AI Paper Atlas

Research map / Video / Video-language understanding

Agentic Video Summarization via Self-Reflecting Multimodal Understanding

Miaotian Guo, Shuguang Dou, Yin Li, Aidong Men, Dongsheng Jiang

CVPR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding

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 V2I alignment of video and image embeddings in the Summarizer (ablation)CSTA baseline · SumMeKendall tau: 0.230 -> 0.265Improved
add V2I alignment (ablation)CSTA baseline · TVSumSpearman rho: 0.232 -> 0.278Improved
add Verifier and Reflector on top of V2I Summarizer (ablation)AgenticVS · SumMeKendall tau: 0.265 -> 0.274Improved
add Verifier and Reflector on top of V2I Summarizer (ablation)AgenticVS · TVSumKendall tau: 0.215 -> 0.220Improved
align video to image space (V2I) instead of image to video (I2V) (ablation)V2I Alignment · SumMeKendall tau: 0.238 -> 0.265Improved
use temporal attention pooling instead of mean pooling (ablation)V2I Alignment · SumMeKendall tau: 0.243 -> 0.265Improved
fuse image and video encoders with alignment instead of using either alone (ablation)Summarizer · SumMeKendall tau: 0.228 (image only), 0.220 (video only) -> 0.265Improved
directly concatenate image and video embeddings instead of aligning (ablation)Summarizer · SumMeKendall tau: 0.228 -> 0.230No clear effect
use CLIP similarity to MLLM-generated summary caption instead of MLLM direct scoring (ablation)Reflector · SumMe (train-free)Kendall tau: 0.073 -> 0.116Improved
use AgenticVS instead of LLMVSLLMVS · SumMeKendall tau: 0.253 -> 0.274Improved
use Verifier without Reflector (ablation)AgenticVS · SumMe and TVSumKendall tauNo clear effect

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