We propose FocusCLIP, integrating subject-level guidance--a specialized mechanism for target-specific supervision--into the CLIP framework for improved zero-shot transfer on human-centric tasks. Our novel contributions enhance CLIP on both the vision and text sides. On the vision side, we incorporate ROI heatmaps emulating human visual attention mechanisms to emphasize subject-relevant image regions. On the text side, we introduce human pose descriptions to provide rich contextual information. For human-centric tasks, FocusCLIP is trained with images from the MPII Human Pose dataset. The proposed approach surpassed CLIP by an average of 8.61% across five previously unseen datasets covering three human-centric tasks. FocusCLIP achieved an average accuracy of 33.65% compared to 25.04% by CLIP. We observed a 3.98% improvement in activity recognition, a 14.78% improvement in age classification, and a 7.06% improvement in emotion recognition. Moreover, using our proposed single-shot LLM prompting strategy, we release a high-quality MPII Pose Descriptions dataset to encourage further research in multimodal learning for human-centric tasks. Furthermore, we also demonstrate the effectiveness of our subject-level supervision on non-human-centric tasks. FocusCLIP shows a 2.47% improvement over CLIP in zero-shot bird classification using the CUB dataset. Our findings emphasize the potential of integrating subject-level guidance with general pretraining methods for enhanced downstream performance.

翻译：我们提出FocusCLIP，将主体级引导——一种针对特定目标监督的专门机制——融入CLIP框架，以提升人类中心任务的零样本迁移性能。我们的创新贡献体现在视觉和文本两侧：在视觉侧，引入模拟人类视觉注意机制的ROI热图，强调与主体相关的图像区域；在文本侧，引入人体姿态描述以提供丰富的上下文信息。针对人类中心任务，FocusCLIP使用MPII人体姿态数据集中的图像进行训练。该方法在覆盖三项人类中心任务的五个未见数据集上，平均超越CLIP 8.61%。FocusCLIP的平均准确率达到33.65%，而CLIP为25.04%。在活动识别、年龄分类和情感识别任务上，我们分别观察到3.98%、14.78%和7.06%的提升。此外，通过提出的单次大语言模型提示策略，我们发布高质量MPII姿态描述数据集，以推动人类中心任务的多模态学习研究。进一步地，我们在非人类中心任务上验证了主体级监督的有效性：使用CUB数据集进行零样本鸟类分类时，FocusCLIP相比CLIP提升2.47%。研究结果表明，将主体级引导与通用预训练方法相结合，对提升下游性能具有重要潜力。