Search Results for author: Pradeep Natarajan

Found 10 papers, 2 papers with code

FPI: Failure Point Isolation in Large-scale Conversational Assistants

no code implementations NAACL (ACL) 2022 Rinat Khaziev, Usman Shahid, Tobias Röding, Rakesh Chada, Emir Kapanci, Pradeep Natarajan

Large-scale conversational assistants such as Cortana, Alexa, Google Assistant and Siri process requests through a series of modules for wake word detection, speech recognition, language understanding and response generation.

Response Generation speech-recognition +1

FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory

no code implementations ICCV 2023 Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal, Xu Zhang, Yue Wu, Rakesh Chada, Pradeep Natarajan, Henrik I. Christensen

Extensive evaluation results show that our proposed method outperforms the previous state-of-the-art algorithm by 50. 5%, on Multi-turn FashionIQ -- the only existing multi-turn fashion dataset currently, in addition to having a relative improvement of 12. 6% on Multi-turn Shoes -- an extension of the single-turn Shoes dataset that we created in this work.

Image Retrieval Retrieval

MoMo: A shared encoder Model for text, image and multi-Modal representations

no code implementations11 Apr 2023 Rakesh Chada, Zhaoheng Zheng, Pradeep Natarajan

The results on downstream text-only, image-only and multimodal tasks show that our model is competitive with several strong models while using fewer parameters and lesser pre-training data.

FashionVLP: Vision Language Transformer for Fashion Retrieval With Feedback

no code implementations CVPR 2022 Sonam Goenka, Zhaoheng Zheng, Ayush Jaiswal, Rakesh Chada, Yue Wu, Varsha Hedau, Pradeep Natarajan

Fashion image retrieval based on a query pair of reference image and natural language feedback is a challenging task that requires models to assess fashion related information from visual and textual modalities simultaneously.

Image Retrieval Retrieval

FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models

1 code implementation EMNLP 2021 Rakesh Chada, Pradeep Natarajan

On the multilingual TydiQA benchmark, our model outperforms the XLM-Roberta-large by an absolute margin of upto 40 F1 points and an average of 33 F1 points in a few-shot setting (<= 64 training examples).

Few-Shot Learning Question Answering

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

Class-agnostic Object Detection

no code implementations28 Nov 2020 Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Premkumar Natarajan

Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions.

Ranked #100 on Image Classification on ObjectNet (using extra training data)

Benchmarking Class-agnostic Object Detection +5

Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts

no code implementations CVPR 2014 Shuang Wu, Sravanthi Bondugula, Florian Luisier, Xiaodan Zhuang, Pradeep Natarajan

Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples.

Attribute Event Detection

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