Picture for Sumit Shekhar

Sumit Shekhar

Seeing the Unseen: Visual Metaphor Captioning for Videos

Add code
Jun 07, 2024
Viaarxiv icon

"Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning

Add code
Jun 01, 2023
Viaarxiv icon

Audio Retrieval for Multimodal Design Documents: A New Dataset and Algorithms

Add code
Feb 28, 2023
Viaarxiv icon

Interactive Control over Temporal-consistency while Stylizing Video Streams

Add code
Jan 02, 2023
Viaarxiv icon

DistillAdapt: Source-Free Active Visual Domain Adaptation

Add code
May 24, 2022
Figure 1 for DistillAdapt: Source-Free Active Visual Domain Adaptation
Figure 2 for DistillAdapt: Source-Free Active Visual Domain Adaptation
Figure 3 for DistillAdapt: Source-Free Active Visual Domain Adaptation
Figure 4 for DistillAdapt: Source-Free Active Visual Domain Adaptation
Viaarxiv icon

Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity

Add code
Mar 09, 2022
Figure 1 for Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity
Figure 2 for Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity
Figure 3 for Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity
Figure 4 for Low-light Image and Video Enhancement via Selective Manipulation of Chromaticity
Viaarxiv icon

TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information

Add code
Nov 30, 2021
Figure 1 for TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
Figure 2 for TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
Figure 3 for TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
Figure 4 for TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information
Viaarxiv icon

OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis

Add code
Oct 07, 2021
Figure 1 for OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis
Figure 2 for OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis
Figure 3 for OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis
Figure 4 for OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis
Viaarxiv icon

LEAF-QA: Locate, Encode & Attend for Figure Question Answering

Add code
Jul 30, 2019
Figure 1 for LEAF-QA: Locate, Encode & Attend for Figure Question Answering
Figure 2 for LEAF-QA: Locate, Encode & Attend for Figure Question Answering
Figure 3 for LEAF-QA: Locate, Encode & Attend for Figure Question Answering
Figure 4 for LEAF-QA: Locate, Encode & Attend for Figure Question Answering
Viaarxiv icon

Show and Recall: Learning What Makes Videos Memorable

Add code
Aug 28, 2017
Figure 1 for Show and Recall: Learning What Makes Videos Memorable
Figure 2 for Show and Recall: Learning What Makes Videos Memorable
Figure 3 for Show and Recall: Learning What Makes Videos Memorable
Figure 4 for Show and Recall: Learning What Makes Videos Memorable
Viaarxiv icon