Search Results for author: Prem Natarajan

Found 39 papers, 18 papers with code

Lifelong Event Detection with Knowledge Transfer

1 code implementation EMNLP 2021 Pengfei Yu, Heng Ji, Prem Natarajan

We focus on lifelong event detection as an exemplar case and propose a new problem formulation that is also generalizable to other IE tasks.

Event Detection Transfer Learning

TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization

no code implementations10 Aug 2023 Soumyaroop Nandi, Prem Natarajan, Wael Abd-Almageed

The evaluation datasets and metrics for image manipulation detection and localization (IMDL) research have been standardized.

Image Enhancement Image Manipulation +1

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model

1 code implementation26 May 2023 I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan, Nanyun Peng

However, existing generation-based EAE models mostly focus on problem re-formulation and prompt design, without incorporating additional information that has been shown to be effective for classification-based models, such as the abstract meaning representation (AMR) of the input passages.

Abstract Meaning Representation Event Argument Extraction

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

1 code implementation2 Aug 2022 Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andy Rosenbaum, Anna Rumshisky, Chandana Satya Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur, Prem Natarajan

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various tasks.

Causal Language Modeling Common Sense Reasoning +9

MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images

no code implementations19 Jul 2022 Ekraam Sabir, Soumyaroop Nandi, Wael AbdAlmageed, Prem Natarajan

Manipulation of biomedical images to misrepresent experimental results has plagued the biomedical community for a while.

A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering

no code implementations14 Jan 2022 Feng Gao, Qing Ping, Govind Thattai, Aishwarya Reganti, Ying Nian Wu, Prem Natarajan

Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information to answer the question.

Generative Question Answering Passage Retrieval +2

Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering

no code implementations CVPR 2022 Feng Gao, Qing Ping, Govind Thattai, Aishwarya Reganti, Ying Nian Wu, Prem Natarajan

Most previous works address the problem by first fusing the image and question in the multi-modal space, which is inflexible for further fusion with a vast amount of external knowledge.

Generative Question Answering Passage Retrieval +2

BioFors: A Large Biomedical Image Forensics Dataset

1 code implementation ICCV 2021 Ekraam Sabir, Soumyaroop Nandi, Wael AbdAlmageed, Prem Natarajan

Our results and analysis show that existing algorithms developed on common computer vision datasets are not robust when applied to biomedical images, validating that more research is required to address the unique challenges of biomedical image forensics.

Benchmarking Image Forensics +1

DEGREE: A Data-Efficient Generation-Based Event Extraction Model

2 code implementations NAACL 2022 I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang, Nanyun Peng

Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern.

Event Extraction Sentence +2

``Nice Try, Kiddo'': Investigating Ad Hominems in Dialogue Responses

no code implementations NAACL 2021 Emily Sheng, Kai-Wei Chang, Prem Natarajan, Nanyun Peng

Ad hominem attacks are those that target some feature of a person{'}s character instead of the position the person is maintaining.

Abusive Language

Style-Aware Normalized Loss for Improving Arbitrary Style Transfer

1 code implementation CVPR 2021 Jiaxin Cheng, Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Prem Natarajan

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST).

Style Transfer

MEG: Multi-Evidence GNN for Multimodal Semantic Forensics

no code implementations23 Nov 2020 Ekraam Sabir, Ayush Jaiswal, Wael AbdAlmageed, Prem Natarajan

The problem setup requires algorithms to perform multimodal semantic forensics to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences.

Graph Neural Network

Recurrent Convolutional Strategies for Face Manipulation Detection in Videos

1 code implementation2 May 2019 Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael Abd-Almageed, Iacopo Masi, Prem Natarajan

The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods.

Face Swapping Misinformation

Image-to-GPS Verification Through A Bottom-Up Pattern Matching Network

no code implementations18 Nov 2018 Jiaxin Cheng, Yue Wu, Wael Abd-Almageed, Prem Natarajan

The image-to-GPS verification problem asks whether a given image is taken at a claimed GPS location.

Image-To-Gps Verification

A Byte-sized Approach to Named Entity Recognition

1 code implementation22 Sep 2018 Emily Sheng, Prem Natarajan

In biomedical literature, it is common for entity boundaries to not align with word boundaries.

named-entity-recognition Named Entity Recognition +1

BusterNet: Detecting Copy-Move Image Forgery with Source/Target Localization

1 code implementation ECCV 2018 Yue Wu, Wael Abd-Almageed, Prem Natarajan

We introduce a novel deep neural architecture for image copy-move forgery detection (CMFD), code-named BusterNet.

Deep Multimodal Image-Repurposing Detection

1 code implementation20 Aug 2018 Ekraam Sabir, Wael Abd-Almageed, Yue Wu, Prem Natarajan

Nefarious actors on social media and other platforms often spread rumors and falsehoods through images whose metadata (e. g., captions) have been modified to provide visual substantiation of the rumor/falsehood.

Learn to Combine Modalities in Multimodal Deep Learning

1 code implementation29 May 2018 Kuan Liu, Yanen Li, Ning Xu, Prem Natarajan

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches.

Multimodal Deep Learning

A Sequential Embedding Approach for Item Recommendation with Heterogeneous Attributes

no code implementations28 May 2018 Kuan Liu, Xing Shi, Prem Natarajan

Our ablation experiments demonstrate the effectiveness of the two components to address heterogeneous attribute challenges including variable lengths and attribute sparseness.

Attribute Recommendation Systems

Implicit Language Model in LSTM for OCR

1 code implementation23 May 2018 Ekraam Sabir, Stephen Rawls, Prem Natarajan

Neural networks have become the technique of choice for OCR, but many aspects of how and why they deliver superior performance are still unknown.

Language Modelling Optical Character Recognition (OCR)

WMRB: Learning to Rank in a Scalable Batch Training Approach

no code implementations10 Nov 2017 Kuan Liu, Prem Natarajan

We propose a new learning to rank algorithm, named Weighted Margin-Rank Batch loss (WMRB), to extend the popular Weighted Approximate-Rank Pairwise loss (WARP).


A Batch Learning Framework for Scalable Personalized Ranking

1 code implementation10 Nov 2017 Kuan Liu, Prem Natarajan

In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list.

An Investigation into the Pedagogical Features of Documents

no code implementations WS 2017 Emily Sheng, Prem Natarajan, Jonathan Gordon, Gully Burns

We refer to this learning utility as the "pedagogical value" of the document to the learner.

Deep Matching and Validation Network -- An End-to-End Solution to Constrained Image Splicing Localization and Detection

no code implementations27 May 2017 Yue Wu, Wael Abd-Almageed, Prem Natarajan

Here the task is to estimate the probability that the donor image has been used to splice the query image, and obtain the splicing masks for both the query and donor images.

Image Manipulation

Pose-Aware Face Recognition in the Wild

no code implementations CVPR 2016 Iacopo Masi, Stephen Rawls, Gerard Medioni, Prem Natarajan

We propose a method to push the frontiers of unconstrained face recognition in the wild, focusing on the problem of extreme pose variations.

Face Recognition

Face Recognition Using Deep Multi-Pose Representations

no code implementations23 Mar 2016 Wael Abd-Almageed, Yue Wua, Stephen Rawlsa, Shai Harel, Tal Hassner, Iacopo Masi, Jongmoo Choi, Jatuporn Toy Leksut, Jungyeon Kim, Prem Natarajan, Ram Nevatia, Gerard Medioni

In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features.

Face Recognition Face Verification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.