Akash Kumar

I am a fifth year PhD student at Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), under the supervision of Prof. Yogesh Singh Rawat.

I have a broad interest in deep learning and computer vision. My current research mainly focuses on data-efficient approaches for dense video tasks.

Looking for full-time positions (Jan'26)! Feel free to drop me an email.

Email  /  Google Scholar  /  Github  /  LinkedIn  /  Resume  /  Thesis Poster

Updates

  May'25: Started internship at Amazon, Bellevue, WA
  Apr'25: Received Doctoral Research Support Award from UCF. 💥
  Mar'25: Student Travel Award grant to attend ICLR 2025
  Mar'25: STPro accepted at CVPR 2025 💥
  Feb'25: Student Travel Award grant to attend WACV 2025
  Feb'25: Student Travel Award grant to attend AAAI 2025
  Jan'25: CoSPaL (First author paper) accepted at ICLR 2025 💥
  Jan'25: Selected for Doctoral consortium at IEEE/CVF WACV 2025 💥
  Dec'24: SMT (First author paper) accepted at AAAI 2025 💥
  May'24: Started internship at Amazon, Palo Alto, CA
  Dec'23: SSL-AL accepted at AAAI 2024 💥
  Oct'23: Benchmark-SSL (First author paper) accepted at NeurIPS Self-Superivsed Workshop 2024
  Mar'23: MAMA-VAD accepted at CVPR Workshops 2022
  Mar'22: E2E-SSL (First author paper) accepted at CVPR 2022 💥

Spatio-Temporal Anamoly Detection.

Towards Open-vocabulary video object understanding.

Below is a selected list of my works (in chronological order), representative papers are highlighted.

Adaptation of VLMs leveraging Large Language Models (LLMs) via spatio-temporal composite relationship.

Improved VLMs grounding capabilities via action composition and complex spatio-temporal scene understanding.

Developed first vision language models (VLMs) for dense multimodal video detection task without any labels. Devised context aware and self-paced progressive scene learning approach.

Learning from mistakes on labelled set and transfer that learning to pseudo labels from unlabeled set to enhance spatio-temporal localization. Class-agnostic spatio-temporal refinement module and temporal coherency constraint for better spatio-temporal localization.

High-pass filtering for enhanced pseudo labels to improvise spatio-temporal localization. Simple sample augmentation strategy for informative sample selection.

First exhaustive study on impact of pre-training in self-supervised learning for videos. Proposed a simple knowledge distillation approach outperforming previous works with 90% less videos.

First end-to-end semi-supervised approach for video action detection task. Short-term and long-term smoothness constraints to exploit spatio-temporal coherency.

Developed new spatio-temporal surveillance based dataset for real-world challenges.

Below is a list of my works (in chronological order) for funding projects.

Investigate the robustness of gait recognition models against perturbations and corruptions, focusing on both key components: the parsing model and the gait recognition model.

A versatile solution applicable to all limited label settings (semi-supervised & domain adaptation), via low-dimensional clustering and knowledge distillation.

Proposed real-time online action detection system for open-world surviellance videos.

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.