AI Paper Atlas

Research map / Video / Video-language understanding

Exploring Temporal Concurrency for Video-Language Representation Learning

Heng Zhang, Daqing Liu, Zezhong Lv, Bing Su, Dacheng Tao

ICCV 2023 · Video › Video-language understanding · approach: Long video understanding · 6 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 process-wise regularization term (PRT) (ablation)TCP · MSR-VTT paragraph-to-video retrievalR@1: 16.4 -> 26.8Improved
add PRT regularization (ablation)TCP · MSR-VTT VQAaccuracy: 51.2 -> 80.8Improved
add PRT regularization (ablation)TCP · ActivityNet video moment retrievalR@0.7 (n=1): 18.6 -> 28.4Improved
use PRT instead of IDM regularization (ablation)TCP · MSR-VTT paragraph-to-video retrievalR@1: 24.2 -> 26.8Improved
use NCE instead of PRT regularization (ablation)TCP · MSR-VTT paragraph-to-video retrieval and ActivityNet VMRR@1 / R@0.7: 26.4 vs 26.8 (PVR); 27.8 vs 28.4 (VMR)No clear effect
use NCE instead of PRT regularization (ablation)TCP · MSR-VTT VQAaccuracy: 80.8 -> 81.2Improved
increase pre-training pairs from 1.5M to 8.5M (ablation)TCP · MSR-VTT paragraph-to-video retrievalR@1: about 4% gain with 7M expansionImproved
model video-text as temporal concurrent processes with soft-DTW vs prior methodsTCP vs HD-VILA · MSR-VTT 1K test (fine-tuning)R@10: 76.4 vs 78.0 (HD-VILA); R@1 38.0 vs 35.6Mixed

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