Scholarlink

<p>The diversity and combinatorial complexity of real-world human-object interactions (HOI) make it impractical for any single dataset to encompass all variations. This requires models with robust zero-shot learning capabilities to infer unseen interactions. A novel approach for HOI detection is proposed, leveraging adaptive contrastive learning and class-specific feature enhancement. This method improves detection accuracy by assigning adaptive weights to challenging samples and incorporating additional human, object, and interaction-specific features. Adaptive contrastive learning computes dynamic weights based on the similarity between each HOI instance and its label, allowing the model to focus more on challenging and long-tail samples. Class-specific feature enhancement improves the matcher by separately calculating losses for humans, objects, and interactions. Experimental results on the HICO-DET and SWIG-HOI datasets demonstrate the effectiveness of the proposed method in detecting seen and unseen interactions. The code is available at <a href="https://github.com/small-code-cat/ACL-CFE">https://github.com/small-code-cat/ACL-CFE</a> (Adaptive Contrastive Learning-Class-specific Feature Enhancement).</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Human-object interaction detection based on adaptive contrastive learning and class-specific feature enhancement

  • 期刊论文

  • 发表日期：

    2025年7月10日

查看全文
  • Huanchun Peng,
  • Kejun Xue,
  • Xincheng Wang,
  • Yongbin Gao,
  • Zhijun Fang,
  • Xiaoyan Jiang,
  • Wenjun Yu,
  • Chenmou Wu

摘要

The diversity and combinatorial complexity of real-world human-object interactions (HOI) make it impractical for any single dataset to encompass all variations. This requires models with robust zero-shot learning capabilities to infer unseen interactions. A novel approach for HOI detection is proposed, leveraging adaptive contrastive learning and class-specific feature enhancement. This method improves detection accuracy by assigning adaptive weights to challenging samples and incorporating additional human, object, and interaction-specific features. Adaptive contrastive learning computes dynamic weights based on the similarity between each HOI instance and its label, allowing the model to focus more on challenging and long-tail samples. Class-specific feature enhancement improves the matcher by separately calculating losses for humans, objects, and interactions. Experimental results on the HICO-DET and SWIG-HOI datasets demonstrate the effectiveness of the proposed method in detecting seen and unseen interactions. The code is available at https://github.com/small-code-cat/ACL-CFE (Adaptive Contrastive Learning-Class-specific Feature Enhancement).