πŸ‘οΈVision is the interface where photons meet consciousness - for carbon and silicon alike.

Hi πŸ‘‹! I’m a CS Ph.D. candidate at UCD in the Vision and Analytics Lab (THEIA Lab), working with Prof. Soumyabrata Dev.

I previously served as a research assistant at SIAT, CAS. collaborating with Prof. Zhengkun Yi, and earned my M.S. degree in Computer Science from USM under the supervision of Prof. Putra Sumari.

My current research focuses on computer vision, machine learning, and AI.


πŸ”₯ News

  • 2025.10:  🀝 Contributed MV-Only (high-speed mode) to mv-extractor. [upstream] [my fork] [PyPI]
  • 2025.09: Β πŸ“ Preprinted MoCLIP-Lite on arXiv: paper [code]
  • 2025.09: Β πŸ“ Preprinted MVP on arXiv: paper [code]
  • 2025.09: Β πŸ“ Preprinted MoCrop on arXiv: paper [code]
  • 2025.07: Β πŸ‘¨β€πŸŽ“ Obtained a new certification: Deep Learning with PyTorch : Image Segmentation from Coursera!
  • 2025.02: Β πŸ‘¨β€πŸŽ“ Obtained a new certification: LLM Agents from UC Berkeley!
  • 2024.11: Β πŸ‘¨β€πŸŽ“ Obtained a new certification: Neural Network and Deep Learning from DeepLearning.AI!
  • 2024.09: Β πŸ† Ranked top2.5% at National Information Center: Video Recognition for City Management Competition!
  • 2024.08: Β πŸ† Ranked top3.5% at NVIDIA and Alibaba: Multimodal Large Model Data Synthesis Challenge!
  • 2024.07: Β πŸ‘¨β€πŸŽ“ Obtained a new certification: Visual Perception from Columbia University!

πŸ“ Latest Publications

2025

  • MoCLIP-Lite: Efficient Video Recognition by Fusing CLIP with Motion Vectors
    B. Huang, N. Wang, A. Parakash, S. Dev
    arXiv preprint [2025] [Paper] [Code]

  • MVP: Motion Vector Propagation for Zero-Shot Video Object Detection
    B. Huang, N. Wang, W. Yao, S. Dev
    arXiv preprint [2025] [Paper] [Code]

  • MoCrop: Training Free Motion Guided Cropping for Efficient Video Action Recognition
    B. Huang, W. Yao, S. Chen, G. Wang, Q. Wang, S. Dev
    arXiv preprint [2025] [Paper] [Code]

  • TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers
    G. Wang, Q. Wang, B. Huang, S. Chen, D. John
    arXiv preprint [2025] [Paper]

  • Optimal Brain Connection: Towards Efficient Structural Pruning
    S. Chen, W. Ma, B. Huang, Q. Wang, G. Wang, W. Sun, L. Huang, D. John
    arXiv preprint [2025] [Paper]

  • DCentNet: Decentralized multistage biomedical signal classification using early exits
    X. Li, B. Huang, B. Cardiff, D. John
    Biomedical Signal Processing and Control [2025] [Paper] [Code]

2024

  • Dynamic liquid volume estimation using optical tactile sensors and spiking neural network
    B. Huang, S. Fang, M. Yin et al.
    Springer - Intelligent Service Robotics [2024] [Paper]

  • More papers on Google Scholar.

🧩 Open-Source Contributions

  • mv-extractor β€” Contributor (2025)
    A fast H.264/MPEG-4 motion-vector extractor with optional RGB decode skipping.
    β€’ Key: Implemented Motion-Vectors-Only / frame-decode skipping mode; docs & tests; acknowledged upstream.
    β€’ Links: Upstream Β· My fork Β· PyPI
    GitHub stars PyPI

πŸ‘¨β€πŸ’» Service

  • Reviewer - AAAI, ACM MM, ICRA, IEEE T-ASE, IEEE TIM
  • Session Assistant - IEEE RCAR

πŸ‘¨β€πŸ’» Research Focuses

 β€’ Video Recognition           (Outputs)       2025.01 - present
 β€’ Model Compression           (Outputs)       2023.09 - 2025.01
 β€’ Embodied Intelligence       (Outputs)       2021.08 - 2023.08

πŸƒβ€β™‚οΈ Personal life

  • πŸƒβ€β™‚οΈ Completed two marathons (42.195 km)