Publications

VideoLights: Cross-Modal Cross-Task Transformer for Joint Video Highlight Detection and Moment Retrieval

Md Rizwan Parvez, Dhiman Paul, Nabeel Mohammed, and Shafin Rahman
Pre-print, 2025

[paper]

BibTeX

@misc{paul2026videolights,
  title = {{VideoLights: Cross-Modal Cross-Task Transformer for Joint Video Highlight Detection and Moment Retrieval}},
  author = {Parvez, Md Rizwan and Paul, Dhiman and Mohammed, Nabeel and Rahman, Shafin},
  howpublished = {Pre-print},
  year = {2025}
}