A Study of Failure Modes in Two-Stage Human-Object Interaction Detection

• URL: http://arxiv.org/abs/2604.13448v1
• Date: Wed, 15 Apr 2026 04:01:23 GMT
• Title: A Study of Failure Modes in Two-Stage Human-Object Interaction Detection
• Abstract summary: We present a study to better understand the failure modes of two-stage HOI models.<n>We decompose HOI detection into multiple interpretable perspectives to study different types of failure patterns.
• Score: 49.37675694881915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human-object interaction (HOI) detection aims to detect interactions between humans and objects in images. While recent advances have improved performance on existing benchmarks, their evaluations mainly focus on overall prediction accuracy and provide limited insight into the underlying causes of model failures. In particular, modern models often struggle in complex scenes involving multiple people and rare interaction combinations. In this work, we present a study to better understand the failure modes of two-stage HOI models, which form the basis of many current HOI detection approaches. Rather than constructing a large-scale benchmark, we instead decompose HOI detection into multiple interpretable perspectives and analyze model behavior across these dimensions to study different types of failure patterns. We curate a subset of images from an existing HOI dataset organized by human-object-interaction configurations (e.g., multi-person interactions and object sharing), and analyze model behavior under these configurations to examine different failure modes. This design allows us to analyze how these HOI models behave under different scene compositions and why their predictions fail. Importantly, high overall benchmark performance does not necessarily reflect robust visual reasoning about human-object relationships. We hope that this study can provide useful insights into the limitations of HOI models and offer observations for future research in this area.

Related papers

• LVLM-Aided Alignment of Task-Specific Vision Models [49.96265491629163]
  Small task-specific vision models are crucial in high-stakes domains.<n>We introduce a novel and efficient method for aligning small task-specific vision models with human domain knowledge.<n>Our method demonstrates substantial improvement in aligning model behavior with human specifications.
  arXiv  Detail & Related papers  (2025-12-26T11:11:25Z)
• Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect [0.8793721044482612]
  We re-evaluate the bouba-kiki effect, where humans reliably associate pseudowords like bouba' with round shapes and kiki' with jagged ones.<n>We show that these model variants do not consistently exhibit the bouba-kiki effect.<n>Results contribute to the ongoing debate about the extent to which vision-and-language models truly understand cross-modal concepts.
  arXiv  Detail & Related papers  (2025-07-14T07:48:54Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• A Review of Human-Object Interaction Detection [10.20202786261744]
  Human-object interaction (HOI) detection plays a key role in high-level visual understanding.<n>This paper systematically summarizes and discusses the recent work in image-based HOI detection.
  arXiv  Detail & Related papers  (2024-08-20T08:32:39Z)
• A Reliable Framework for Human-in-the-Loop Anomaly Detection in Time Series [17.08674819906415]
  We introduce HILAD, a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI.<n>Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale.
  arXiv  Detail & Related papers  (2024-05-06T07:44:07Z)
• Diagnosing Human-object Interaction Detectors [42.283857276076596]
  We introduce a diagnosis toolbox to provide detailed quantitative break-down analysis of HOI detection models. We analyze eight state-of-the-art HOI detection models and provide valuable diagnosis insights to foster future research.
  arXiv  Detail & Related papers  (2023-08-16T17:39:15Z)
• Unified Visual Relationship Detection with Vision and Language Models [89.77838890788638]
  This work focuses on training a single visual relationship detector predicting over the union of label spaces from multiple datasets. We propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models. Empirical results on both human-object interaction detection and scene-graph generation demonstrate the competitive performance of our model.
  arXiv  Detail & Related papers  (2023-03-16T00:06:28Z)
• Are Neural Topic Models Broken? [81.15470302729638]
  We study the relationship between automated and human evaluation of topic models. We find that neural topic models fare worse in both respects compared to an established classical method.
  arXiv  Detail & Related papers  (2022-10-28T14:38:50Z)
• Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection [22.3445174577181]
  Human-Object Interaction (HOI) in images is an important step towards high-level visual comprehension. We propose a novel plug-and-play Object-wise Debiasing Memory (ODM) method for re-balancing the distribution of interactions under detected objects. Our method brings consistent and significant improvements over baselines, especially on rare interactions under each object.
  arXiv  Detail & Related papers  (2022-07-06T01:55:28Z)
• Suspected Object Matters: Rethinking Model's Prediction for One-stage Visual Grounding [93.82542533426766]
  We propose a Suspected Object Transformation mechanism (SOT) to encourage the target object selection among the suspected ones. SOT can be seamlessly integrated into existing CNN and Transformer-based one-stage visual grounders. Extensive experiments demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2022-03-10T06:41:07Z)
• DRG: Dual Relation Graph for Human-Object Interaction Detection [65.50707710054141]
  We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features. In this paper, we leverage an abstract spatial-semantic representation to describe each human-object pair and aggregate the contextual information of the scene via a dual relation graph.
  arXiv  Detail & Related papers  (2020-08-26T17:59:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.