Skip to content
View AKASH2907's full-sized avatar
🎯
(1.01)^365
🎯
(1.01)^365

Highlights

  • Pro

Organizations

@UCF-CRCV

Block or report AKASH2907

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
AKASH2907/README.md

Hola, I'm Akash Kumar! πŸ‘‹

  • πŸ”­ I’m a final-year Ph.D. student at the University of Central Florida.
  • 🌱 Research Focus: Label-efficient approaches (Weakly/Semi/Self) for dense video tasks (Unimodal - Video Action Detection and Multimodal - Spatio-Temporal Video Grounding).
  • πŸ€– Looking actively for full-time positions. Feel free to drop me an email.
    • πŸ”¬ Label-Efficient (self/semi/weakly-supervised)
    • πŸŽ₯ Dense Video understanding (detection/segmentation)
    • 🀝 Adapting VLMs to be more user interactive + context aware

Pinned Loading

  1. copsal-weakly-stvg copsal-weakly-stvg Public

    [ICLR'25, 5xCVPRW'25] Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding

    1

  2. stable-mean-teacher stable-mean-teacher Public

    [AAAI25 Main Technical Track] Stable Mean Teacher for Semi-supervised Video Action Detection

    Python 4

  3. pi-consistency-activity-detection pi-consistency-activity-detection Public

    [CVPR 2022] End-to-End Semi-Supervised Learning for Video Action Detection

    Python 35 4

  4. semi-sup-active-learning semi-sup-active-learning Public

    [AAAI-24 Main Technical Track] - Semi-Supervised Active Learning for Video Action Detection

    Python 1

  5. project_sunroof_india project_sunroof_india Public

    Analyzed Google Satellite images to generate a report on individual house rooftop's solar power potential

    Python 157 46

  6. deepfakes_video_classification deepfakes_video_classification Public

    Deepfakes Video classification via CNN, LSTM, C3D and triplets [IWBF'20]

    Python 67 20