27 citations · 127 across the 53 of their papers we have counts for
12 papers · 2 filters
Navigating Open Set Scenarios for Skeleton-based Action Recognition
Kunyu Peng, Cheng Yin, Junwei Zheng +7
In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones. Howeve…
CoBEV: Elevating Roadside 3D Object Detection with Depth and Height Complementarity
Hao Shi, Chengshan Pang, Jiaming Zhang +6
Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehi…
Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
Yiping Wei, Kunyu Peng, Alina Roitberg +6
Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a mult…
Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments
Ruiping Liu, Jiaming Zhang, Kunyu Peng +5
Grounded Situation Recognition (GSR) is capable of recognizing and interpreting visual scenes in a contextually intuitive way, yielding salient activities (verbs) and the involved…
Line Graphics Digitization: A Step Towards Full Automation
Omar Moured, Jiaming Zhang, Alina Roitberg +2
The digitization of documents allows for wider accessibility and reproducibility. While automatic digitization of document layout and text content has been a long-standing focus of…
OAFuser: Towards Omni-Aperture Fusion for Light Field Semantic Segmentation
Fei Teng, Jiaming Zhang, Kunyu Peng +3
Light field cameras are capable of capturing intricate angular and spatial details. This allows for acquiring complex light patterns and details from multiple angles, significantly…