220 citations · 599 across the 51 of their papers we have counts for
8 papers · 1 filter
MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering
Fangzhi Xu, Qika Lin, Jun Liu +4
Textbook Question Answering (TQA) is a complex multimodal task to infer answers given large context descriptions and abundant diagrams. Compared with Visual Question Answering (VQA…
LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation
WeiFu Fu, CongChong Nie, Ting Sun +3
This report introduces the technical details of the team FuXi-Fresher for LVIS Challenge 2021. Our method focuses on the problem in following two aspects: the long-tail distributio…
Beam smoothing based on prism pair for multistep pulse compressor in PW lasers
Shuman Du, Xiong Shen, Wenhai Liang +2
Ultra-short ultra-intense laser provides unprecedented experimental tools and extreme physical conditions to explore frontier secrets of nature. Recently, multistep pulse compresso…
Ultrafast photonic rainbow with controllable orbital angular momentum
Shunlin Huang, Peng Wang, Xiong Shen +2
Increasing any degree of freedom of light beam may open a wide application area of this special light beam. Vortex beam with a dimension of orbital angular momentum (OAM) as a usef…
Learning Inner-Group Relations on Point Clouds
Haoxi Ran, Wei Zhuo, Jun Liu +1
The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation oper…
The Multi-Modal Video Reasoning and Analyzing Competition
Haoran Peng, He Huang, Li Xu +15
In this paper, we introduce the Multi-Modal Video Reasoning and Analyzing Competition (MMVRAC) workshop in conjunction with ICCV 2021. This competition is composed of four differen…
An adaptive variational model for multireference alignment with mixed noise
Cuicui Zhao, Jun Liu, Xinqi Gong
Multireference alignment (MRA) problem is to estimate an underlying signal from a large number of noisy circularly-shifted observations. The existing methods are always proposed un…
Noised Consistency Training for Text Summarization
Junnan Liu, Qianren Mao, Bang Liu +3
Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to…