AI Paper Atlas

Research map / Video / Video-language understanding

AdShot: Benchmarking Multimodal Large Language Models for Video Advertisement Clipping

Wen Xie, Om Rastogi, Sai S Rangoju, Gijs Overgoor, Yakov Bart, Sarah Ostadabbas

NeurIPS 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces AdShot, a benchmark evaluating multimodal large language models on shot selection for video ad clipping.

Problem

Advertisers must create multiple duration variants of video ads, a labor-intensive process; the ability of MLLMs to perform this specialized editorial task is unexplored.

Approach

A benchmark framing ad clipping as shot selection so MLLMs can be evaluated on this editorial task, rather than general video understanding.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add audio track to the model input (ablation)Qwen2.5-Omni 7B · AdShot (823 ad pairs, shot selection)F1: 0.585 -> 0.668Improved
add audio track to the model input (ablation)MiniCPM-o 2.6 8B · AdShot (823 ad pairs, shot selection)F1: 0.644 -> 0.669Improved
add audio track to the model input (ablation)Qwen2.5-Omni 7B · AdShot (823 ad pairs, shot selection)MDE (s): 7.75 -> 11.18Hurt
add audio track to the model input (ablation)MiniCPM-o 2.6 8B · AdShot (823 ad pairs, shot selection)Precision: 0.588 -> 0.581No clear effect
scale model up within familyQwen3-VL · AdShot (823 ad pairs, shot selection)F1: 0.576 -> 0.611Improved
scale model up (7B to 32B) / newer versionQwen family · AdShot (823 ad pairs, shot selection)F1: Qwen3-VL 8B 0.576 vs Qwen2.5-VL 7B 0.582Mixed
use larger modelLLaVA-OneVision 72B vs smaller MLLMs · AdShot (823 ad pairs, shot selection)F1: 0.464 (below random baseline 0.503)Hurt
compare MLLMs against random heuristic15 MLLMs · AdShot (823 ad pairs, shot selection)F1: 0.503 baseline; nine models above, six belowMixed
target ads with 6-10 shots versus fewer than 6video-only MLLMs · AdShot (823 ad pairs, shot selection)F1Improved
use high-recall model (Aria) instead of balanced modelAria 25.3B · AdShot (823 ad pairs, shot selection)MDE (s): 3.71 (Qwen3-VL 32B) -> 11.95Hurt

Experimental setup

Benchmarks: AdShot

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