组会图复现ppt

Paper info	Key elements
> Learning Independent Instance Maps for Crowd Localization（IIM）	> Rounded line arrow（圆角折线箭头）
> Changes to Captions: An Attentive Network for Remote Sensing Change Captioning	> Partitioned cube（分块立方体）
> Attention Is All You Need	>Custom curved arrow（自定义弯曲箭头）
> Image Captioning with Deep Bidirectional LSTMs
> EVCAP Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension	> Vector icon（矢量图标）
> Few-shot Oriented Object Detection with Memorable Contrastive Learning in Remote Sensing Images	> Thin rectangle（薄长方体）
> Transferable Decoding with Visual Entities for Zero-Shot Image Captioning
>UP-Diff Latent Diffusion Model for Remote Sensing Urban Prediction	> Judge the arrow is straight or not（判断箭头笔直与否）
>GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature-Guided DDPM	> Any shape polygon（任意形状多边形）
>GCD-DDPM: Language-only Efficient Training of Zero-shot Composed Image Retrieval
>Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models	> Half curved rectangle（半曲线矩形）
>From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping	> Merge shapes（合并形状）
>KIND: Knowledge Integration and Diversion in Diffusion Models	> Color box（彩色方块）
>Single-Stream Extractor Network With Contrastive Pre-Training for Remote-Sensing Change Captioning
>Diffusion-RSCC: Diffusion Probabilistic Model for Change Captioning in Remote Sensing Images	> 立方体阴影、平面堆叠正方形
>CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval	> islide（PPT插件）
>Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation	> 均匀分布、堆叠矩形
>MeTA: Multi-source Test Time Adaptation	> 不同曲线的选用和坐标轴设置
>Teaching CLIP to Count to Ten