[论文粗读][CVPR22workshop]ViTOL: Vision transformer for weakly supervised object localizationPaper ReadingFeb 24, 2023 CV Obejct Localization
[论文粗读][NIPS21]Low-fidelity video encoder optimization for temporal action localizationPaper ReadingTAL任务存在task discrepancy problem，作者参考object detection task中的思路，探索TAL上的end to end trainingFeb 20, 2023 Video Understanding CV Temporal Action Localization
[论文简读][CVPR20]Revisiting the Sibling Head in Object DetectorPaper Reading现有OD处理分类和定位时采用参数共享head，会导致spatial misalignment，作者探索了一种解耦方法来解决此问题Mar 28, 2022 CV Object Detection
[论文简读][CVPR20]Offset Bin Classification Network for Accurate Object DetectionPaper ReadingMar 9, 2022 CV Object Detection
[论文简读][NIPS20]Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object DetectionPaper ReadingMar 6, 2022 CV Object Detection
[论文简读][CVPR19]Distilling Object Detectors with Fine-grained Feature ImitationPaper ReadingMar 4, 2022 CV Object Detection
《TSM: Temporal Shift Module for Efficient Video Understanding》笔记Paper ReadingSep 24, 2020 CV Video Understanding Action Recognition
《Temporal Relational Reasoning in Videos》笔记Paper ReadingSep 16, 2020 CV Video Understanding Action Recognition
《Temporal Segment Networks for Action Recognition in Videos》笔记Paper ReadingSep 15, 2020 CV Video Understanding Action Recognition
![[论文粗读][CVPR22workshop]ViTOL: Vision transformer for weakly supervised object localization](data:image/gif;base64,R0lGODlhAQABAIAAAP///wAAACH5BAEAAAAALAAAAAABAAEAAAICRAEAOw==)