AI Paper Atlas

Research map / Video / Video segmentation and tracking

TF-Blender: Temporal Feature Blender for Video Object Detection

Yiming Cui, Liqi Yan, Zhiwen Cao, Dongfang Liu

ICCV 2021 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 194 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 temporal relation module (ablation)FGFA · ImageNet VID val (FGFA)mAP: 77.8 -> 78.5Improved
add feature adjustment module (ablation)FGFA · ImageNet VID val (FGFA)mAP: 77.8 -> 78.1Improved
add feature blender module (ablation)FGFA · ImageNet VID val (FGFA)mAP: 77.8 -> 78.3Improved
add all three modules (ablation)FGFA · ImageNet VID val (FGFA)mAP: 77.8 -> 79.3Improved
add feature blender to temporal relation (ablation)FGFA + temporal relation · ImageNet VID val (FGFA)mAP: 78.5 -> 78.8Improved
use f_i, f_j, f_i - f_j, f_j - f_i as relation function instead of f_i, f_j (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 78.3 -> 79.3Improved
use f_i + f_j as relation function instead of f_i - f_j (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 78.6 -> 77.9Hurt
add f_i + f_j to f_i, f_j relation function (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 78.3 -> 78.1Hurt
add f_j - f_i to f_i, f_j, f_i - f_j (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 78.9 -> 79.3Improved
increase mini-network from 1 to 3 conv layers (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 78.8 -> 79.2Improved
increase mini-network from 3 to 4 conv layers (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 79.2 -> 79.1Hurt
use 3x3 instead of 1x1 kernels in mini-network (ablation)FGFA + TF-Blender · ImageNet VID val (FGFA)mAP: 79.2 -> 79.3No clear effect

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