Ishan Dave

I am a fifth-year Ph.D. student in the Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), advised by Prof. Mubarak Shah. .

Email  /  Google Scholar  /  Github  /  LinkedIn  /  CV (it is public version, for a detailed version feel free to ask!)

Developed fine-grained video retrieval systems for large-scale video galleries with millions of videos

Proposed Self-supervised Video Representation Learning method suitable for both high-level and low-level video downstream tasks

I have a broad interest in computer vision and machine learning. My current research mainly focuses on video representation learning with limited labels (self/semi-supervised learning), action recognition, and privacy preservation in video understanding tasks. I have also worked on various robotics-related vision tasks like event-camera-based action recognition and drone-to-drone detections from videos. Below is a selected list of my works (in chronological order), representative papers are highlighted.

We demonstrate experimentally that our more challenging frame-level task formulations and the removal of shortcuts drastically improve the quality of features learned through temporal self-supervision. Our extensive experiments show state-of-the-art performance across 10 video understanding datasets, illustrating the generalization ability and robustness of our learned video representations.

We propose TeD-SPAD, a privacy-aware video anomaly detection framework that destroys visual private information in a self-supervised manner. In particular, we propose the use of a temporally-distinct triplet loss to promote temporally discriminative features, which complements current weakly-supervised VAD methods.

We propose a video transformer-based framework for event-camera based action recognition, which leverages event-contrastive loss and augmentations to adapt the network to event data. Our method achieved state-of-the-art results on N-EPIC Kitchens dataset and competitive results on the standard DVS Gesture recognition dataset, while requiring less computation time compared to competitive prior approaches.

We propose a student-teacher semi-supervised learning framework, where we distill knowledge from a temporally-invariant and temporally-distinctive teacher. Depending on the nature of the unlabeled video, we dynamically combine the knowledge of these two teachers based on a novel temporal similarity-based reweighting scheme. State-of-the-art results on Kinetics400, UCF101, HMDB51.

We propose a simple yet effective framework, TransVisDrone, that provides an end-to-end solution with higher computational efficiency. We utilize CSPDarkNet-53 network to learn object-related spatial features and VideoSwin model to improve drone detection in challenging scenarios by learning spatio-temporal dependencies of drone motion.

For the first time, we present a novel training framework that removes privacy information from input video in a self-supervised manner without requiring privacy labels. We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss.

We propose a new temporal contrastive learning framework for self-supervised video representation learning, consisting of two novel losses that aim to increase the temporal diversity of learned features. The framework achieves state-of-the-art results on various downstream video understanding tasks, including significant improvement in fine-grained action classification for visually similar classes.

We propose a realtime, online, action detection system which can generalize robustly on any unknown facility surveillance videos. We tackle the challenging nature of action classification problem in various aspects like handling the class-imbalance training using PLM method and learning multi-label action correlations using LSEP loss. In order to improve the computational efficiency of the system, we utilize knowledge distillation.

Gabriella consists of three stages: tubelet extraction, activity classification, and online tubelet merging. Gabriella utilizes a localization network for tubelet extraction, with a novel Patch-Dice loss to handle variations in actor size, and a Tubelet-Merge Action-Split (TMAS) algorithm to detect activities efficiently and robustly.

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.