Lele Cao

Pay Self-Attention to Audio-Visual Navigation

Oct 05, 2022
Yinfeng Yu, Lele Cao, Fuchun Sun, Xiaohong Liu, Liejun Wang

Figure 2 for Pay Self-Attention to Audio-Visual Navigation

Figure 3 for Pay Self-Attention to Audio-Visual Navigation

Figure 4 for Pay Self-Attention to Audio-Visual Navigation

* Main paper (10 pages and 7 figures) and appendix (21 figures and 4 tables). Accepted for publication by BMVC 2022. For data and code, see https://yyf17.github.io/FSAAVN/index.html

Access Paper or Ask Questions

Bridged Transformer for Vision and Point Cloud 3D Object Detection

Oct 04, 2022
Yikai Wang, TengQi Ye, Lele Cao, Wenbing Huang, Fuchun Sun, Fengxiang He, Dacheng Tao

Figure 2 for Bridged Transformer for Vision and Point Cloud 3D Object Detection

Figure 3 for Bridged Transformer for Vision and Point Cloud 3D Object Detection

* CVPR 2022

Access Paper or Ask Questions

Simulation-Informed Revenue Extrapolation with Confidence Estimate for Scaleup Companies Using Scarce Time-Series Data

Aug 23, 2022
Lele Cao, Sonja Horn, Vilhelm von Ehrenheim, Richard Anselmo Stahl, Henrik Landgren

Figure 2 for Simulation-Informed Revenue Extrapolation with Confidence Estimate for Scaleup Companies Using Scarce Time-Series Data

Figure 3 for Simulation-Informed Revenue Extrapolation with Confidence Estimate for Scaleup Companies Using Scarce Time-Series Data

Figure 4 for Simulation-Informed Revenue Extrapolation with Confidence Estimate for Scaleup Companies Using Scarce Time-Series Data

* Accepted by CIKM 2022 as full applied research paper (12 pages and 6 figures). For source code and datasets, see https://github.com/EQTPartners/sire

Access Paper or Ask Questions

Multimodal Token Fusion for Vision Transformers

Apr 19, 2022
Yikai Wang, Xinghao Chen, Lele Cao, Wenbing Huang, Fuchun Sun, Yunhe Wang

Figure 2 for Multimodal Token Fusion for Vision Transformers

Figure 3 for Multimodal Token Fusion for Vision Transformers

Figure 4 for Multimodal Token Fusion for Vision Transformers

* CVPR 2022

Access Paper or Ask Questions

PAUSE: Positive and Annealed Unlabeled Sentence Embedding

Sep 07, 2021
Lele Cao, Emil Larsson, Vilhelm von Ehrenheim, Dhiana Deva Cavalcanti Rocha, Anna Martin, Sonja Horn

Figure 2 for PAUSE: Positive and Annealed Unlabeled Sentence Embedding

Figure 3 for PAUSE: Positive and Annealed Unlabeled Sentence Embedding

Figure 4 for PAUSE: Positive and Annealed Unlabeled Sentence Embedding

* Accepted by EMNLP 2021 main conference as long paper (12 pages and 2 figures). For source code, see https://github.com/EQTPartners/pause

Access Paper or Ask Questions

Simple, Scalable, and Stable Variational Deep Clustering

May 21, 2020
Lele Cao, Sahar Asadi, Wenfei Zhu, Christian Schmidli, Michael Sjöberg

Figure 2 for Simple, Scalable, and Stable Variational Deep Clustering

Figure 3 for Simple, Scalable, and Stable Variational Deep Clustering

Figure 4 for Simple, Scalable, and Stable Variational Deep Clustering

* 17 pages, 5 figures, source code: https://github.com/king/s3vdc

Access Paper or Ask Questions

Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

Feb 27, 2017
Wenbing Huang, Fuchun Sun, Lele Cao, Mehrtash Harandi

Figure 2 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

Figure 3 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

Figure 4 for Analyzing Linear Dynamical Systems: From Modeling to Coding and Learning

* 38 pages

Access Paper or Ask Questions