AI Paper Atlas

Research map / Video / Video-language understanding

Enhancing Partially Relevant Video Retrieval with Hyperbolic Learning

Jun Li, Jinpeng Wang, Chaolei Tan, Niu Lian, Long Chen, Yaowei Wang, Min Zhang, Shu-Tao Xia, Bin Chen

ICCV 2025 · Video › Video-language understanding · approach: Text-video retrieval · 9 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 gaze frame-level branch (ablation)HLFormer · ActivityNet CaptionsSumR: 146.1 -> 154.9Improved
add gaze frame-level branch (ablation)HLFormer · TVRSumR: 178.3 -> 187.7Improved
add glance clip-level branch (ablation)HLFormer · ActivityNet CaptionsSumR: 137.2 -> 154.9Improved
add glance clip-level branch (ablation)HLFormer · TVRSumR: 166.1 -> 187.7Improved
add L_div and L_pop to similarity loss (ablation)HLFormer · ActivityNet CaptionsSumR: 149.1 -> 154.9Improved
add L_div and L_pop to similarity loss (ablation)HLFormer · Charades-STASumR: 75.3 -> 78.7Improved
add query diverse loss L_div (ablation)HLFormer · Charades-STASumR: 76.4 -> 78.7Improved
add partial order preservation loss L_pop (ablation)HLFormer · ActivityNet CaptionsSumR: 154.0 -> 154.9Improved
add partial order preservation loss L_pop (ablation)HLFormer · TVRSumR: 186.8 -> 187.7Improved
use MAIM instead of mean pooling for aggregation (ablation)HLFormer · ActivityNet CaptionsSumR: 150.2 -> 154.9Improved
use MAIM instead of concat+linear aggregation (ablation)HLFormer · TVRSumR: 186.6 -> 187.7Improved
use concat+linear instead of mean pooling aggregation (ablation)HLFormer · ActivityNet CaptionsSumR: 150.2 -> 153.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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