ICCV2021 Oral 論文及論文實現程式碼合集

ICCV2021共接收有效投稿6236篇論文,其中1617 篇論文被接受,接收率為 25。9%。AMienr根據會議論文情況,已經上線了ICCV2021會議系統,將從論文、學者、論文解讀和影片等多維度進行解讀,歡迎持續關注!

1、Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation(Oral)

連結:https://www。aminer。cn/pub/60fe353b5244ab9dcb3567b9?f=toutiao

2、Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation(Oral)

連結:https://www。aminer。cn/pub/60fe36095244ab9dcb35b009?f=toutiao

程式碼:https://github。com/CVMI-Lab/DARS

3、Human Pose Regression with Residual Log-likelihood Estimation(Oral)

連結:https://www。aminer。cn/pub/60fe36535244ab9dcb35cd35?f=toutiao

程式碼:https://github。com/Jeff-sjtu/res-loglikelihood-regression

4、Robustness via Cross-Domain Ensembles(Oral)

連結:https://www。aminer。cn/pub/6058732991e011537aff4d26?f=toutiao

程式碼:https://github。com/EPFL-VILAB/XDEnsembles

5、Warp Consistency for Unsupervised Learning of Dense Correspondences(Oral)

連結:https://www。aminer。cn/pub/606eeb3e91e011aa47b6acc8?f=toutiao

程式碼:https://github。com/PruneTruong/DenseMatching

6、PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop(Oral)

連結:https://www。aminer。cn/pub/6064656691e011538305d177?f=toutiao

程式碼:https://github。com/HongwenZhang/PyMAF

7、HuMoR: 3D Human Motion Model for Robust Pose Estimation(Oral)

連結:https://www。aminer。cn/pub/609ba31691e0113c3c7692af?f=toutiao

程式碼:https://geometry。stanford。edu/projects/humor/

8、Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers(Oral)

連結:https://www。aminer。cn/pub/60643b3b91e011538305ce3b?f=toutiao

程式碼:https://github。com/hila-chefer/Transformer-MM-Explainability

9、MDETR : Modulated Detection for End-to-End Multi-Modal Understanding(Oral)

連結:https://www。aminer。cn/pub/6088060391e011e25a316ebb?f=toutiao

程式碼:https://github。com/ashkamath/mdetr

10、Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions(Oral)

連結:https://www。aminer。cn/pub/6037844c91e011d7c73cd4b7?f=toutiao

程式碼:https://github。com/whai362/PVT

11、Mining Latent Classes for Few-shot Segmentation(Oral)

連結:https://www。aminer。cn/pub/60630f4191e0118c891f1bd9?f=toutiao

程式碼:https://github。com/LiheYoung/MiningFSS

12、In-Place Scene Labelling and Understanding with Implicit Scene Representation(Oral)

連結:https://www。aminer。cn/pub/6064451791e011538305ceff?f=toutiao

程式碼:https://shuaifengzhi。com/Semantic-NeRF/

13、Just Ask: Learning to Answer Questions from Millions of Narrated Videos(Oral)

連結:https://www。aminer。cn/pub/5fc7730991e0114897921243?f=toutiao

程式碼:https://github。com/antoyang/just-ask

更多ICCV2021會議論文:https://www。aminer。cn/conf/iccv2021/papers?f=toutiao