AI Paper Atlas

Research map / Video / Video-language understanding

Temporal Saliency Query Network for Efficient Video Recognition

Boyang Xia, Zhihao Wang, Wenhao Wu, Haoran Wang, Jungong Han

ECCV 2022 · Video › Video-language understanding · approach: Dense video captioning · 22 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 class-specific attention and classifier (CS+CS) over class-agnostic (ablation)TSQNet VQM · ActivityNet (ResNet-101)mAP (%): 74.0 -> 74.7Improved
use class-specific classifier together with class-specific attention (ablation)TSQNet VQM · ActivityNet (ResNet-101)mAP (%): 68.7 -> 74.7Improved
fuse VQM and TQM without interaction losses (ablation)TSQNet · ActivityNet (ResNet-101)mAP (%): 72.0 -> 74.9 (TQM), 74.6 -> 74.9 (VQM)Improved
add both cross-modal interaction losses (L t->v and L v->t) (ablation)TSQNet · ActivityNet (ResNet-101)mAP (%): 74.9 -> 75.3Improved
add L v->t loss alone (ablation)TQM · ActivityNet (ResNet-101)mAP (%): 72.0 -> 72.7Improved
use Bert with top-10 object scores instead of Word2Vec (ablation)TQM · ActivityNet (ResNet-101)mAP (%): 71.2 -> 72.1Improved
keep only top-10 object categories instead of all (ablation)TQM with Bert · ActivityNet (ResNet-101)mAP (%): 71.4 -> 72.1Improved
initialize visual TSQ embedding with prototypes instead of random (ablation)VQM · ActivityNet (ResNet-101)mAP (%): 73.8 -> 74.7Improved
initialize textual TSQ embedding with Bert embedding instead of random (ablation)TQM · ActivityNet (ResNet-101)mAP (%): 71.6 -> 72.1Improved
add self-attention layer over TSQ queries (ablation)TSQNet VQM · ActivityNet (ResNet-101)mAP (%): 74.7 -> 74.5Hurt
use 8 heads instead of 1 in cross-attention (ablation)TSQNet VQM · ActivityNet (ResNet-101)mAP (%): 74.7 -> 73.7Hurt
use 2 layers instead of 1 in cross-attention (ablation)TSQNet VQM · ActivityNet (ResNet-101)mAP (%): 74.7 -> 73.4Hurt

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