AI Paper Atlas

Research map / Video / Video-language understanding

Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos

Bingbin Liu, Serena Yeung, Edward Chou, De-An Huang, Li Fei-Fei, Juan Carlos Niebles

ECCV 2018 · Video › Video-language understanding · approach: Long video understanding · 67 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
use TMN modular compositional network instead of MCNMCN · DiDeMo RGBRank@5: 44.82 -> 72.97Improved
use TMN instead of MCNMCN · DiDeMo RGBRank@1: 13.10 -> 18.71Improved
use TMN instead of MCNMCN · DiDeMo FlowRank@1: 18.35 -> 19.90Improved
use TMN instead of MCNMCN · DiDeMo FuseRank@1: 19.88 -> 22.92Improved
use TMN instead of MCNMCN · DiDeMo Fusemean IoU: 33.51 -> 35.17Improved
add combine attention instead of max pooling (ablation)TMN const + rank loss · DiDeMo intra-video (Fuse)Rank@1: 21.89 -> 22.92Improved
add combine attention instead of max pooling (ablation)TMN const + rank loss · DiDeMo intra-video (Fuse)Rank@5: 75.69 -> 76.08Improved
use ranking loss instead of BCE loss (ablation)TMN const + attention · DiDeMo intra-video (Fuse)Rank@1: 21.60 -> 22.92Improved
use ranking loss instead of BCE loss (ablation)TMN dep + attention · DiDeMo intra-video (Fuse)Rank@1: 20.41 -> 21.67Improved
use constituency parser instead of dependency parser (ablation)TMN attention + rank loss · DiDeMo intra-video (Fuse)Rank@1: 21.67 -> 22.92Improved
use constituency parser instead of dependency parser (ablation)TMN attention + rank loss · DiDeMo intra-video (Fuse)mean IoU: 33.94 -> 35.17Improved
add compositional tree structure (vs MCN, no tree) (ablation)TMN · DiDeMo intra-video (Fuse)Rank@5: 62.39 -> 75.69Improved

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