LEMON: Learning 3D Human-Object Interaction Relation from 2D Images

Y Yang, W Zhai, H Luo, Y Cao… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Learning 3D human-object interaction relation is pivotal to embodied AI and interaction
modeling. Most existing methods approach the goal by learning to predict isolated …

Grounded affordance from exocentric view

H Luo, W Zhai, J Zhang, Y Cao, D Tao - International Journal of Computer …, 2024 - Springer
Affordance grounding aims to locate objects'“action possibilities” regions, an essential step
toward embodied intelligence. Due to the diversity of interactive affordance, ie, the …

Mambapupil: Bidirectional selective recurrent model for event-based eye tracking

Z Wang, Z Wan, H Han, B Liao, Y Wu… - Proceedings of the …, 2024 - openaccess.thecvf.com
Event-based eye tracking has shown great promise with the high temporal resolution and
low redundancy provided by the event camera. However the diversity and abruptness of eye …

Tackling Event-Based Lip-Reading by Exploring Multigrained Spatiotemporal Clues

G Tan, Z Wan, Y Wang, Y Cao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Automatic lip-reading (ALR) is the task of recognizing words based on visual information
obtained from the speaker's lip movements. In this study, we introduce event cameras, a …

Hierarchical home action understanding with implicit and explicit prior knowledge

Y Zhou, G Tan, C Gou - ICASSP 2024-2024 IEEE International …, 2024 - ieeexplore.ieee.org
Existing investigations on action understanding have made noteworthy advancements by
treating activities as holistic events occurring in videos. However, these investigations have …

Branches mutual promotion for end-to-end weakly supervised semantic segmentation

L Zhu, X Zhang, H He, Q Chen, S Li… - … on Neural Networks …, 2024 - ieeexplore.ieee.org
End-to-end weakly supervised semantic segmentation (E2E-WSSS) aims at optimizing a
segmentation model in a single-stage training process based on only image annotations …

Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation

Y Du, Z Fu, Q Liu - IEEE Transactions on Image Processing, 2024 - ieeexplore.ieee.org
Recent attention has been devoted to the pursuit of learning semantic segmentation models
exclusively from image tags, a paradigm known as image-level Weakly Supervised …

Adaptive Zone Learning for Weakly Supervised Object Localization

Z Chen, S Wang, L Cao, Y Shen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Weakly supervised object localization (WSOL) stands as a pivotal endeavor within the realm
of computer vision, entailing the location of objects utilizing merely image-level labels …

Foreground–background separation transformer for weakly supervised surface defect detection

X Jiang, J Feng, F Yan, Y Lu, Q Fa, W Zhang… - Journal of Intelligent …, 2024 - Springer
In industrial scenarios, weakly supervised pixel-level defect detection methods leverage
image-level labels for training, significantly reducing the effort required for manual …

PCSformer: Pair-wise Cross-scale Sub-prototypes mining with CNN-transformers for weakly supervised semantic segmentation

C Liu, Y Shen, Q Xiao, G Li - Neurocomputing, 2024 - Elsevier
Generating initial seeds is an important step in weakly supervised semantic segmentation
(WSSS). Our approach concentrates on generating and refining initial seeds. The …