Sauradip Nag

STALE. [ECCV 2022] Official Pytorch Implementation of the paper : " Zero-Shot Temporal Action Detection via Vision-Language Prompting "

DiffusionTAD. [ICCV 2023] Official PyTorch implementation of the paper "DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion"

night_image_semantic_segmentation. [ICIP 2019] : Official PyTorch implementation of the paper "What's There in The Dark" accepted in IEEE International Conference in Image Processing 2019 (ICIP19) , Taipei, Taiwan.

action_localization_visualization. Temporal Action Localization Visualization Tool (TALVT) is a Javascript based simple visualization tool to visualize the outcomes of the code before using the evaluation script

SPOT. [ECCV 2022] Official Pytorch Implementation of the paper : " Semi-Supervised Temporal Action Detection with Proposal-Free Masking "

TAGS. [ECCV 2022] Official Pytorch Implementation of paper : " Proposal-Free Temporal Action Detection with Global Segmentation Mask Learning "

GAP. [CVPR 2023] Official PyTorch implementation of the paper "GAP: Post-Processing Temporal Action Detection"

In-2-4D. [SIGGRAPH ASIA 2025] PyTorch implementation of "Inbetweening from Two Single-View Images to 4D Generation"

MUPPET. [ Arxiv 2023 ] This repository contains the code for "MUPPET: Multi-Modal Few-Shot Temporal Action Detection"

vision_based_robot_navigation. Deep Learning based Free Space Planning and Robot Navigation

BaseLine-Remover. This a small Matlab Implementation for Removal of Base Line from document using Edge Directional Kernel stated in paper " Edge enhancement algorithm for low-dose X-ray fluoroscopic imaging " by Lee et al.

depthForecasting.

Gesture-Recognition-And-Software-Mapping. This is an application , where Gesture is Recognised from Live Video Stream of WebCam of Laptop and each of these Gestures are mapped to Softwares to perform certain Action . All of this is implemented from scratch using OpenCV + Tensorflow Backend + TFLearn + Image Processing

GSM. [ECCV 2022] Official PyTorch Implementation for : Global Segmentation Mask based Temporal Action Localization

DiffSED. [AAAI 2024] DiffSED: Sound Event Detection with Denoising Diffusion

Opencv-Hand-Classifier. Jupyter Notebook

GVF-SWT-Based-OCR. This is a Self Designed OCR , built implementing Gradient Vector Flow and Stroke Width Transform which can Identify any Marathon / Sports Bib Number