Picture for Jyoti Kini

Jyoti Kini

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

Add code
May 28, 2024
Viaarxiv icon

Egocentric RGB+Depth Action Recognition in Industry-Like Settings

Add code
Sep 25, 2023
Viaarxiv icon

Ensemble Modeling for Multimodal Visual Action Recognition

Add code
Aug 10, 2023
Viaarxiv icon

3DMODT: Attention-Guided Affinities for Joint Detection & Tracking in 3D Point Clouds

Add code
Nov 01, 2022
Viaarxiv icon

Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging

Add code
Apr 22, 2022
Figure 1 for Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging
Figure 2 for Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging
Figure 3 for Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging
Figure 4 for Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging
Viaarxiv icon

Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation

Add code
Apr 22, 2022
Figure 1 for Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation
Figure 2 for Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation
Figure 3 for Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation
Figure 4 for Tag-Based Attention Guided Bottom-Up Approach for Video Instance Segmentation
Viaarxiv icon

Florida Wildlife Camera Trap Dataset

Add code
Jun 23, 2021
Figure 1 for Florida Wildlife Camera Trap Dataset
Figure 2 for Florida Wildlife Camera Trap Dataset
Figure 3 for Florida Wildlife Camera Trap Dataset
Figure 4 for Florida Wildlife Camera Trap Dataset
Viaarxiv icon

PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking

Add code
Jun 03, 2021
Figure 1 for PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking
Figure 2 for PC-DAN: Point Cloud based Deep Affinity Network for 3D Multi-Object Tracking
Viaarxiv icon