Papers
arxiv:2603.27500

Streamlined Open-Vocabulary Human-Object Interaction Detection

Published on Mar 29
Authors:
,
,

Abstract

SL-HOI presents a streamlined open-vocabulary human-object interaction detection framework using DINOv3's complementary components for localization and classification while enabling efficient cross-attention through shared vision head processing.

AI-generated summary

Open-vocabulary human-object interaction (HOI) detection aims to localize and recognize all human-object interactions in an image, including those unseen during training. Existing approaches usually rely on the collaboration between a conventional HOI detector and a Vision-Language Model (VLM) to recognize unseen HOI categories. However, feature fusion in this paradigm is challenging due to significant gaps in cross-model representations. To address this issue, we introduce SL-HOI, a StreamLined open-vocabulary HOI detection framework based solely on the powerful DINOv3 model. Our design leverages the complementary strengths of DINOv3's components: its backbone for fine-grained localization and its text-aligned vision head for open-vocabulary interaction classification. Moreover, to facilitate smooth cross-attention between the interaction queries and the vision head's output, we propose first feeding both the interaction queries and the backbone image tokens into the vision head, effectively bridging their representation gaps. All DINOv3 parameters in our approach are frozen, with only a small number of learnable parameters added, allowing a fast adaptation to the HOI detection task. Extensive experiments show that SL-HOI achieves state-of-the-art performance on both the SWiG-HOI and HICO-DET benchmarks, demonstrating the effectiveness of our streamlined model architecture. Code is available at https://github.com/MPI-Lab/SL-HOI.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2603.27500
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2603.27500 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.27500 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.