AI Paper Atlas

Research map / Video / Video-language understanding

Context-Aware Academic Emotion Dataset and Benchmark

Luming Zhao, Jingwen Xuan, Jiamin Lou, Yonghui Yu, Wenwu Yang

ICCV 2025 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 3 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 full-frame context sequence alongside face sequence (ablation)face-only CLIP-CAER · RAER testUAR (%): 61.19 -> 68.00Improved
replace face sequence with full-frame sequence only (ablation)face-only CLIP-CAER · RAER testUAR (%): -3.16%Hurt
add context input (ablation)CLIP-CAER · RAER distraction classaccuracy (%): 51.43 -> 70.48Improved
add learnable prompt to class-name prompt (ablation)CLIP-CAER · RAER testUAR (%): 62.14 -> 64.26Improved
use descriptive prompts instead of class names (ablation)CLIP-CAER · RAER testUAR (%): 64.26 -> 65.43Improved
add learnable prompt to descriptors (ablation)CLIP-CAER · RAER testUAR (%): 65.43 -> 68.00Improved
increase temporal encoder layers from 1 to 2 (ablation)CLIP-CAER · RAER testUAR (%): 68.00 -> 64.78Hurt
increase temporal encoder layers from 1 to 3 (ablation)CLIP-CAER · RAER testUAR (%): 68.00 -> 64.29Hurt
use 4 instead of 8 learnable prompt tokens (ablation)CLIP-CAER · RAER testUAR (%): 68.00 -> 65.54Hurt
use 12 or 16 instead of 8 learnable prompt tokens (ablation)CLIP-CAER · RAER testUAR (%): 68.00 -> 64.15 (12); 64.27 (16)Hurt
add context information (ablation)CLIP-CAER · CAERUAR (%): 75.36 -> 81.77Improved
fine-tune RAER-trained model on JuniorRAERCLIP-CAER · JuniorRAER testUAR (%): 41.43 -> 61.20Improved

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