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.【目标检测】A Novel Voronoi-based Convolutional Neural Network Framework for Pushing Person Detection in Crowd Videos
-
论文地址:https://arxiv.org//pdf/2310.07416
-
开源代码:https://github.com/PedestrianDynamics/VCNN4PuDe
2.【目标检测、分割】Relational Prior Knowledge Graphs for Detection and Instance Segmentation
-
论文地址:https://arxiv.org//pdf/2310.07573
-
开源代码(即将开源):https://github.com/ozzyou/RP-FEM
3.【异常检测】PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
-
论文地址:https://arxiv.org//pdf/2310.07716
-
开源代码:https://github.com/EricLee0224/PAD
4.【异常检测】A Discrepancy Aware Framework for Robust Anomaly Detection
-
论文地址:https://arxiv.org//pdf/2310.07585
-
开源代码:https://github.com/caiyuxuan1120/DAF
5.【异常检测】A Unified Remote Sensing Anomaly Detector Across Modalities and Scenes via Deviation Relationship Learning
-
论文地址:https://arxiv.org//pdf/2310.07511
-
开源代码(即将开源):https://github.com/Jingtao-Li-CVer/UniADRS
6.【语义分割】Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation
-
论文地址:https://arxiv.org//pdf/2310.07265
-
工程主页:C2VKD
-
代码即将开源
7.【多模态】ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation
-
论文地址:https://arxiv.org//pdf/2310.07697
-
工程主页:ConditionVideo: Training-Free Condition-Guided Video Generation
-
开源代码:https://github.com/pengbo807/ConditionVideo
8.【多模态】Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else
-
论文地址:https://arxiv.org//pdf/2310.07419
-
工程主页:Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else
-
代码即将开源
9.【多模态】Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images
-
论文地址:https://arxiv.org//pdf/2310.07027
-
代码即将开源
10.【数字人】AdaMesh: Personalized Facial Expressions and Head Poses for Speech-Driven 3D Facial Animation
-
论文地址:https://arxiv.org//pdf/2310.07236
-
工程主页:AdaMesh
-
开源代码(即将开源):https://github.com/adamesh/adamesh
11.【自动驾驶:radar】Dual Radar: A Multi-modal Dataset with Dual 4D Radar for Autononous Driving
-
论文地址:https://arxiv.org//pdf/2310.07602
-
开源代码:https://github.com/adept-thu/Dual-Radar
12.【图像修复】Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model
-
论文地址:https://arxiv.org//pdf/2310.07222
-
开源代码(即将开源):GitHub - ysy31415/unipaint: Code Implementation of "Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model"
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-2023.10.11-CSDN博客
CV计算机视觉每日开源代码Paper with code速览-2023.10.10
CV计算机视觉每日开源代码Paper with code速览-2023.10.9
CV计算机视觉每日开源代码Paper with code速览-2023.10.6