AI Paper Atlas

Research map / Video / Video-language understanding

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

WonJun Moon, Cheol-Ho Cho, Woojin Jun, Taeoh Kim, Inwoong Lee, Dongyoon Wee, Minho Shim, Jae-Pil Heo

ICCV 2025 · Video › Video-language understanding · approach: Text-video retrieval · 7 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 cross-modal mask reconstruction (ablation)prototype generator · TVR (CLIP L/14)SumR: 253.0 -> 254.2Improved
add uni-modal reconstruction (ablation)prototype model with cross-modal reconstruction · TVR (CLIP L/14)SumR: 254.2 -> 255.1Improved
add weak attention guidance via video mixing (ablation)prototype model with dual reconstruction · TVR (CLIP L/14)SumR: 255.1 -> 258.2Improved
add orthogonal prototype diversification loss (ablation)prototype model with guidance · TVR (CLIP L/14)SumR: 258.2 -> 259.2Improved
use 10 prototypes instead of 30 (ablation)Ours · TVR (CLIP L/14)SumR: 259.2 -> 252.9Hurt
use 20 prototypes instead of 30 (ablation)Ours · TVR (CLIP L/14)SumR: 259.2 -> 257.8Hurt
use 60 prototypes instead of 30 (ablation)Ours · TVR (CLIP L/14)SumR: 259.2 -> 260.2Improved
replace cross-attention-only generator with Perceiver (ablation)Ours · TVR (CLIP L/14)SumR: 259.2 -> 249.5Hurt
replace cross-attention-only generator with Slot-attention (ablation)Ours · TVR (CLIP L/14)SumR: 259.2 -> 253.8Hurt
use prototypes instead of GMMFormer local-clip modeling (ablation)GMMFormer · TVR (CLIP L/14)SumR: 243.2 -> 259.2Improved
use prototypes versus storing all clips (MS-SL) (ablation)MS-SL · TVR (CLIP L/14)Memory (MB): 1.01 -> 0.09Improved

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