Trendoday

EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning

Egocentric video captioning requires fine-grained detail and accurate timing, yet current multimodal large language models (MLLMs) often miss brief actions, confuse their order, or misinterpret the we

  • Upvotes5
#10Rank now –
#7Peak rank
3Days on list
409Score · 7d
Nov 20, 2026First seen
Rank · 7 days

About this paper

Egocentric video captioning requires fine-grained detail and accurate timing, yet current multimodal large language models (MLLMs) often miss brief actions, confuse their order, or misinterpret the wearer's motion. Existing caption formats also offer limited support for combining detailed narration with precise timing. We present EgoCaptioner, which pairs a video-level overview of the setting, participants, and the wearer's overall activity with timed steps whose narration adapts to varying perceptual demands and marks key moments at specific timestamps. We develop a coarse-to-fine annotation pipeline that establishes event structure before expanding step descriptions, yielding 50,000…

Upvotes
5
Authors
17
Published
Nov 19, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 30 checks on 3 different days. Its best position was #7 of 30, reached on Nov 20, 11:29 UTC. It is #10 right now, holding steady at #10 over the last 6 checks.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 Nov 20Nov 20Nov 21Nov 22Nov 22 Nov 20, 05:29 UTC · #27Nov 20, 07:29 UTC · #17Nov 20, 09:29 UTC · #9Nov 20, 11:29 UTC · #7Nov 20, 13:29 UTC · #8Nov 20, 15:29 UTC · #8Nov 20, 17:29 UTC · #8Nov 20, 19:29 UTC · #10Nov 20, 21:29 UTC · #10Nov 20, 23:29 UTC · #10Nov 21, 01:29 UTC · #10Nov 21, 03:29 UTC · #10Nov 21, 05:29 UTC · #10Nov 21, 07:29 UTC · #10Nov 21, 09:29 UTC · #10Nov 21, 11:29 UTC · #10Nov 21, 13:29 UTC · #10Nov 21, 15:29 UTC · #10Nov 21, 17:29 UTC · #10Nov 21, 19:29 UTC · #10Nov 21, 21:29 UTC · #10Nov 21, 23:29 UTC · #10Nov 22, 01:29 UTC · #10Nov 22, 03:29 UTC · #10Nov 22, 05:29 UTC · #10Nov 22, 07:29 UTC · #10Nov 22, 09:29 UTC · #10Nov 22, 11:29 UTC · #10Nov 22, 13:29 UTC · #10Nov 22, 15:29 UTC · #10

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

▲ as reported by Hugging Face.

081725 Nov 20Nov 20Nov 21Nov 22Nov 22 Nov 20, 05:29 UTC · 5Nov 20, 07:29 UTC · 9Nov 20, 09:29 UTC · 19Nov 20, 11:29 UTC · 22Nov 20, 13:29 UTC · 22Nov 20, 15:29 UTC · 23Nov 20, 17:29 UTC · 24Nov 20, 19:29 UTC · 24Nov 20, 21:29 UTC · 24Nov 20, 23:29 UTC · 24Nov 21, 01:29 UTC · 24Nov 21, 03:29 UTC · 24Nov 21, 05:29 UTC · 24Nov 21, 07:29 UTC · 24Nov 21, 09:29 UTC · 24Nov 21, 11:29 UTC · 24Nov 21, 13:29 UTC · 24Nov 21, 15:29 UTC · 25Nov 21, 17:29 UTC · 25Nov 21, 19:29 UTC · 25Nov 21, 21:29 UTC · 25Nov 21, 23:29 UTC · 25Nov 22, 01:29 UTC · 25Nov 22, 03:29 UTC · 25Nov 22, 05:29 UTC · 25Nov 22, 07:29 UTC · 25Nov 22, 09:29 UTC · 25Nov 22, 11:29 UTC · 25Nov 22, 13:29 UTC · 25Nov 22, 15:29 UTC · 25

Questions

Is EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning trending on HF Daily Papers right now?

Yes. As of Nov 22, 15:29 UTC it is #10, holding steady at #10 over the last 6 checks.

What is the highest rank EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning reached?

#7 on Hugging Face · Daily papers, on Nov 20, 11:29 UTC. Trendoday checks this list every 120 minutes.

How long has EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning been trending?

It was first seen on Nov 20, 2026 and has been on the list on 3 days (30 checks) since.