Picture for Saumik Bhattacharya

Saumik Bhattacharya

Simba: Mamba augmented U-ShiftGCN for Skeletal Action Recognition in Videos

Apr 11, 2024
Viaarxiv icon

LATIS: Lambda Abstraction-based Thermal Image Super-resolution

Nov 18, 2023
Viaarxiv icon

Histopathological Image Analysis with Style-Augmented Feature Domain Mixing for Improved Generalization

Add code
Oct 31, 2023
Viaarxiv icon

Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance

Oct 06, 2023
Figure 1 for Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Figure 2 for Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Figure 3 for Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Figure 4 for Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Viaarxiv icon

ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition

Aug 07, 2023
Viaarxiv icon

FAST: Font-Agnostic Scene Text Editing

Aug 05, 2023
Viaarxiv icon

DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning

Aug 02, 2023
Figure 1 for DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
Figure 2 for DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
Figure 3 for DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
Figure 4 for DySTreSS: Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
Viaarxiv icon

SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation

Add code
May 02, 2023
Figure 1 for SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Figure 2 for SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Figure 3 for SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Figure 4 for SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation
Viaarxiv icon

MMC: Multi-Modal Colorization of Images using Textual Descriptions

Apr 25, 2023
Figure 1 for MMC: Multi-Modal Colorization of Images using Textual Descriptions
Figure 2 for MMC: Multi-Modal Colorization of Images using Textual Descriptions
Figure 3 for MMC: Multi-Modal Colorization of Images using Textual Descriptions
Figure 4 for MMC: Multi-Modal Colorization of Images using Textual Descriptions
Viaarxiv icon

Global Context-Aware Person Image Generation

Add code
Feb 28, 2023
Figure 1 for Global Context-Aware Person Image Generation
Figure 2 for Global Context-Aware Person Image Generation
Figure 3 for Global Context-Aware Person Image Generation
Figure 4 for Global Context-Aware Person Image Generation
Viaarxiv icon