activity
20122022
most citedRecurrent Convolutional Strategies for Face Manipulation Detection in Videos

337 citations · 493 across the 14 of their papers we have counts for

collaborators

33 papers

cs.CL20223 cited

Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction

Kuan-Hao Huang, I-Hung Hsu, Premkumar Natarajan +2

We present a study on leveraging multilingual pre-trained generative language models for zero-shot cross-lingual event argument extraction (EAE). By formulating EAE as a language g…

cs.CV20213 cited

SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation

Jiaxin Cheng, Soumyaroop Nandi, Prem Natarajan +1

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic…

cs.CL202112 cited

Societal Biases in Language Generation: Progress and Challenges

Emily Sheng, Kai-Wei Chang, Premkumar Natarajan +1

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to comm…

cs.CV20214 cited

Style-Aware Normalized Loss for Improving Arbitrary Style Transfer

Jiaxin Cheng, Ayush Jaiswal, Yue Wu +2

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widel…

cs.CL20212 cited

Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations

Ying Lin, Han Wang, Jiangning Chen +5

The growing popularity of Virtual Assistants poses new challenges for Entity Resolution, the task of linking mentions in text to their referent entities in a knowledge base. Specif…

cs.CV2020

Class-agnostic Object Detection

Ayush Jaiswal, Yue Wu, Pradeep Natarajan +1

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and…