image Compression With Conditional Diffusion Transformers

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Scene adaptive sparse transformer for event-based object detection

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Semantic-Enhanced Point-Box Joint Prompting for Video Object Segmentation

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Semi-Supervised Medical Image Segmentation Via Dynamic Pseudo-Label Refinement

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Task navigator: Decomposing complex tasks for multimodal large language models

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Tmformer: Token merging transformer for brain tumor segmentation with missing modalities

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Understanding of facial features in face perception: insights from deep convolutional neural networks

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Visual perception by large language model’s weights. Advances in Neural Information Processing Systems

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Wavelet-like Transform with Subbands Fusion in Decoupled Structure for Deep Image Compression

Mon, 01 Jul 2024 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

欢迎2023级同学加入实验室！

Sun, 05 Nov 2023 19:00:00 +0000

Attention-guided contrastive masked image modeling for transformer-based self-supervised learning

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Better and faster: Adaptive event conversion for event-based object detection

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Deep spiking-unet for image processing

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Electron microscopy image registration using correlation volume

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Eoformer: Edge-oriented transformer for brain tumor segmentation

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Get: Group event transformer for event-based vision

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Learned rate-distortion cost prediction for ultrafast screen content intra coding

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Multimodal sentiment analysis with preferential fusion and distance-aware contrastive learning

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Text-Only Image Captioning with Multi-Context Data Generation

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

Video super-resolution via event-driven temporal alignment

Sat, 01 Jul 2023 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

参加2023年无锡Valse

Thu, 22 Jun 2023 18:00:00 +0000

欢迎2022级同学加入实验室！

Fri, 18 Nov 2022 18:00:00 +0000

Join Us

Mon, 24 Oct 2022 00:00:00 +0000

Tour

Mon, 24 Oct 2022 00:00:00 +0000

实验室成员

Mon, 24 Oct 2022 00:00:00 +0000

Training spiking neural networks with accumulated spiking flow

Thu, 01 Jul 2021 00:00:00 +0000

Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Create your slides in Markdown - click the Slides button to check out the example.

Add the publication’s full text or supplementary notes here. You can use rich formatting such as including code, math, and images.

生物医学图像

Wed, 02 Dec 2020 00:00:00 +0000

本小组致力于将计算机视觉与人工智能前沿算法深度融入临床实践，面向真实世界的医学挑战构建智能化解决方案。我们聚焦于医学影像分析的核心痛点，研究方向涵盖医学图像分割、跨模态转换、图像生成与增强以及多模态医学大模型等前沿课题。特别关注 CT、MRI、病理及超声等多模态数据的深度融合与统一建模，旨在提升诊断效率、优化治疗路径及推动个性化医疗发展。团队与多家三甲医院及顶尖科研机构保持长期紧密合作，积极承担国家重点科研任务，相关成果已在 MICCAI、AAAI 等国际顶级会议与期刊上发表。

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Integer tempus augue non tempor egestas. Proin nisl nunc, dignissim in accumsan dapibus, auctor ullamcorper neque. Quisque at elit felis. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae; Aenean eget elementum odio. Cras interdum eget risus sit amet aliquet. In volutpat, nisl ut fringilla dignissim, arcu nisl suscipit ante, at accumsan sapien nisl eu eros.

Sed eu dui nec ligula bibendum dapibus. Nullam imperdiet auctor tortor, vel cursus mauris malesuada non. Quisque ultrices euismod dapibus. Aenean sed gravida risus. Sed nisi tortor, vulputate nec quam non, placerat porta nisl. Nunc varius lobortis urna, condimentum facilisis ipsum molestie eu. Ut molestie eleifend ligula sed dignissim. Duis ut tellus turpis. Praesent tincidunt, nunc sed congue malesuada, mauris enim maximus massa, eget interdum turpis urna et ante. Morbi sem nisl, cursus quis mollis et, interdum luctus augue. Aliquam laoreet, leo et accumsan tincidunt, libero neque aliquet lectus, a ultricies lorem mi a orci.

Mauris dapibus sem vel magna convallis laoreet. Donec in venenatis urna, vitae sodales odio. Praesent tortor diam, varius non luctus nec, bibendum vel est. Quisque id sem enim. Maecenas at est leo. Vestibulum tristique pellentesque ex, blandit placerat nunc eleifend sit amet. Fusce eget lectus bibendum, accumsan mi quis, luctus sem. Etiam vitae nulla scelerisque, eleifend odio in, euismod quam. Etiam porta ullamcorper massa, vitae gravida turpis euismod quis. Mauris sodales sem ac ultrices viverra. In placerat ultrices sapien. Suspendisse eu arcu hendrerit, luctus tortor cursus, maximus dolor. Proin et velit et quam gravida dapibus. Donec blandit justo ut consequat tristique.

类脑计算

Wed, 02 Dec 2020 00:00:00 +0000

本方向专注于事件相机（Event Camera）信号的处理与高阶视觉应用，旨在挖掘类脑视觉传感器的极速与高动态范围优势。主要研究内容包括：构建基于自注意力的事件分组与特征提取框架，通过分层聚合提升表征能力；设计纹理增强网络，利用迭代融合技术还原图像细节；探索事件引导的语义分割与多模态特征融合模型，增强复杂场景下的解析能力。此外，我们还致力于开发高效的事件特征选择与检测架构，利用稀疏选择机制在保证精度的同时大幅提升计算效率，为高速运动目标检测与极端光照场景下的视觉感知提供技术支撑。

视频理解

Wed, 02 Dec 2020 00:00:00 +0000

本方向聚焦于视频理解、生成与具身智能的核心技术突破。在多模态理解方面，构建融合视觉、文本与语音的统一语义框架，攻克跨模态检索、视觉问答及情感分析等难题。在视频动态解析上，利用时空建模技术实现高精度的行为识别与事件预测。同时，我们积极探索跨模态生成技术，结合扩散模型与自监督学习，推动内容可控且具真实感的图像视频创作。此外，团队正拓展视觉-语言-动作模型（VLA）研究，通过多模态指令理解与物理空间交互建模，赋予智能体连接虚拟认知与实体操作的能力，迈向具身智能的新高度。

视频编码

Wed, 02 Dec 2020 00:00:00 +0000

本小组深入探索下一代图像与视频编码技术，核心方向涵盖端到端编码架构设计、生成式压缩以及特征编码理论。我们致力于突破传统编码框架的性能瓶颈，设计平衡高保真重建与低延迟需求的端到端架构。利用扩散模型与 GAN 等生成式技术，实现低码率下的高感知质量重建，颠覆传统压缩范式。同时，创新性地引入基于类小波变换的子带融合与混合注意力适配器，显著提升对域外图像的压缩鲁棒性。在特征编码方面，我们构建从像素级到语义级的压缩理论体系，探索面向机器视觉任务的语义信息压缩极限，为智能时代的视频传输提供高效解决方案。

Mon, 01 Jan 0001 00:00:00 +0000