24 citations · 92 across the 36 of their papers we have counts for
11 papers · 1 filter
Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation
Jia-Fong Yeh, Chi-Ming Chung, Hung-Ting Su +2
In few-shot imitation learning (FSIL), using behavioral cloning (BC) to solve unseen tasks with few expert demonstrations becomes a popular research direction. The following capabi…
Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data
Guan-Rong Lu, Yueh-Cheng Liu, Tung-I Chen +3
Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly…
Multivariate and Propagation Graph Attention Network for Spatial-Temporal Prediction with Outdoor Cellular Traffic
Chung-Yi Lin, Hung-Ting Su, Shen-Lung Tung +1
Spatial-temporal prediction is a critical problem for intelligent transportation, which is helpful for tasks such as traffic control and accident prevention. Previous studies rely…
TrUMAn: Trope Understanding in Movies and Animations
Hung-Ting Su, Po-Wei Shen, Bing-Chen Tsai +3
Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boos…
ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
Tsung-Han Wu, Yueh-Cheng Liu, Yu-Kai Huang +4
Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale point-by-point manual annotations is still a significant challenge. To r…
OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Ke-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su +4
To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded…
Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining
Yueh-Cheng Liu, Yu-Kai Huang, Hung-Yueh Chiang +5
Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets. In this paper, we present a novel 3D pretraining method by leveraging 2D netw…
: Learnable Sparse Signal Superdensity for Guided Depth Estimation
Yu-Kai Huang, Yueh-Cheng Liu, Tsung-Han Wu +5
Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been le…
Dual-Awareness Attention for Few-Shot Object Detection
Tung-I Chen, Yueh-Cheng Liu, Hung-Ting Su +5
While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems. Existin…
End-to-End Video Question-Answer Generation with Generator-Pretester Network
Hung-Ting Su, Chen-Hsi Chang, Po-Wei Shen +5
We study a novel task, Video Question-Answer Generation (VQAG), for challenging Video Question Answering (Video QA) task in multimedia. Due to expensive data annotation costs, many…
Situation and Behavior Understanding by Trope Detection on Films
Chen-Hsi Chang, Hung-Ting Su, Jui-heng Hsu +7
The human ability of deep cognitive skills are crucial for the development of various real-world applications that process diverse and abundant user generated input. While recent p…