Makarand Tapaswi

research

∙ 09/08/2023

Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rays

Real-world application of chest X-ray abnormality classification require...

0 Aroof Aimen, et al. ∙

research

∙ 04/12/2023

How you feelin'? Learning Emotions and Mental States in Movie Scenes

Movie story analysis requires understanding characters' emotions and men...

0 Dhruv Srivastava, et al. ∙

research

∙ 03/22/2023

GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

Commonsense question-answering (QA) methods combine the power of pre-tra...

0 Dhaval Taunk, et al. ∙

research

∙ 01/05/2023

Test of Time: Instilling Video-Language Models with a Sense of Time

Modeling and understanding time remains a challenge in contemporary vide...

11 Piyush Bagad, et al. ∙

research

∙ 12/02/2022

Sonus Texere! Automated Dense Soundtrack Construction for Books using Movie Adaptations

Reading, much like music listening, is an immersive experience that tran...

0 Jaidev Shriram, et al. ∙

research

∙ 11/23/2022

Can we Adopt Self-supervised Pretraining for Chest X-Rays?

Chest radiograph (or Chest X-Ray, CXR) is a popular medical imaging moda...

0 Arsh Verma, et al. ∙

research

∙ 11/17/2022

Language Conditioned Spatial Relation Reasoning for 3D Object Grounding

Localizing objects in 3D scenes based on natural language requires under...

0 Shizhe Chen, et al. ∙

research

∙ 10/29/2022

Unsupervised Audio-Visual Lecture Segmentation

Over the last decade, online lecture videos have become increasingly pop...

0 Darshan Singh S, et al. ∙

research

∙ 10/19/2022

Grounded Video Situation Recognition

Dense video understanding requires answering several questions such as w...

0 Zeeshan Khan, et al. ∙

research

∙ 09/11/2022

Instruction-driven history-aware policies for robotic manipulations

In human environments, robots are expected to accomplish a variety of ma...

6 Pierre-Louis Guhur, et al. ∙

research

∙ 08/24/2022

Learning from Unlabeled 3D Environments for Vision-and-Language Navigation

In vision-and-language navigation (VLN), an embodied agent is required t...

17 Shizhe Chen, et al. ∙

research

∙ 08/03/2022

Learning Object Manipulation Skills from Video via Approximate Differentiable Physics

We aim to teach robots to perform simple object manipulation tasks by wa...

8 Vladimír Petrík, et al. ∙

research

∙ 02/23/2022

Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation

Following language instructions to navigate in unseen environments is a ...

35 Shizhe Chen, et al. ∙

research

∙ 11/10/2021

Feature Generation for Long-tail Classification

The visual world naturally exhibits an imbalance in the number of object...

0 Rahul Vigneswaran, et al. ∙

research

∙ 08/20/2021

Airbert: In-domain Pretraining for Vision-and-Language Navigation

Vision-and-language navigation (VLN) aims to enable embodied agents to n...

42 Pierre-Louis Guhur, et al. ∙

research

∙ 11/13/2020

Learning Object Manipulation Skills via Approximate State Estimation from Real Videos

Humans are adept at learning new tasks by watching a few instructional v...

9 Vladimír Petrík, et al. ∙

research

∙ 04/05/2020

Deep Multimodal Feature Encoding for Video Ordering

True understanding of videos comes from a joint analysis of all its moda...

0 Vivek Sharma, et al. ∙

research

∙ 04/05/2020

Clustering based Contrastive Learning for Improving Face Representations

A good clustering algorithm can discover natural groupings in data. Thes...

0 Vivek Sharma, et al. ∙

research

∙ 03/29/2020

Learning Interactions and Relationships between Movie Characters

Interactions between people are often governed by their relationships. O...

0 Anna Kukleva, et al. ∙

research

∙ 12/30/2019

The Shmoop Corpus: A Dataset of Stories with Loosely Aligned Summaries

Understanding stories is a challenging reading comprehension problem for...

0 Atef Chaudhury, et al. ∙

research

∙ 08/09/2019

Video Face Clustering with Unknown Number of Clusters

Understanding videos such as TV series and movies requires analyzing who...

1 Makarand Tapaswi, et al. ∙

research

∙ 06/07/2019

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips

Learning text-video embeddings usually requires a dataset of video clips...

1 Antoine Miech, et al. ∙

research

∙ 03/03/2019

Self-Supervised Learning of Face Representations for Video Face Clustering

Analyzing the story behind TV series and movies often requires understan...

0 Vivek Sharma, et al. ∙

research

∙ 06/06/2018

Progressive Reasoning by Module Composition

Humans learn to solve tasks of increasing complexity by building on top ...

0 Seung Wook Kim, et al. ∙

research

∙ 12/19/2017

MovieGraphs: Towards Understanding Human-Centric Situations from Videos

There is growing interest in artificial intelligence to build socially i...

0 Paul Vicol, et al. ∙

research

∙ 08/14/2017

Situation Recognition with Graph Neural Networks

We address the problem of recognizing situations in images. Given an ima...

0 Ruiyu Li, et al. ∙

research

∙ 11/22/2016

Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning

The Earth Mover's Distance (EMD) computes the optimal cost of transformi...

0 Manuel Martinez, et al. ∙

research

∙ 10/15/2016

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Collecting training images for all visual categories is not only expensi...

0 Ziad Al-Halah, et al. ∙

research

∙ 12/09/2015

MovieQA: Understanding Stories in Movies through Question-Answering

We introduce the MovieQA dataset which aims to evaluate automatic story ...

0 Makarand Tapaswi, et al. ∙

Makarand Tapaswi

Featured Co-authors