AI Paper Atlas

Research map / Video / Video-language understanding

Aligning Effective Tokens with Video Anomaly in Large Language Models

Yingxian Chen, Jiahui Liu, Ruidi Fan, Yanwei Li, Chirui Chang, Shizhen Zhao, Wilton W. T. Fok, Xiaojuan Qi, Yik-Chung Wu

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 4 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
add Spatial Effective Token Selection (SETS) without fine-tuning (ablation)LLaMA-VID baseline · UCF-CrimeTotal Acc.: 14.83 -> 24.83Improved
add Temporal Effective Tokens (TETG) without fine-tuning (ablation)LLaMA-VID baseline · UCF-CrimeTotal Acc.: 14.83 -> 23.79Improved
add TETG on top of SETS, no fine-tuning (ablation)VA-GPT · UCF-CrimeTotal Acc.: 24.83 -> 25.12Improved
add TETG on top of SETS, stage two (ablation)VA-GPT · UCF-CrimeTemporal Acc.: 31.60 -> 35.00Improved
add anomaly video fine-tuning (stage one) (ablation)VA-GPT · UCF-CrimeTotal Acc.: 25.12 -> 27.50Improved
add stage two fine-tuning with SETS (ablation)VA-GPT · UCF-CrimeTotal Acc.: 27.50 -> 30.69Improved
fine-tune on UCF instruct-following dataLLaMA-VID · UCF-CrimeTotal Acc.: 14.83 -> 23.10Improved
fine-tune on UCF instruct-following dataVideo-ChatGPT · UCF-CrimeTotal Acc.: 24.13 -> 26.23Improved
fine-tune on UCF instruct-following dataVA-GPT · UCF-CrimeTotal Acc.: 25.12 -> 30.69Improved
raise SETS sample rate K from 0.5 to 0.9 (ablation)VA-GPT · UCF-CrimeTotal Acc.: 30.69 -> 27.27Hurt
lower SETS sample rate K from 0.5 to 0.1 (ablation)VA-GPT · UCF-CrimeTotal Acc.: 30.69 -> 23.61Hurt
raise SETS sample rate K from 0.5 to 0.7 (ablation)VA-GPT · UCF-CrimeTemporal Acc.: 35.00 -> 31.23Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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