https://forminju.github.io/https://forminju.github.io/cv/https://forminju.github.io/dev-tools/https://forminju.github.io/dev-tools/palette-visualizer/https://forminju.github.io/dev-tools/screen-visualizer/https://forminju.github.io/dev-tools/simple-theme-visualizer/https://forminju.github.io/dev-tools/theme-visualizer/https://forminju.github.io/projects/https://forminju.github.io/projects/rag-video-qa/https://forminju.github.io/projects/risk-state-prediction/https://forminju.github.io/projects/zeroshot-driver-captioning/https://forminju.github.io/publications/https://forminju.github.io/publications/cap4bridge/https://forminju.github.io/publications/follow-the-saliency/https://forminju.github.io/publications/phonemizing/https://forminju.github.io/publications/sail/https://forminju.github.io/publications/sali4vid/https://forminju.github.io/publications/sync/https://forminju.github.io/tags/https://forminju.github.io/tags/data-centric/https://forminju.github.io/tags/dense%20video%20captioning/https://forminju.github.io/tags/driver%20monitoring/https://forminju.github.io/tags/fine-tuning/https://forminju.github.io/tags/grapheme-to-phoneme/https://forminju.github.io/tags/multilingual%20speech/https://forminju.github.io/tags/retrieval-augmented%20generation/https://forminju.github.io/tags/safety/https://forminju.github.io/tags/text-video%20retrieval/https://forminju.github.io/tags/video%20qa/https://forminju.github.io/tags/vision-language/https://forminju.github.io/tags/vision-language%20model/https://forminju.github.io/tags/zero-shot%20captioning/https://forminju.github.io/talks/https://forminju.github.io/teaching/