Search Results for author: Vishwa Vinay

Found 15 papers, 2 papers with code

Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions

no code implementations4 Nov 2022 Gaurav Verma, Vishwa Vinay, Ryan A. Rossi, Srijan Kumar

Our work aims to highlight and encourage further research on the robustness of deep multimodal models to realistic variations, especially in human-facing societal applications.

GEMS: Scene Expansion using Generative Models of Graphs

no code implementations8 Jul 2022 Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil, Aniruddha Mahapatra, Kuldeep Kulkarni, Vishwa Vinay

To this end, we formulate scene graph expansion as a sequential prediction task involving multiple steps of first predicting a new node and then predicting the set of relationships between the newly predicted node and previous nodes in the graph.

Graph Generation Image Retrieval +1

Offline Evaluation of Ranked Lists using Parametric Estimation of Propensities

no code implementations6 Jun 2022 Vishwa Vinay, Manoj Kilaru, David Arbour

Search engines and recommendation systems attempt to continually improve the quality of the experience they afford to their users.

Learning-To-Rank Recommendation Systems

CyCLIP: Cyclic Contrastive Language-Image Pretraining

1 code implementation28 May 2022 Shashank Goel, Hritik Bansal, Sumit Bhatia, Ryan A. Rossi, Vishwa Vinay, Aditya Grover

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness.

Representation Learning Visual Reasoning +1

Curriculum Learning for Dense Retrieval Distillation

1 code implementation28 Apr 2022 Hansi Zeng, Hamed Zamani, Vishwa Vinay

Recent work has shown that more effective dense retrieval models can be obtained by distilling ranking knowledge from an existing base re-ranking model.

Knowledge Distillation Passage Retrieval +2

Gaudí: Conversational Interactions with Deep Representations to Generate Image Collections

no code implementations5 Dec 2021 Victor S. Bursztyn, Jennifer Healey, Vishwa Vinay

Based on recent advances in realistic language modeling (GPT-3) and cross-modal representations (CLIP), Gaud\'i was developed to help designers search for inspirational images using natural language.

Language Modelling

Generating Compositional Color Representations from Text

no code implementations22 Sep 2021 Paridhi Maheshwari, Nihal Jain, Praneetha Vaddamanu, Dhananjay Raut, Shraiysh Vaishay, Vishwa Vinay

While this dataset is specialized for our investigations on color, the method can be extended to other visual dimensions where composition is of interest.

Attribute Contrastive Learning +3

Scene Graph Embeddings Using Relative Similarity Supervision

no code implementations6 Apr 2021 Paridhi Maheshwari, Ritwick Chaudhry, Vishwa Vinay

In this work, we employ a graph convolutional network to exploit structure in scene graphs and produce image embeddings useful for semantic image retrieval.

Contrastive Learning Image Retrieval +1

Botcha: Detecting Malicious Non-Human Traffic in the Wild

no code implementations2 Mar 2021 Sunny Dhamnani, Ritwik Sinha, Vishwa Vinay, Lilly Kumari, Margarita Savova

Malicious bots make up about a quarter of all traffic on the web, and degrade the performance of personalization and recommendation algorithms that operate on e-commerce sites.

Learning Colour Representations of Search Queries

no code implementations17 Jun 2020 Paridhi Maheshwari, Manoj Ghuhan, Vishwa Vinay

We leverage historical clickthrough data to produce a colour representation for search queries and propose a recurrent neural network architecture to encode unseen queries into colour space.

Image Retrieval

"To Target or Not to Target": Identification and Analysis of Abusive Text Using Ensemble of Classifiers

no code implementations5 Jun 2020 Gaurav Verma, Niyati Chhaya, Vishwa Vinay

With rising concern around abusive and hateful behavior on social media platforms, we present an ensemble learning method to identify and analyze the linguistic properties of such content.

BIG-bench Machine Learning Ensemble Learning

Using Image Captions and Multitask Learning for Recommending Query Reformulations

no code implementations2 Mar 2020 Gaurav Verma, Vishwa Vinay, Sahil Bansal, Shashank Oberoi, Makkunda Sharma, Prakhar Gupta

Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results.

Descriptive Image Captioning +1

Modeling Time to Open of Emails with a Latent State for User Engagement Level

no code implementations18 Aug 2019 Moumita Sinha, Vishwa Vinay, Harvineet Singh

In this paper we use a survival analysis framework to predict the time to open an email once it has been received.

General Classification Marketing +2

Offline Evaluation of Ranking Policies with Click Models

no code implementations27 Apr 2018 Shuai Li, Yasin Abbasi-Yadkori, Branislav Kveton, S. Muthukrishnan, Vishwa Vinay, Zheng Wen

We analyze our estimators and prove that they are more efficient than the estimators that do not use the structure of the click model, under the assumption that the click model holds.

Recommendation Systems

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