挖掘以实例为中心的视觉语言上下文用于人-物交互检测
Mining Instance-Centric Vision-Language Contexts for Human-Object Interaction Detection
把 VLM 特征按实例内、实例间、全局三种粒度拆解并渐进融合到检测器实例特征上，这套「实例中心上下文挖掘」思路可直接迁移到任何需要细粒度关系推理的视觉任务（如场景图生成、指代理解）。
原文依据 we propose the Instance-centric Context Mining Network (InCoM-Net)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人-物交互（HOI）检测旨在从单张图像中定位人-物对并对其交互进行分类，该任务要求强大的视觉理解能力与细致的上下文推理能力。近期方法借助视觉语言模型（VLM）引入语义先验，显著提升了 HOI 检测性能。然而，现有方法往往未能充分利用分布在整个场景中的多样化上下文线索。为克服这些局限，我们提出以实例为中心的上下文挖掘网络（InCoM-Net）——一个新颖的框架，它将从 VLM 中提取的丰富语义知识与目标检测器产生的实例特定特征有效融合。该设计不仅对每个检测到的实例内部的关系建模，还对实例之间及其周围场景上下文的关系建模，从而实现更深层的交互推理。InCoM-Net 包含两个核心组件：以实例为中心的上下文精炼（ICR），它分别从 VLM 导出的特征中提取实例内、实例间与全局上下文线索；以及渐进式上下文聚合（ProCA），它迭代地将这些多上下文特征与实例级检测器特征融合，以支撑高层次的 HOI 推理。在 HICO-DET 与 V-COCO 基准上的大量实验表明，InCoM-Net 取得了最优性能，超越了以往的 HOI 检测方法。代码已发布于 https://github.com/nowuss/InCoM-Net。
英文原文摘要 1499 字符
Human-Object Interaction (HOI) detection aims to localize human-object pairs and classify their interactions from a single image, a task that demands strong visual understanding and nuanced contextual reasoning. Recent approaches have leveraged Vision-Language Models (VLMs) to introduce semantic priors, significantly improving HOI detection performance. However, existing methods often fail to fully capitalize on the diverse contextual cues distributed across the entire scene. To overcome these limitations, we propose the Instance-centric Context Mining Network (InCoM-Net)--a novel framework that effectively integrates rich semantic knowledge extracted from VLMs with instance-specific features produced by an object detector. This design enables deeper interaction reasoning by modeling relationships not only within each detected instance but also across instances and their surrounding scene context. InCoM-Net comprises two core components: Instance-centric Context Refinement (ICR), which separately extracts intra-instance, inter-instance, and global contextual cues from VLM-derived features, and Progressive Context Aggregation (ProCA), which iteratively fuses these multi-context features with instance-level detector features to support high-level HOI reasoning. Extensive experiments on the HICO-DET and V-COCO benchmarks show that InCoM-Net achieves state-of-the-art performance, surpassing previous HOI detection methods. Code is available at https://github.com/nowuss/InCoM-Net.