AI Paper Atlas

Research map / Video / Video-language understanding

SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding

Chang-Hsun Wu, Kai-Po Chang, Yu-Yang Sheng, Hung-Kai Chung, Kuei-Chun Wang, Yu-Chiang Frank Wang

CVPR 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 8 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
replace temporal homogenization with shuffled-frame negative (ablation)SEASON · temporal benchmark AVGaccuracy: 61.4 -> 55.0Hurt
replace temporal homogenization with average negative (ablation)SEASON · temporal benchmark AVGaccuracy: 61.4 -> 59.9Hurt
replace temporal homogenization with reverse negative (ablation)SEASON · temporal benchmark AVGaccuracy: 62.0 -> 58.8Hurt
add temporal negative on top of spatial negative (full SEASON) (ablation)SEASON · hallucination benchmarks AVGaccuracy: 63.7 -> 64.4Improved
add spatial negative to temporal negative (full SEASON) (ablation)SEASON · hallucination benchmarks AVGaccuracy: 66.2 -> 66.5Improved
add self-diagnostic combination vs temporal negative only (ablation)SEASON · EventHallusionaccuracy: 68.0 -> 66.0Hurt
add SEASON decodingQwen2.5-VL-7B · VidHallucaccuracy: 73.4 -> 78.7Improved
add SEASON decodingLLaVA-OV-7B · VidHalluc TSHaccuracy: 53.00 -> 77.50Improved
add SEASON decodingLLaVA-OV-7B · VidHalluc STHaccuracy: 63.65 -> 60.29Hurt
add SEASON decoding to 72B modelLLaVA-OV-72B · VidHallucaccuracy: 69.41 -> 71.46Improved
add SEASON decodingLLaVA-Video-7B · TempCompassaccuracy: 69.7 -> 71.1Improved
add SEASON decodingLLaVA-Video-7B · VideoMMEaccuracy: 53.0 -> 53.4No 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