时间汇报人论文题目

20201225

刘文霞

【NeurIPS2020】Rethinking the Value of Labels for Improving Class-Imbalanced Learning, 微信公众号文章


曲晓帆

【ICCV2019】Symmetric Cross Entropy for Robust Learning with Noisy Labels”, International Conference on Computer Vision,北大王奕森老师报告

20201218

修士勇

Contrastive Multi-view Learning and the Influence of View Construction,VALSE自监督学习报告


张天戈

【NeurIPS2020】Rethinking Learnable Tree Filter for Generic Feature Transform,微信公众号文章

20201211

高峰

Finding the Common Ground between Causal Inference and Machine Learning,崔鹏报告


高峰

【NeurIPS2020】Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect汤凯华报告


王会金

Towards Efficient Scene Understanding via Squeeze Reasoning,微信公众号文章

20201204

高琰

Rethinking Bottleneck and Self-attention Structures for Efficient Network Design,来自VALSE 2020冯佳时报告


李欣

【ECCV2020】Dynamic ReLU,微信公众号文章

20201127


焦淑婷

【ICLR2020】LambdaNet: Probabilistic Type Inference using Graph Neural Networks,微信公众号文章


赵政达

【ECCV 2020】Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification,知乎专栏文章

20201113

杨紫陌

Tied Block Convolution, 加州大学伯克利的 Xudong Wang 博士20年9月放在 arxiv 上的论文,知乎专栏文章


刘彦汝

【ECCV 2020】Funnel Activation for Visual Recognition, 知乎专栏文章


高峰

Triplet attention,知乎专栏文章


高峰

【ECCV 2020】IIAI&谷歌等提出MIRNet用于图像修复, 微信公众号文章

20201106

曲磊刚

【ACMMM2020】Context-Aware Multi-View Summarization Network for Image-Text Matching


王猛

【ECCV 2020】Class matter: A fine grained adversarial approach to cross-domain semantic segmentation ,知乎专栏文章

20201030

潘浩东

【ECCV 2020】GINet: Graph Interaction Network for Scene Parsing 来自 ECCV 2020中国预讲会


王俊杰

【ACM MM 2020】Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback

20201023

张马群

【TIP 2020】Neural Multimodal Cooperative Learning Toward Micro-Video Understanding , 技术博客


徐云哲

【ECCV 2020】Class-wise dynamic graph convolution for semantic convolution,来自极市平台ECCV预讲会,        知乎专栏文章

20201016

冯敏

【ECCV2020】Suppressing Mislabeled Data via Grouping and Self-Attention,来自极市平台ECCV预讲会  ,知乎专栏文档


张天戈

【ECCV2020】Self-Supervised CycleGAN for  Object-Preserving Image-to-Image Domain Adaptation,来自极市平台ECCV预讲会      知乎专栏文章

20201009

高峰

小组文化培训 【PPT】 + 跨模态人物关系检测、指代表达、指代分割 【PPT】,知乎专栏文章


曲晓帆

【ECCV2020】 EfficientFCN: Holistically-guided Decoding  for Semantic Segmentation,来自极市平台ECCV预讲会  ,         知乎专栏文章

20200918刘文霞ECCV 2020 论文“解耦自注意模型”,公众号文章
20200911高峰【ECCV2020】Representative graph neural network,来自智源研究院ECCV预讲会
高峰【ECCV2020】AutoMix,来自智源研究院ECCV预讲会
王会金Learning Physical Graph Representations from Visual Scenes 图推理用于场景理解
20200903高峰【ECCV2020】WeightNet,知乎文章
修士勇【ECCV2020】Context-Gated Convolution 知乎专栏文章
张天戈【ECCV2020】Unsupervised sketch-to-photo synthesis 来自智源研究院ECCV预讲会
20200903高峰【WACV2020】ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
知乎专栏文章
高琰【ICML 2020 杰出论文】 Tuning-free plug-and-play proximal algorithm for inverse imaging problems 作者讲解视频