50 citations · 97 across the 7 of their papers we have counts for
7 papers
DiT: Self-supervised Pre-training for Document Image Transformer
Junlong Li, Yiheng Xu, Tengchao Lv +3
Image Transformer has recently achieved significant progress for natural image understanding, either using supervised (ViT, DeiT, etc.) or self-supervised (BEiT, MAE, etc.) pre-tra…
LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding
Yiheng Xu, Tengchao Lv, Lei Cui +5
Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential f…
TAP: Text-Aware Pre-training for Text-VQA and Text-Caption
Zhengyuan Yang, Yijuan Lu, Jianfeng Wang +6
In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answ…
Multimodal active speaker detection and virtual cinematography for video conferencing
Ross Cutler, Ramin Mehran, Sam Johnson +4
Active speaker detection (ASD) and virtual cinematography (VC) can significantly improve the remote user experience of a video conference by automatically panning, tilting and zoom…
RePr: Improved Training of Convolutional Filters
Aaditya Prakash, James Storer, Dinei Florencio +1
A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the net…
Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution
Emad Barsoum, Cha Zhang, Cristian Canton Ferrer +1
Crowd sourcing has become a widely adopted scheme to collect ground truth labels. However, it is a well-known problem that these labels can be very noisy. In this paper, we demonst…
Precision Enhancement of 3D Surfaces from Multiple Compressed Depth Maps
Pengfei Wan, Gene Cheung, Philip A. Chou +3
In texture-plus-depth representation of a 3D scene, depth maps from different camera viewpoints are typically lossily compressed via the classical transform coding / coefficient qu…