iiinova — where your digital self keeps evolving

Hao-Wen (Herman) Dong 董皓文

@hermandong.bsky.social

Assistant Professor at University of Michigan | PhD from UC San Diego | Human-Centered Generative AI for Content Creation

Posts Replies Media

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🙌Of course, nothing would have been possible without the lead of Weihan Xu (wx83.github.io) and the amazing collaboration with Paul Liang, Haven Kim, Julian McAuley and Taylor Berg-Kirkpatrick! 📜Paper: arxiv.org/pdf/2410.05586 🎦Demo: wx83.github.io/TeaserGen_Of...

010

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

📽And old movies!

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🧑‍🏫And TED talks!

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🎬We tested our models on documentaries of various topics, including environmental, societal and historical issues.

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🛠️We proposed two methods for narration-video matching: 1️⃣a pretraining-based model using pretrained contrastive language-vision models and 2️⃣a deep sequential model that learns the mapping between the narrations and visuals.

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🛠️We adopted a two-stage approach for generating a documentary teaser: 1️⃣first, we generate the teaser narration given the transcribed narration of the documentary; 2️⃣then, we select the relevant visual content to accompany the generated narration.

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🔥We presented the DocumentaryNet, a collection of 1,200+ high-quality documentaries with their teasers.

110

Hao-Wen (Herman) Dong 董皓文 @hermandong.bsky.social · 26/01/2025

🎉Super excited to share that our TeaserGen project led by Weihan Xu (wx83.github.io) has been accepted to #ICLR2025! 🔍We explored a new task of generating teasers for long documentaries. 🤩We presented a new dataset, new models, and new evaluation metrics for teaser generation.

141