AI Paper Atlas

Research map / Video / Video-language understanding

CroPS: Improving Dense Retrieval with Cross-Perspective Positive Samples in Short-Video Search

Ao Xie, Jiahui Chen, Quanzhi Zhu, Xiaoze Jiang, Zhiheng Qin, Enyun Yu, Han Li

AAAI 2026 · Video › Video-language understanding · approach: Text-video retrieval · 0 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 query-level positive augmentation (ablation)dense retriever baseline · CPSQA CTRecall@100: 59.6 -> 63.3Improved
add query-level positive augmentation (ablation)dense retriever baseline · CPSQA QRRecall@100: 33.0 -> 36.1Improved
add system-level positive augmentation (ablation)CroPS with query-level aug. · CPSQA CTRecall@100: 63.3 -> 65.7Improved
add system-level positive augmentation (ablation)CroPS with query-level aug. · CPSQA QRRecall@100: 36.1 -> 37.4Improved
add world-knowledge LLM positives (ablation)CroPS with query and system aug. · CPSQA CTRecall@100: 65.7 -> 69.1Improved
add world-knowledge LLM positives (ablation)CroPS with query and system aug. · CPSQA QRRecall@100: 37.4 -> 40.1Improved
use hierarchical labels with H-InfoNCE instead of binary labels (ablation)CroPS · CPSQA CTRecall@100: 59.9 -> 69.1Improved
use hierarchical labels with H-InfoNCE instead of binary labels (ablation)CroPS · CPSQA QRRecall@100: 32.1 -> 40.1Improved
give query-level positives the highest label 5 instead of 4 (ablation)CroPS · CPSQA CTRecall@100: 67.1 -> 69.1Improved
give query-level positives the highest label 5 instead of 4 (ablation)CroPS · CPSQA QRRecall@100: 38.4 -> 40.1Improved
use H-InfoNCE instead of InfoNCE (ablation)CroPS · CPSQA trainingtraining time: 178h -> 88hImproved
use H-InfoNCE instead of Softmax-CE (ablation)CroPS · CPSQA CTRecall@100: 65.3 -> 69.1Improved

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