Jayesh Rajkumar Vachhani — accepted AI-conference papers

2026

ContextGraph: Lifelog Intelligence Framework for Contextual Subgraph Evolution

Anil Sharma, Gunturi Venkata Sai Phani Kiran, Jayesh Rajkumar Vachhani, Sourabh Vasant Gothe, Ayon Chattopadhyay, Yashwant Saini +2

AAAI 2026technical

Lifelogging involves the continuous and comprehensive recording of a user’s daily activities, behaviors, and interactions, offering valuable insights for personalized healthcare, event retrieval, and lifestyle analysis. However, extracting meaningful patterns from lifelog data requires models to cap

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

PhysID: Physics-based Interactive Dynamics from a Single-view Image

Sourabh Vasant Gothe, Ayon Chattopadhyay, Gunturi Venkata Sai Phani Kiran, Pratik, Vibhav Agarwal, Jayesh Rajkumar Vachhani +3

ICASSP 2025accepted

Transforming static images into interactive experiences remains a challenging task in computer vision. Tackling this challenge holds the potential to elevate mobile user experiences, notably through interactive and AR/VR applications. Current approaches aim to achieve this either using pre-recorded…

Cited by 0 Source ↗Scholar ↗

2024

SAM-GEBD: Zero-Cost Approach for Generic Event Boundary Detection

Pranay Kashyap, Sourabh Vasant Gothe, Vibhav Agarwal, Jayesh Rajkumar Vachhani

ICASSP 2024accepted

Generic Event Boundary Detection (GEBD) [1] is a crucial task in video analysis, aiming to identify class-agnostic event boundaries. Traditional supervised or unsupervised methods for GEBD rely on expensive data annotation and time-consuming training, often leading to limited generalization across d…

Cited by 0 Source ↗Scholar ↗

2023

Repetition Counting from Compressed Videos Using Sparse Residual Similarity

Rishabh Khurana, Jayesh Rajkumar Vachhani, Sourabh Vasant Gothe, Pranay Kashyap

ICASSP 2023accepted

It is common for modern video codecs to reach triple digit compression ratios, which clearly shows the information redundancy and low information density of the ubiquitous RGB frame video representation. We propose an approach that directly utilizes the components of a compressed video for predictin…

Cited by 0 Source ↗Scholar ↗

2023

Self-Similarity is all You Need for Fast and Light-Weight Generic Event Boundary Detection

Sourabh Vasant Gothe, Jayesh Rajkumar Vachhani, Rishabh Khurana, Pranay Kashyap

ICASSP 2023accepted

The self-similarity matrix (SSM) is becoming more prevalent in temporal representation understanding; it has been utilized for various video understanding tasks, such as classifying human actions, counting repetitions, and identifying generic event boundaries. Recently proposed methods for Generic E…

Cited by 0 Source ↗Scholar ↗

2021

Fontnet: On-Device Font Understanding and Prediction Pipeline

Rakshith S, Rishabh Khurana, Vibhav Agarwal, Jayesh Rajkumar Vachhani, Bhanodai Guggilla

ICASSP 2021accepted

Fonts are one of the most basic and core design concepts. Numerous use cases can benefit from an in depth understanding of Fonts such as Text Customization which can change text in an image while maintaining the Font attributes like style, color, size. Currently, Text recognition solutions can group…

Cited by 0 Source ↗Scholar ↗