activity
20162021
most citedTracking Persons-of-Interest via Unsupervised Representation Adaptation

6 citations · 10 across the 4 of their papers we have counts for

collaborators

8 papers

cs.CV2021

A Hierarchical Variational Neural Uncertainty Model for Stochastic Video Prediction

Moitreya Chatterjee, Narendra Ahuja, Anoop Cherian

Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena. Prior approaches to solve this task typically estimate…

cs.CV2021

Visual Scene Graphs for Audio Source Separation

Moitreya Chatterjee, Jonathan Le Roux, Narendra Ahuja +1

State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches ofte…

cs.CV20213 cited

Unsupervised 3D Pose Estimation for Hierarchical Dance Video Recognition

Xiaodan Hu, Narendra Ahuja

Dance experts often view dance as a hierarchy of information, spanning low-level (raw images, image sequences), mid-levels (human poses and bodypart movements), and high-level (dan…

cs.CV20201 cited

Sound2Sight: Generating Visual Dynamics from Sound and Context

Anoop Cherian, Moitreya Chatterjee, Narendra Ahuja

Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this proble…

cs.CV2018

Coreset-Based Neural Network Compression

Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja

We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weig…

cs.CV2018

DeepMVS: Learning Multi-view Stereopsis

Po-Han Huang, Kevin Matzen, Johannes Kopf +2

We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction. Taking an arbitrary number of posed images as input, we first produce a set…