Alert button
Picture for Bo Xiong

Bo Xiong

Alert button

Improved Multiscale Vision Transformers for Classification and Detection

Dec 02, 2021
Yanghao Li, Chao-Yuan Wu, Haoqi Fan, Karttikeya Mangalam, Bo Xiong, Jitendra Malik, Christoph Feichtenhofer

Figure 1 for Improved Multiscale Vision Transformers for Classification and Detection
Figure 2 for Improved Multiscale Vision Transformers for Classification and Detection
Figure 3 for Improved Multiscale Vision Transformers for Classification and Detection
Figure 4 for Improved Multiscale Vision Transformers for Classification and Detection
Viaarxiv icon

PyTorchVideo: A Deep Learning Library for Video Understanding

Nov 18, 2021
Haoqi Fan, Tullie Murrell, Heng Wang, Kalyan Vasudev Alwala, Yanghao Li, Yilei Li, Bo Xiong, Nikhila Ravi, Meng Li, Haichuan Yang, Jitendra Malik, Ross Girshick, Matt Feiszli, Aaron Adcock, Wan-Yen Lo, Christoph Feichtenhofer

Figure 1 for PyTorchVideo: A Deep Learning Library for Video Understanding
Figure 2 for PyTorchVideo: A Deep Learning Library for Video Understanding
Figure 3 for PyTorchVideo: A Deep Learning Library for Video Understanding
Viaarxiv icon

Semi-Riemannian Graph Convolutional Networks

Jun 06, 2021
Bo Xiong, Shichao Zhu, Nico Potyka, Shirui Pan, Chuan Zhou, Steffen Staab

Figure 1 for Semi-Riemannian Graph Convolutional Networks
Figure 2 for Semi-Riemannian Graph Convolutional Networks
Figure 3 for Semi-Riemannian Graph Convolutional Networks
Figure 4 for Semi-Riemannian Graph Convolutional Networks
Viaarxiv icon

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

Apr 29, 2021
Christoph Feichtenhofer, Haoqi Fan, Bo Xiong, Ross Girshick, Kaiming He

Figure 1 for A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Figure 2 for A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Figure 3 for A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Figure 4 for A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
Viaarxiv icon

Multiscale Vision Transformers

Apr 22, 2021
Haoqi Fan, Bo Xiong, Karttikeya Mangalam, Yanghao Li, Zhicheng Yan, Jitendra Malik, Christoph Feichtenhofer

Figure 1 for Multiscale Vision Transformers
Figure 2 for Multiscale Vision Transformers
Figure 3 for Multiscale Vision Transformers
Figure 4 for Multiscale Vision Transformers
Viaarxiv icon

Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

Apr 16, 2021
Yanghao Li, Tushar Nagarajan, Bo Xiong, Kristen Grauman

Figure 1 for Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
Figure 2 for Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
Figure 3 for Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
Figure 4 for Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos
Viaarxiv icon

Multiview Pseudo-Labeling for Semi-supervised Learning from Video

Apr 01, 2021
Bo Xiong, Haoqi Fan, Kristen Grauman, Christoph Feichtenhofer

Figure 1 for Multiview Pseudo-Labeling for Semi-supervised Learning from Video
Figure 2 for Multiview Pseudo-Labeling for Semi-supervised Learning from Video
Figure 3 for Multiview Pseudo-Labeling for Semi-supervised Learning from Video
Figure 4 for Multiview Pseudo-Labeling for Semi-supervised Learning from Video
Viaarxiv icon

MOFA: Modular Factorial Design for Hyperparameter Optimization

Nov 18, 2020
Bo Xiong, Yimin Huang, Steffen Staab, Zhenguo Li

Figure 1 for MOFA: Modular Factorial Design for Hyperparameter Optimization
Figure 2 for MOFA: Modular Factorial Design for Hyperparameter Optimization
Figure 3 for MOFA: Modular Factorial Design for Hyperparameter Optimization
Figure 4 for MOFA: Modular Factorial Design for Hyperparameter Optimization
Viaarxiv icon

Less is More: Learning Highlight Detection from Video Duration

Mar 03, 2019
Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman

Figure 1 for Less is More: Learning Highlight Detection from Video Duration
Figure 2 for Less is More: Learning Highlight Detection from Video Duration
Figure 3 for Less is More: Learning Highlight Detection from Video Duration
Figure 4 for Less is More: Learning Highlight Detection from Video Duration
Viaarxiv icon

Snap Angle Prediction for 360$^{\circ}$ Panoramas

Aug 12, 2018
Bo Xiong, Kristen Grauman

Figure 1 for Snap Angle Prediction for 360$^{\circ}$ Panoramas
Figure 2 for Snap Angle Prediction for 360$^{\circ}$ Panoramas
Figure 3 for Snap Angle Prediction for 360$^{\circ}$ Panoramas
Figure 4 for Snap Angle Prediction for 360$^{\circ}$ Panoramas
Viaarxiv icon