ICCV2021 Oral 论文及论文实现代码合集

ICCV2021共接收有效投稿6236篇论文，其中1617 篇论文被接受，接收率为 25.9%。AMienr根据会议论文情况，已经上线了ICCV2021会议系统，将从论文、学者、论文解读和视频等多维度进行解读，欢迎持续关注！

1、Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation(Oral)
链接：https://www.aminer.cn/pub/60fe353b5244ab9dcb3567b9

2、Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation(Oral)
链接：https://www.aminer.cn/pub/60fe36095244ab9dcb35b009
代码：https://github.com/CVMI-Lab/DARS

3、Human Pose Regression with Residual Log-likelihood Estimation(Oral)
链接：https://www.aminer.cn/pub/60fe36535244ab9dcb35cd35
代码：https://github.com/Jeff-sjtu/res-loglikelihood-regression

4、Robustness via Cross-Domain Ensembles(Oral)
链接：https://www.aminer.cn/pub/6058732991e011537aff4d26
代码：https://github.com/EPFL-VILAB/XDEnsembles

5、Warp Consistency for Unsupervised Learning of Dense Correspondences(Oral)
链接：https://www.aminer.cn/pub/606eeb3e91e011aa47b6acc8
代码：https://github.com/PruneTruong/DenseMatching

6、PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop(Oral)
链接：https://www.aminer.cn/pub/6064656691e011538305d177
代码：https://github.com/HongwenZhang/PyMAF

7、HuMoR: 3D Human Motion Model for Robust Pose Estimation(Oral)
链接：https://www.aminer.cn/pub/609ba31691e0113c3c7692af
代码：https://geometry.stanford.edu/projects/humor/

8、Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers(Oral)
链接：https://www.aminer.cn/pub/60643b3b91e011538305ce3b
代码：https://github.com/hila-chefer/Transformer-MM-Explainability

9、MDETR : Modulated Detection for End-to-End Multi-Modal Understanding(Oral)
链接：https://www.aminer.cn/pub/6088060391e011e25a316ebb
代码：https://github.com/ashkamath/mdetr

10、Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions(Oral)
链接：https://www.aminer.cn/pub/6037844c91e011d7c73cd4b7
代码：https://github.com/whai362/PVT

11、Mining Latent Classes for Few-shot Segmentation(Oral)
链接：https://www.aminer.cn/pub/60630f4191e0118c891f1bd9
代码：https://github.com/LiheYoung/MiningFSS

12、In-Place Scene Labelling and Understanding with Implicit Scene Representation(Oral)
链接：https://www.aminer.cn/pub/6064451791e011538305ceff
代码：https://shuaifengzhi.com/Semantic-NeRF/

13、Just Ask: Learning to Answer Questions from Millions of Narrated Videos(Oral)
链接：https://www.aminer.cn/pub/5fc7730991e0114897921243
代码：https://github.com/antoyang/just-ask

更多ICCV2021会议论文：https://www.aminer.cn/conf/iccv2021/papers