AI Paper Atlas

Research map / Video / Video-language understanding

Learning Trajectory-Word Alignments for Video-Language Tasks

Xu Yang, Zhangzikang Li, Haiyang Xu, Hanwang Zhang, Qinghao Ye, Chenliang Li, Ming Yan, Yu Zhang, Fei Huang, Songfang Huang

ICCV 2023 · Video › Video-language understanding · approach: Video-language pretraining · 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
replace patch-to-word attention with trajectory-to-word (T2W) attention (ablation)TW-BERT cross-modal encoder · MSRVTT zero-shotR@5: 46.4 -> 50.0Improved
replace P2W with T2W attention (ablation)TW-BERT · DiDeMo zero-shotR@1: 26.6 -> 28.4Improved
replace P2W with T2W attention (ablation)TW-BERT · MSVD-QAaccuracy: 47.4 -> 48.2Improved
use T2W trajectory attention instead of mean-pooling trajectory over time (ablation)TW-BERT · DiDeMo zero-shotR@1: 27.4 -> 28.4Improved
place frame-selector layers deeper ([6,12] instead of [2,4]) (ablation)HFS · MSRVTT fine-tuningR@1: 36.7 -> 38.4Improved
use HFS (F@20-14-8) rather than uniform 8 frames (ablation)TW-BERT fine-tuning · MSRVTT fine-tuningR@1: 38.1 -> 38.4Improved
use HFS (F@32-24-16) rather than uniform 16 frames (ablation)TW-BERT fine-tuning · MSVD-QAaccuracy: 48.2 -> 48.5Improved
increase sampled frames from 8-6-4 to 20-14-8 with HFS (ablation)TW-BERT · MSRVTT fine-tuningR@1: 37.5 -> 38.4Improved
TW-BERT with 5.5M pretrain pairs versus VIOLET with 186MTW-BERT · MSRVTT-QAaccuracy: 43.9 -> 43.6Hurt

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