精华置顶
墙裂推荐!小白如何1个月系统学习CV核心知识:链接
点击@CV计算机视觉,关注更多CV干货
论文已打包,点击进入—>下载界面
点击加入—>CV计算机视觉交流群
1.【语义分割】IDRNet: Intervention-Driven Relation Network for Semantic Segmentation
-
论文地址:https://arxiv.org//pdf/2310.10755
-
开源代码:https://github.com/SegmentationBLWX/sssegmentation
2.【医学图像分割:3D】Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation
-
论文地址:https://arxiv.org//pdf/2310.11320
-
开源代码:https://github.com/xmed-lab/GenericSSL
3.【多模态】Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
-
论文地址:https://arxiv.org//pdf/2310.11441
-
工程主页:SoM-GPT4V
-
开源代码(暂未开源):https://github.com/microsoft/SoM
4.【多模态】EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
-
论文地址:https://arxiv.org//pdf/2310.11440
-
工程主页:EvalCrafter
-
开源代码(即将开源):https://github.com/EvalCrafter/EvalCrafter
5.【多模态】Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models
-
论文地址:https://arxiv.org//pdf/2310.11173
-
开源代码:https://github.com/shuowang26/EndoKED
6.【数字人】CorrTalk: Correlation Between Hierarchical Speech and Facial Activity Variances for 3D Animation
-
论文地址:https://arxiv.org//pdf/2310.11295
-
工程主页:CorrTalk
-
开源代码(即将开源):https://github.com/zjchu/CorrTalk
7.【单目3D目标检测】MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient
-
论文地址:https://arxiv.org//pdf/2310.11316
-
开源代码:https://github.com/Senwang98/MonoSKD
8.【自动驾驶:Occupancy Prediction】LiDAR-based 4D Occupancy Completion and Forecasting
-
论文地址:https://arxiv.org//pdf/2310.11239
-
开源代码(即将开源):https://github.com/ai4ce/Occ4cast
9.【视频生成】LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation
-
论文地址:https://arxiv.org//pdf/2310.10769
-
工程主页:LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation
-
开源代码:https://github.com/RQ-Wu/LAMP
论文已打包,点击进入—>下载界面
CV计算机视觉交流群
群内包含目标检测、图像分割、目标跟踪、Transformer、多模态、NeRF、GAN、缺陷检测、显著目标检测、关键点检测、超分辨率重建、SLAM、人脸、OCR、生物医学图像、三维重建、姿态估计、自动驾驶感知、深度估计、视频理解、行为识别、图像去雾、图像去雨、图像修复、图像检索、车道线检测、点云目标检测、点云分割、图像压缩、运动预测、神经网络量化、网络部署等多个领域的大佬,不定期分享技术知识、面试技巧和内推招聘信息。
想进群的同学请添加微信号联系管理员:PingShanHai666。添加好友时请备注:学校/公司+研究方向+昵称。
推荐阅读:
CV计算机视觉每日开源代码Paper with code速览-2023.10.17
CV计算机视觉每日开源代码Paper with code速览-2023.10.16
CV计算机视觉每日开源代码Paper with code速览-2023.10.13
使用目标之间的先验关系提升目标检测器性能
港科大提出适用于夜间场景语义分割的无监督域自适应新方法
HSN:微调预训练ViT用于目标检测和语义分割,华南理工和阿里巴巴联合提出
EViT:借鉴鹰眼视觉结构,南开大学等提出ViT新骨干架构,在多个任务上涨点
如何优雅地读取网络的中间特征?