Recent News

  • [05/12/2022] One paper (Entity Segmentation) gets accepted to PAMI.
  • [19/11/2022] One paper gets accepted to AAAI 2023.
  • [24/10/2022] One paper (Differential Privacy in Learning Language Models) gets accepted to BigData 2022.
  • [10/10/2022] One paper gets accepted to WACV 2023.
  • [06/10/2022] The third Doc-series paper (SelfDoc->UniDoc->MGDoc) gets accepted to EMNLP-2022.
  • [14/09/2022] One paper (OOD) gets accepted to NeurIPS-2022.
  • [03/07/2022] Three papers get accepted to ECCV 2022.
  • [14/06/2022] One paper gets accepted to Interspeech 2022.
  • [07/04/2022] One paper gets accepted to NAACL 2022.
  • [01/03/2022] Three papers get accepted to CVPR 2022.
  • [24/02/2022] One paper (Adaptive Axis Attentions) gets accepted to ACL 2022 Findings.
  • [13/01/2022] One paper gets accepted to WWW 2022.
  • [01/12/2021] Two papers get accepted to AAAI-2022.
  • [28/09/2021] The second Doc-series paper (SelfDoc->UniDoc) gets accepted to NeurIPS-2021.
  • [10/03/2021] One paper gets accepted to NAACL-2021.
  • [28/02/2021] Three papers (SelfDoc is our first Doc-series paper) get accepted to CVPR-2021.
  • More >>

Research Topics

Attention Convolutional Neural Networks Cross-Modal Retrieval Differential Privacy Document Understanding Entity Segmentation Federated Learning GAN Image Captioning Image Generation Multilingual Object Detection Out-of-Distribution Pretraining Reinforcement Learning Scene Graph Generation Self-Supervised Learning Unsupervised Learning Video Captioning Vision-Language

Publications

Quickly discover relevant content by filtering publications.

We introduce a new image segmentation task, called Entity Segmentation (ES), which aims to segment all visual entities (objects and …
Code TPAMI

Professional document editing tools require a certain level of expertise to perform complex edit operations. To make editing tools …
AAAI 2023

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection …
BigData 2022

Digital documents often contain images and scanned text. Parsing such visually-rich documents is a core task for automating document …
PDF WACV 2023

Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine …
PDF EMNLP 2022

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems deployed in the open world. The vast majority of …
NeurIPS 2022

We propose a new task of synthesizing speech directly from semi-structured documents where the extracted text tokens from OCR systems …
Interspeech 2022

We introduce DocTime - a novel temporal dependency graph (TDG) parser that takes as input a text document and produces a temporal …
PDF NAACL 2022

This work presents one of the first comprehensive studies on different sparse attention patterns in Transformer models. We first …
ACL 2022

Multilingual natural language understanding, which aims to comprehend multilingual documents, is an important task. Existing efforts …
WWW 2022
See all publications