AI Paper Atlas

Research map / Video / Video-language understanding

HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics

Gueter Josmy Faure, Jia-Fong Yeh, Min-Hung Chen, Hung-Ting Su, Shang-Hong Lai, Winston H. Hsu

ICCV 2025 · Video › Video-language understanding · approach: Long video understanding · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace MA-LMM memory bank with ECOMA-LMM · MovieChat-1k (zero-shot, plug-in)accuracy: 73.3 -> 76.7Improved
replace MA-LMM memory bank with ECOMA-LMM · MovieChat-1k (zero-shot, plug-in)inference time: 1 -> 0.569 (-43%)Improved
add SeTR to MA-LMMMA-LMM · MovieChat-1k (zero-shot, plug-in)accuracy: 73.3 -> 77.1Improved
add SeTR to MA-LMMMA-LMM · MovieChat-1k (zero-shot, plug-in)inference time: +1.5%No clear effect
integrate ECO into LongVA and LLaVA-OneVisionLongVA, LLaVA-OneVision · VideoMME and MovieChat-1klatency: 30% and 35% reductionImproved
add SeTR on top of ECOLongVA, LLaVA-OneVision · VideoMME and MovieChat-1kaccuracy: +0.37%Improved
add positional encoding before ECO (ablation)HERMES · MovieChat-1k (zero-shot, global)accuracy: 77.3 -> 78.6Improved
add SeTR (ablation)HERMES · MovieChat-1k (zero-shot, global)accuracy: 5% drop in accuracy when removedImproved
use ECO update strategy instead of random or FIFO retention (ablation)HERMES · MovieChat-1k (zero-shot, global)accuracyImproved
use hierarchical Q-Former instead of flat frame or video Q-Former (ablation)HERMES · Breakfastaccuracy: 95.2%Improved
use ECO instead of ToMe and MA-LMM memory (ablation)HERMES · MovieChat-1k (zero-shot, global)accuracy: 78.6% vs 13.8% above ToMe, 5.3% above MA-LMMImproved
increase input frames from 40 to 1000 (ablation)HERMES · MovieChat-1k (zero-shot, global)accuracy: 77.6% -> 76.7%Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy