7 citations
- Nanyang Technological UniversitySG5 papers
- Tsinghua UniversityCN4 papers
- Chinese Academy of SciencesCN2 papers
- University of Chinese Academy of SciencesCN2 papers
- Academy of Military Medical SciencesCN1 paper
- Beijing Academy of Artificial IntelligenceCN1 paper
- Beijing Institute for General Artificial IntelligenceCN1 paper
- Beijing Institute of Mathematical Sciences and Applications1 paper
- Beijing Normal UniversityCN1 paper
- Carnegie Mellon UniversityUS1 paper
- CentraleSupélecFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
5 papers · 1 filter
IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning
Jiapeng Li, Ping Wei, Wenjuan Han +2
Video understanding requires intelligent agents to transcend mere recognition of visual facts and comprehend the underlying intents behind human actions (often termed the "dark mat…
HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
Runzhong Zhang, Suchen Wang, Yueqi Duan +3
In this paper, we propose an HOI-aware adaptive network named AdaAct for weakly-supervised action segmentation. Most existing methods learn a fixed network to predict the action of…
High-Fidelity 3D Facial Avatar Synthesis with Controllable Fine-Grained Expressions
Yikang He, Jichao Zhang, Wei Wang +2
Facial expression editing methods can be mainly categorized into two types based on their architectures: 2D-based and 3D-based methods. The former lacks 3D face modeling capabiliti…
Robust Image Stitching with Optimal Plane
Lang Nie, Yuan Mei, Kang Liao +3
We present \textit{RopStitch}, an unsupervised deep image stitching framework with both robustness and naturalness. To ensure the robustness of \textit{RopStitch}, we propose to in…
DGFusion: Dual-guided Fusion for Robust Multi-Modal 3D Object Detection
Feiyang Jia, Caiyan Jia, Ailin Liu +6
As a critical task in autonomous driving perception systems, 3D object detection is used to identify and track key objects, such as vehicles and pedestrians. However, detecting dis…