Recent News

More >>

  • [14/09/2022] One paper 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 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] One paper gets accepted to NeurIPS-2021.
  • [10/03/2021] One paper gets accepted to NAACL-2021.
  • [28/02/2021] Three papers get accepted to CVPR-2021.

Publications

Quickly discover relevant content by filtering publications.

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

Using natural-language feedback to guide image generation and manipulation can greatly lower the required efforts and skills. This …
AAAI 2022

Most recent image captioning works are conducted in English as the majority of image-caption datasets are in English. However, there …
PDF AAAI 2022

Document intelligence automates the extraction of information from documents and supports many business applications. Recent …
NeurIPS 2021

Recent studies indicate that NLU models are prone to rely on shortcut features for prediction. As a result, these models could …
NAACL 2021

Recent study on detecting facial action units (AU) has utilized auxiliary information (i.e., facial landmarks, relationship among AUs …
CVPR 2021

In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. …
CVPR 2021

We propose SelfDoc, a task-agnostic pre-training framework for document image analysis. Because documents are multimodal displays and …
CVPR 2021

Structured representations of images according to visual relationships are beneficial for many vision and vision-language applications. …
NeurIPS 2020

The explosion of video data on the internet requires effective and efficient technology to generate captions automatically for people …
Neurocomputing

The prevalent approach to the image captioning is an encoder-decoder framework, where the combination of convolutional neural networks …
ECCV 2020

Mobile energy storage systems (MESSs) provide mobility and flexibility to enhance distribution system resilience. The paper proposes a …
Preprint IEEE PES GM 2020

We, as humans, can easily use our vision and language capabilities to accomplish a wide variety of tasks that combine the image and the …
PDF

With the rapid growth of video data and the increasing demands of various applications such as intelligent video search and assistance …
ACMMM 2019

Most of the existing deep learning based image captioning methods are fully-supervised models, which require large-scale paired …
PDF Code ICCV 2019

Scene graph generation has received growing attention with advancement image understanding tasks such as object detection, attributes …
CVPR 2019
See all publications

Miscellaneous

Conference Reviewer

  • Senior Program Committee of IJCAI.
  • Program Committee of AAAI, IJCAI, NNACL.
  • ICLR, NeruIPS, CVPR, ECCV, ICCV, AAAI, etc.

Journal Reviewer

  • T-PAMI, IJCV, JMLR, T-IP, T-MM, T-NNLS, T-CSVT, T-SMC-B, PR, PRL, etc.