publications

Published, under review, and in-preparation work — grouped by year, newest first.

2027

  1. Video Comprehension Score (VCS) and Benchmark (VCB) for Long-Form Paragraph-Level Video Description Evaluation
    Harsh Dubey, Mukhtiar Ali, Kwanghee Won, and 1 more author
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2027
    In preparation — targeting CVPR 2027 main conference

2026

  1. Multi-Scale Encoding, Gated Fusion, and Temporal Context for Lightweight Wearable Stress Detection
    Mukhtiar Ali and Chulwoo Pack
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Jun 2026
  2. CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video–Language Models
    Mukhtiar Ali, Harsh Dubey, Sugam Mishra, and 1 more author
    In Proceedings of the 2nd Workshop on Evaluation for Multimodal Generation (EvalMG @ ACM SIGIR). Dataset: CLIP-CC / HF , Jul 2026
    Long paper; presented at EvalMG 2026, Melbourne. Mukhtiar Ali, Harsh Dubey, and Sugam Mishra contributed equally
  3. KBS
    4_physiofusion_architecture.png
    Trustworthy Multimodal Learning via Uncertainty-aware Feature Modulation and Reliability Auditing
    Seungpil Choi, Mukhtiar Ali, Chulwoo Pack, and 1 more author
    Knowledge-Based Systems (KBS), 2026
    Under review