與陽光共進(jìn)早餐

IP屬地：江蘇

論文｜ ECCV24: Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector
1 寫在前面論文解讀系列斷更很久了士八，感覺自己還是挺喜歡文字的牺堰，這次先從介紹我們自己發(fā)表在ECCV24工作開始恢復(fù)一下～主要信息文章：htt...

109 0 0
Generative Modeling for Small-Data Object Detection (ICCV2019)
1. main info iccv2019 task: Small-Data Object Detection main idea: using...

107 0 0

Paper | OVTrack: Open-Vocabulary Multiple Object Tracking
1 basic info OVTrack: Open-Vocabulary Multiple Object Tracking paper[htt...

1.0 325 1 1
Paper | Tracking everything in the wild
1 寫在前面 https://arxiv.org/pdf/2207.12978.pdf[https://arxiv.org/pdf/2207.1...

0.9 89 0 1
Paper ｜ Open Vocabulary Object Detection with Pseudo Bounding-Box Labels （ECCV 2022）
1. 寫在前面 https://arxiv.org/abs/2111.09452[https://arxiv.org/abs/2111.0945...

0.8 201 0 2
Paper | Detecting?Twenty-thousand?Classes?using?Image-level?Supervision
寫在前面文章出處： ECCV 2022 模型名字： Detic 整體概括：這篇文章跟最開始的OVD-Net一樣，都是從pretraining的...

1.0 214 0 1
Paper ｜ Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers
1 introduction 1.1 main story OVD： training text category as text embedd...

1.0 144 0 1

Topic | Advancements in Embodied AI: Integrating Large Language Models and Open-Vocabulary Manipu...
1. 寫在前面簡略地了解一下基于LLMs的embodied AI進(jìn)展 2. paper：Embodied Task Planning wit...

0.9 169 0 1
task | U-net based semantic segmentation
一寫在前面之前沒有太了解segmentation任務(wù)是怎么做的搅裙，重溫一下經(jīng)典的u net結(jié)構(gòu)皱卓。 U-Net: Convolutional N...

71 0 0