activity
20172023
most citedThin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos

13 citations · 40 across the 15 of their papers we have counts for

collaborators
Showing 2021Show all

9 papers · 1 filter

cs.CR2021

Safe Distillation Box

Jingwen Ye, Yining Mao, Jie Song +3

Knowledge distillation (KD) has recently emerged as a powerful strategy to transfer knowledge from a pre-trained teacher model to a lightweight student, and has demonstrated its un…

cs.CV2021★ 1 cited

Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training

Haofei Zhang, Jiarui Duan, Mengqi Xue +3

Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV). W…

cs.CV2021

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions

Sammy Christen, Muhammed Kocabas, Emre Aksan +3

We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose.…

cs.CV2021

A Survey of Deep Learning for Low-Shot Object Detection

Qihan Huang, Haofei Zhang, Mengqi Xue +2

Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the sce…

cs.CV2021

Human Performance Capture from Monocular Video in the Wild

Chen Guo, Xu Chen, Jie Song +1

Capturing the dynamically deforming 3D shape of clothed human is essential for numerous applications, including VR/AR, autonomous driving, and human-computer interaction. Existing…

cs.CV2021

Render In-between: Motion Guided Video Synthesis for Action Interpolation

Hsuan-I Ho, Xu Chen, Jie Song +1

Upsampling videos of human activity is an interesting yet challenging task with many potential applications ranging from gaming to entertainment and sports broadcasting. The main d…