AI Paper Atlas

Research map / Video / Video-language understanding

TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval

Yuqi Liu, Pengfei Xiong, Luhui Xu, Shengming Cao, Qin Jin

ECCV 2022 · Video › Video-language understanding · approach: Text-video retrieval · 166 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 token shift in layers 11-12 (25%) to baseline (ablation)CLIP-based baseline · MSR-VTT 1k-A (text-to-video)R@1: 45.4 -> 46.2; rsum 401.5 -> 406.2Improved
apply token shift to all layers 1-12 instead of only 11-12 (ablation)Token Shift · MSR-VTT 1k-A (text-to-video)R@1: 46.2 -> 42.8Hurt
apply token shift to layers 9-12 instead of 11-12 (ablation)Token Shift · MSR-VTT 1k-A (text-to-video)R@1: 46.2 -> 45.2Hurt
shift 12.5% or 50% of tokens instead of 25% (ablation)Token Shift · MSR-VTT 1k-A (text-to-video)R@1: 46.0 and 46.1 vs 46.2No clear effect
replace channel shift with token shift (ablation)Shift variants · MSR-VTT 1k-A (text-to-video)R@1: 45.6 -> 46.2Improved
replace [CLS] channel shift with token shift (ablation)Shift variants · MSR-VTT 1k-A (text-to-video)R@1: 45.8 -> 46.2Improved
add learned token selection (top-4) after token shift (ablation)TS2-Net · MSR-VTT 1k-A (text-to-video)R@1: 46.2 -> 47.0; rsum 406.2 -> 408.4Improved
use all 50 tokens instead of top-K selection (ablation)Token Selection · MSR-VTT 1k-A (text-to-video)R@1: 47.0 -> 45.8Hurt
replace learned selection with random selection of 4 tokens (ablation)Token Selection · MSR-VTT 1k-A (text-to-video)R@1: 47.0 -> 46.4Hurt
increase selected tokens from 4 to 8 (ablation)Token Selection · MSR-VTT 1k-A (text-to-video)R@1: 47.0 -> 46.4Hurt
apply inverted softmax at inferenceTS2-Net · MSR-VTT 1k-A (text-to-video)R@1: 47.0 -> 51.1Improved
TS2-Net vs CLIP4Clip on hard subset of small objects and subtle motionTS2-Net · MSR-VTT 1k-A hard subset (103 queries)R@1: 39.8 -> 79.6Improved

Later papers that compared with this method

10 later accepted papers report TS2-Net as a baseline in their results tables; 10 of them report a better number on most of the results they share with it.

2 more not listed.

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