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.【基础网络架构:Transformer】(NeurIPS2023)MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory
-
论文地址:https://arxiv.org//pdf/2310.16898
-
开源代码(即将开源):https://github.com/liangyn22/MCUFormer
2.【Open-Vocabulary Object Detection】LP-OVOD: Open-Vocabulary Object Detection by Linear Probing
-
论文地址:https://arxiv.org//pdf/2310.17109
-
开源代码(即将开源):https://github.com/VinAIResearch/LP-OVOD
3.【视频异常检测】A Coarse-to-Fine Pseudo-Labeling (C2FPL) Framework for Unsupervised Video Anomaly Detection
-
论文地址:https://arxiv.org//pdf/2310.17650
-
开源代码(即将开源):https://github.com/AnasEmad11/C2FPL
4.【视频超分辨率重建】(WACV2024)Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution
-
论文地址:https://arxiv.org//pdf/2310.17294
-
开源代码:https://github.com/megvii-research/WACV2024-SAFA
5.【图像增强】(NeurIPS2023)Global Structure-Aware Diffusion Process for Low-Light Image Enhancement
-
论文地址:https://arxiv.org//pdf/2310.17577
-
开源代码(即将开源):https://github.com/jinnh/GSAD
6.【领域泛化】SPA: A Graph Spectral Alignment Perspective for Domain Adaptation
-
论文地址:https://arxiv.org//pdf/2310.17594
-
开源代码(即将开源):https://github.com/CrownX/SPA
7.【多模态】(EMNLP2023)Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models
-
论文地址:https://arxiv.org//pdf/2310.17530
-
开源代码:https://github.com/coastalcph/gender-neutral-vl
8.【多模态】(NeurIPS2023)Cross-modal Active Complementary Learning with Self-refining Correspondence
-
论文地址:https://arxiv.org//pdf/2310.17468
-
开源代码(即将开源):https://github.com/QinYang79/CRCL
9.【自动驾驶】Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models
-
论文地址:https://arxiv.org//pdf/2310.17642
-
工程主页:Drive Anywhere: Generalizable End-to-end Autonomous Driving with Multi-modal Foundation Models
-
开源代码(即将开源):https://github.com/zswang666/drive-anywhere
10.【自动驾驶:BEV】BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
-
论文地址:https://arxiv.org//pdf/2310.17281
-
开源代码:https://github.com/valeoai/BEVContrast
11.【自动驾驶:协同感知】(WACV2024)MACP: Efficient Model Adaptation for Cooperative Perception
-
论文地址:https://arxiv.org//pdf/2310.16870
-
开源代码:https://github.com/PurdueDigitalTwin/MACP
12.【NeRF】4D-Editor: Interactive Object-level Editing in Dynamic Neural Radiance Fields via 4D Semantic Segmentation
-
论文地址:https://arxiv.org//pdf/2310.16858
-
工程主页:4D-Editor: Interactive Object-level Editing in Dynamic Neural Radiance Fields via 4D Semantic Segmentation
-
代码即将开源
论文已打包,下载链接
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-2023.10.26
CV计算机视觉每日开源代码Paper with code速览-2023.10.25
CV计算机视觉每日开源代码Paper with code速览-2023.10.24
CV计算机视觉每日开源代码Paper with code速览-2023.10.23
使用目标之间的先验关系提升目标检测器性能
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?
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