Shapellm: Universal 3d object understanding for embodied interaction

Z Qi, R Dong, S Zhang, H Geng, C Han, Z Ge… - … on Computer Vision, 2025 - Springer
This paper presents ShapeLLM, the first 3D Multimodal Large Language Model (LLM)
designed for embodied interaction, exploring a universal 3D object understanding with 3D …

Tubetk: Adopting tubes to track multi-object in a one-step training model

B Pang, Y Li, Y Zhang, M Li… - Proceedings of the IEEE …, 2020 - openaccess.thecvf.com
Multi-object tracking is a fundamental vision problem that has been studied for a long time.
As deep learning brings excellent performances to object detection algorithms, Tracking by …

Transferable interactiveness knowledge for human-object interaction detection

YL Li, S Zhou, X Huang, L Xu, Z Ma… - Proceedings of the …, 2019 - openaccess.thecvf.com
Abstract Human-Object Interaction (HOI) Detection is an important problem to understand
how humans interact with objects. In this paper, we explore Interactiveness Knowledge …

Weakly supervised complementary parts models for fine-grained image classification from the bottom up

W Ge, X Lin, Y Yu - … of the IEEE/CVF Conference on …, 2019 - openaccess.thecvf.com
Given a training dataset composed of images and corresponding category labels, deep
convolutional neural networks show a strong ability in mining discriminative parts for image …

Pastanet: Toward human activity knowledge engine

YL Li, L Xu, X Liu, X Huang, Y Xu… - Proceedings of the …, 2020 - openaccess.thecvf.com
Existing image-based activity understanding methods mainly adopt direct mapping, ie from
image to activity concepts, which may encounter performance bottleneck since the huge …

Hoi analysis: Integrating and decomposing human-object interaction

YL Li, X Liu, X Wu, Y Li, C Lu - Advances in Neural …, 2020 - proceedings.neurips.cc
Abstract Human-Object Interaction (HOI) consists of human, object and implicit
interaction/verb. Different from previous methods that directly map pixels to HOI semantics …

Detailed 2d-3d joint representation for human-object interaction

YL Li, X Liu, H Lu, S Wang, J Liu… - Proceedings of the …, 2020 - openaccess.thecvf.com
Abstract Human-Object Interaction (HOI) detection lies at the core of action understanding.
Besides 2D information such as human/object appearance and locations, 3D pose is also …

Pixels to graphs by associative embedding

A Newell, J Deng - Advances in neural information …, 2017 - proceedings.neurips.cc
Graphs are a useful abstraction of image content. Not only can graphs represent details
about individual objects in a scene but they can capture the interactions between pairs of …

Mining cross-person cues for body-part interactiveness learning in hoi detection

X Wu, YL Li, X Liu, J Zhang, Y Wu, C Lu - European Conference on …, 2022 - Springer
Abstract Human-Object Interaction (HOI) detection plays a crucial role in activity
understanding. Though significant progress has been made, interactiveness learning …

Interactiveness field in human-object interactions

X Liu, YL Li, X Wu, YW Tai, C Lu… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Human-Object Interaction (HOI) detection plays a core role in activity
understanding. Though recent two/one-stage methods have achieved impressive results, as …