VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting

VLCounter：零样本目标计数的文本感知视觉表示.

Semantic Generative Augmentations for Few-Shot Counting

少样本计数的语义生成增强.

博物记：银杏

Natural Record: Ginkgo.

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

FlashFFTConv: 使用张量核实现长序列的高效卷积.

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

DetCLIPv2：通过词汇-区域对齐实现可扩展开放词汇目标检测预训练.

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

DetCLIP：用于开放世界检测的字典增强视觉概念并行预训练.