AI Paper Atlas

Research map / Video / Video-language understanding

EthoCLIP: Ontology-Enhanced Video-Language Pretraining for Animal Behavior Understanding

Yinuo Jing, Jinyan Wu, Zixi Yang, Kongming Liang, Xiatian Zhu, Zhanyu Ma

CVPR 2026 · Video › Video-language understanding · approach: Long video understanding

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 ontology semantic embedding (labels+synonyms+definitions) (ablation)X-CLIP · AnimalBand test set (behavior classification)overall mAP: 61.20 -> 62.54Improved
add ontology-aware graph modeling (ablation)X-CLIP · AnimalBand test set (behavior classification)overall mAP: 61.20 -> 62.25Improved
combine OSE and OAGM (ablation)EthoCLIP · AnimalBand test set (behavior classification)overall mAP: 62.54 -> 62.98Improved
use OSE weighted embedding instead of concatenation (ablation)EthoCLIP · AnimalBand test set (behavior classification)overall mAP: 61.40 -> 62.54Improved
use OSE instead of LLM keyword extraction (ablation)EthoCLIP · AnimalBand test set (behavior classification)overall mAP: 61.92 -> 62.54Improved
use 2 hops instead of 1 or 3 in graph attention (ablation)EthoCLIP · AnimalBand test set (behavior classification)overall mAP: 61.93 -> 62.98 (1 hop), 62.23 (3 hops)Improved
pretrain on AnimalBand instead of directly merged labels (ablation)X-CLIP · Transfer mean (Panda, SheepActivity, ChimpACT)mean score: 69.04 -> 74.26Improved
pretrain on AnimalBand instead of Kinetics-400 (ablation)X-CLIP · Transfer meanmean score: 64.22 -> 74.26Improved
use ontology-enhanced EthoCLIP over X-CLIPAnimalBand-pretrained · Transfer meanmean score: 74.26 -> 78.11Improved
partially unfreeze temporal transformer and prompting modules (ablation)EthoCLIP · Transfer meanmean score: 78.11 -> 87.72Improved
use EthoCLIP over X-CLIP on tail labelsEthoCLIP · AnimalBand test set (behavior classification)tail mAP: 50.36 -> 53.27Improved
use 40% of AnimalBand pretraining data (ablation)EthoCLIP · Panda (transfer)Acc@1: 84.80 -> 72.00 (40%)Mixed

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