A3Bench: an audience-aligned multilingual benchmark for video audience insights understanding

Yi-Ming Lei Guozhen Peng Ze-Ming Liu Huida Qiu Hai-Tao Leng Shaoguo Liu Tingting Gao Qingjie Liu Annan Li Yunhong Wang

Aug 2026 · Frontiers of Computer Science · Vol 20 · 0 citations · 22 references

Computer Science

TL;DR

A3Bench is introduced, an audience-aligned benchmark for evaluating video audience insights with large-scale videos and high-quality multilingual comments and Cognition Interaction of Thought (CIoT), a structured reasoning framework that emulates key aspects of cognitive processes is proposed.

DOI Semantic Scholar

View source

Similar papers

#natural language process... Preprint Aug 2026

DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos

DVBench is introduced, a benchmark for evaluating MLLMs on data videos, a storytelling medium that integrates dynamic charts with structured narratives, and decompose data video understanding into five dimensions, identifying two notable phenomena.

Bomiao Wang, Zekai Shao, Jiexiang Lan et al. · 0 citations

#natural language process... Preprint Aug 2026

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

This work presents AudioChaps, a post-training framework for aligning end-to-end LALMs for this task via Group Relative Policy Optimization (GRPO) guided by Chain-of-Thought (CoT) reasoning, and demonstrates that GRPO-trained LALMs can reliably transform unstructured auditory streams into navigable, structured media.

Tony Alex, Wish Suharitdamrong, Sara Atito et al. · 0 citations

Preprint Sep 2026

CinematicVQA: Benchmarking Film-Grammar Reasoning in Large Vision-Language Models

CinematicVQA is introduced, the first-of-its-kind benchmark for cinematic video understanding that goes beyond technique recognition to evaluate film-grammar reasoning, utilizing the introduced Cinematic Scene Graph (CSG), a structured representation that links filming techniques to their perceptual effects and narrati...

Shuo Xing, Pooja Verlani, Balu Adsumilli et al. · 0 citations

Preprint Sep 2026

Not Another Text Benchmark: Putting the"Visual"Back in Visual Question Answering for Large Video Models

Three new vision-centric evaluation benchmarks in temporal frame retrieval, video future prediction, and causal memory distortion are introduced, all designed around evaluating visual understanding capabilities in large video models, which complements the existing approaches to evaluate video understanding in frontier...

Rwiddhi Chakraborty, Y. Wang, Cheng Zhang et al. · 0 citations

Preprint Aug 2026

Reasoning for Social Audio-Visual Question Answering: Where Do We Stand?

It is revealed that substantial priors can be learned solely from the text modality and that using a textual caption instead of the video yields performance on par with Vanilla SFT, revealing the limitations of current MLLMs when it comes to social understanding.

Koen P. de Vries, Xavier Alameda-Pineda, Estefanía Talavera et al. · 0 citations

Preprint Aug 2026

Beyond Frame Selection: Rethinking Long-Video Understanding with MLLMs

VideoRouter (VR) is proposed that rethinks long-video understanding as coordinating complementary evidence views rather than selecting a single subset of frames, and introduces a verification-guided router to determine which view is better supported by the selected evidence and select the final answer.

Ziling Huang, Yuki M. Asano, Shin'ichi Satoh · 0 citations