V
主页
20220323【我要找到你：2D/3D物体检测和定位】贺通：3D instance segmentation with dynamic convolution
发布人
报告嘉宾：贺通 (上海人工智能实验室) 报告时间：2022年03月23日 (星期三)晚上20:00 (北京时间) 报告题目：3D instance segmentation with dynamic convolution 报告人简介： Tong was a Research Fellow at Australian Institute for Machine Learning (AIML), the University of Adelaide, working with Prof. Chunhua Shen and Prof. Anton van den Hengel. Tong got his PhD in computer science at the University of Adelaide and supervised by Chunhua Shen. He was a visiting student at MMLAB of the Chinese University of Hong Kong at Shenzhen under the supervision of Prof.Yu Qiao and Dr.Weilin Huang. His research interests lie in the area of computer vision and machine learning, especially in enabling machines to see and understand the environment. Specific research topics include 2D/3D object detection and instance segmentation. 个人主页： https://tonghe90.github.io 报告摘要： Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions. The inevitable variation in the instance scales can lead bottom-up methods to become particularly sensitive to hyper-parameter values. To this end, we propose instead a dynamic, proposal-free, data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances. The proposed method achieves promising results on both ScanetNetV2 and S3DIS, and this performance is robust to the particular hyper-parameter values chosen.
打开封面
下载高清视频
观看高清视频
视频下载器
20220323【我要找到你：2D/3D物体检测和定位】Panel
20230531【大模型时代下的三维视觉：路在何方？】杨波：3D Semantic and Instance Segmentation without 3D……
20220413【脑启发视觉】Panel
20210120【无人驾驶场景3D物体检测与跟踪】 周星壹 Center-based 3D Object Detection and Tracking
20240717【面向事件相机的物体检测与跟踪】李家宁：Object Detection with Neuromorphic Cameras
20220105【标签噪声学习专题论坛】彭玺：噪声关联学习：一种新的噪声标注学习范式
20220112【脉络分明：脉冲神经网络及其应用】余肇飞：脉冲神经网络学习理论与方法
20220119特邀报告【智能情绪感知与情感接口】赵国英(芬兰Oulu大学)
【VALSE2024】0505 吴小俊《特邀报告：多模态视觉融合方法：是否存在性能极限？》
20220113 VALSE Student Webinar【论文写作那些事儿】王玫：科研路上的心得与体会
【VALSE论文速览-80期】Exploring Cross-Image Pixel Contrast for Semantic Segmentation
20240814【多模态医学图像处理及医学大模型的发展近况】Panel
【VALSE2024】0505 赵恒爽《APR：视觉基础大模型》
20230329【多模态预训练的研究进展与未来】Panel
20211222【自动驾驶中的机器视觉与学习问题】赵行：环视自动驾驶感知
20220706【联邦学习在医学图像处理的应用】李霄霄：Federated learning for healthcare: from theory to……
20240605【Prompt Learning in Vision】刘东方：Prompt Tuning as Sustainable Fast Learner
【VALSE论文速览-54期】Learngene：从开放世界到目标学习任务
20210922 特邀报告【具身智能 (Embodied AI)】卢策吾 (上海交通大学)
20230607【开放世界的感知：探索可迁移与可持续学习之路】巩东：Continual Learning and Memory Augmentation……
【VALSE论文速览-69期】Learning with Twin Noisy Labels for Visible-Infrared Person……
【VALSE2024】0506《Workshop ：具身智能的视觉与学习》
20211229【基于神经表示的三维建模与渲染】许岚：基于神经网络的人体动态捕捉与渲染
【VALSE2024】0505 李鸿升《特邀报告：图像生成和视频生成若干前沿技术探索》
20211021【Transformer在医学图像处理的应用】Panel
20240320【鲁棒开放世界感知】杨丽鹤：Depth Anything: Unleashing the Power of Large-Scale Unlab…
20211021【Transformer在医学图像处理的应用】付华柱：Transformers 在多模态 MR 成像中的应用
20240828【医学多模态分析与研究：从传统模型到大模型的演变】刘明霞：多中心多模态脑影像智能分析及应用研究
【VALSE2024】0505 王兴刚《APR：面向大模型的新型高效率网络架构》
20210714【弱监督视觉学习：定位、分割及其他】万方：Weakly Supervised Object Localization：From CNN to…
20220831【就正有道：物理机理驱动的图像恢复与增强】任文琦：融合先验知识的图像视频复原方法研究
计算机视觉如何入门？手把手教会你【物体检测YOLOv8】，快速上手深度学习，简单高效！！！
20210811【知其所以然：因果推理与学习】张含望：真正的无偏模型
20230322【大规模预训练模型的可信性】庞天宇：Trustworthy Diffusion Models & Diffusion Models for……
20230322【大规模预训练模型的可信性】Panel
20240814【多模态医学图像处理及医学大模型的发展近况】王连生：病理数据的多模态分析
【VALSE论文速览-64期】用于图像盲超分辨的无监督退化表示学习
20220420【点云场景理解】赵恒爽：Scene Understanding in 3D and 2D-3D
20220907【自动驾驶感知】李鸿升：MPPNet: Multi-Frame Feature Intertwining with Proxy Points……
【VALSE论文速览-55期】PyMAF：基于多尺度网格对齐反馈机制的三维人体模型重建
