452 citations · 715 across the 7 of their papers we have counts for
7 papers
Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling
Xin Ma, Chang Liu, Chunyu Xie +3
Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency. We believe the insufficient utilization of tra…
TripleRE: Knowledge Graph Embeddings via Tripled Relation Vectors
Long Yu, Zhicong Luo, Huanyong Liu +3
Translation-based knowledge graph embedding has been one of the most important branches for knowledge representation learning since TransE came out. Although many translation-based…
StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
Hongzhu Li, Xiangrui Gao, Linhui Feng +2
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector, ignoring the rich information contained in the neighborhood.…
WaBERT: A Low-resource End-to-end Model for Spoken Language Understanding and Speech-to-BERT Alignment
Lin Yao, Jianfei Song, Ruizhuo Xu +3
Historically lower-level tasks such as automatic speech recognition (ASR) and speaker identification are the main focus in the speech field. Interest has been growing in higher-lev…
The 2nd Anti-UAV Workshop & Challenge: Methods and Results
Jian Zhao, Gang Wang, Jianan Li +9
The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking. The Anti-UAV dataset used for the Anti-U…
DenseBox: Unifying Landmark Localization with End to End Object Detection
Lichao Huang, Yi Yang, Yafeng Deng +1
How can a single fully convolutional neural network (FCN) perform on object detection? We introduce DenseBox, a unified end-to-end FCN framework that directly predicts bounding box…
Targeting Ultimate Accuracy: Face Recognition via Deep Embedding
Jingtuo Liu, Yafeng Deng, Tao Bai +2
Face Recognition has been studied for many decades. As opposed to traditional hand-crafted features such as LBP and HOG, much more sophisticated features can be learned automatical…