AI Paper Atlas

Research map / Video / Video-language understanding

ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance

Hyojin Park, Yi Li, Janghoon Cho, Sungha Choi, Jungsoo Lee, TAOTAO JING, shuai zhang, Munawar Hayat, Dashan Gao, Ning Bi, Fatih Porikli

ECCV 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 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
person-centric tracking and retrieval before the video LLM, versus feeding the full video (ablation)VideoLLaMA3-7B · ForeSeaQA-MMaccuracy / temporal IoU: 61.6 -> 64.6 acc; 10.9 -> 12.5 IoUImproved
crop frames to the tracked bounding box (ablation)ForeSea · ForeSeaQA-MMaccuracy: 64.6 -> 61.3Hurt
add bbox coordinates as text in prompt (ablation)ForeSea · ForeSeaQA-MMaccuracy / IoU: 64.6 -> 65.4 acc; 12.5 -> 13.8 IoUImproved
add visual bbox overlay on top of coordinates (ablation)ForeSea · ForeSeaQA-MMaccuracy / IoU: 65.4 -> 64.5 acc; 13.8 -> 12.1 IoUNo clear effect
increase retrieved tracks K from 3 to 5 (ablation)ForeSea · ForeSeaQA-MMaccuracy / IoU: 65.4 -> 66.4 acc; 13.8 -> 12.1 IoUMixed
index global frames instead of person clips (ForeSea-Global) (ablation)ForeSea · ForeSeaQA-MMsearch accuracy / IoU: search 60.5 -> 57.5 acc, 17.6 -> 14.1 IoU; avg IoU 13.8 -> 16.1Mixed
combine person and global retrieval (ForeSea-Hybrid) (ablation)ForeSea · ForeSeaQA overalltemporal IoU: 13.6 -> 18.4Improved
swap GCL encoder for SigLIP, SigLIP2 or EVA-CLIP (ablation)ForeSea · ForeSeaQA overallaccuracy: 66.0 vs 65.5 / 65.8 / 64.8No clear effect
ForeSea framework versus VideoRAG with the same VideoLLaMA3 backbone (ablation)VideoLLaMA3-7B · ForeSeaQA overalltemporal IoU: 9.9 -> 18.4Improved
replace video with predicted dense captions (ablation)ForeSea · ForeSeaQA overallaccuracy: 66.0 -> 52.3Hurt
use ForeSea on open-domain VideoMME instead of VideoLLaMA3 aloneVideoLLaMA3-7B · VideoMMEaccuracy: 66.2 -> 65.6No clear effect

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