点击@CV51，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】EViT: An Eagle Vision Transformer with Bi-Fovea Self-Attention
-
论文地址：https://arxiv.org//pdf/2310.06629
-
代码即将开源
2.【基础网络架构：Transformer】Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing
-
论文地址：https://arxiv.org//pdf/2310.06234
-
开源代码：https://github.com/DavidYanAnDe/ARC
3.【图像分割】CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
-
论文地址：https://arxiv.org//pdf/2310.06368
-
开源代码：https://github.com/zkzhang98/CoinSeg
4.【领域泛化】Domain Generalization by Rejecting Extreme Augmentations
-
论文地址：https://arxiv.org//pdf/2310.06670
-
开源代码（即将开源）：https://github.com/Masseeh/DCAug
5.【多模态】Uni3D: Exploring Unified 3D Representation at Scale
-
论文地址：https://arxiv.org//pdf/2310.06773
-
开源代码：https://github.com/baaivision/Uni3D
6.【多模态】REVO-LION: Evaluating and Refining Vision-Language Instruction Tuning Datasets
-
论文地址：https://arxiv.org//pdf/2310.06594
-
开源代码（即将开源）：https://github.com/liaoning97/REVO-LION
7.【多模态】What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
-
论文地址：https://arxiv.org//pdf/2310.06627
-
开源代码：https://github.com/Letian2003/C-VQA
8.【多模态】SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network
-
论文地址：https://arxiv.org//pdf/2310.06488
-
即将开源
9.【Diffusion】Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
-
论文地址：https://arxiv.org//pdf/2310.06313
-
开源代码（即将开源）：https://github.com/muzishen/PCDMs
10.【Diffusion】Latent Diffusion Counterfactual Explanations
-
论文地址：https://arxiv.org//pdf/2310.06668
-
开源代码（即将开源）：https://github.com/lmb-freiburg/ldce
11.【网络剪枝】Filter Pruning For CNN With Enhanced Linear Representation Redundancy
-
论文地址：https://arxiv.org//pdf/2310.06344
-
开源代码：https://github.com/Bojue-Wang/CCM-LRR
12.【三维重建】HiFi-123: Towards High-fidelity One Image to 3D Content Generation
-
论文地址：https://arxiv.org//pdf/2310.06744
-
工程主页：HiFi-123
-
代码即将开源
13.【三维重建】CrowdRec: 3D Crowd Reconstruction from Single Color Images
-
论文地址：https://arxiv.org//pdf/2310.06332
-
开源代码：https://github.com/boycehbz/CrowdRec
14.【图像检索】Efficient Retrieval of Images with Irregular Patterns using Morphological Image Analysis: Applications to Industrial and Healthcare datasets
-
论文地址：https://arxiv.org//pdf/2310.06566
-
开源代码：https://github.com/edgetrier/ImgRetreival-DefChars
15.【Temporal action detection】Boundary Discretization and Reliable Classification Network for Temporal Action Detection
-
论文地址：https://arxiv.org//pdf/2310.06403
-
开源代码（即将开源）：https://github.com/zhenyingfang/BDRC-Net
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-2023.10.10
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
