AI Paper Atlas

Research map / Detection and segmentation / CNN features

Few-Shot Video Object Detection

Qi Fan, Chi-Keung Tang, Yu-Wing Tai

ECCV 2022 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors

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 RPN with Tube Proposal Network (TPN) (ablation)matching network (MN) · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 19.5 -> 23.2Improved
replace image-level MN with temporal matching network (TMN) (ablation)TPN · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 23.2 -> 26.4Improved
add label-smoothing regularization to TMN (ablation)TPN + TMN · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 26.4 -> 27.9Improved
add support classification module to TMN (ablation)TPN + TMN · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 26.4 -> 29.4Improved
combine LSR and SCM (TMN+) (ablation)TPN + TMN · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 26.4 -> 30.0Improved
use tube-based features instead of image-based features at inference (ablation)TMN+ model · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 25.8 -> 30.0Improved
add relation-network matching vs matching network on RPN (ablation)RPN · FSVOD-500 val (80 novel classes, full-way 5-shot)AP: 10.1 -> 19.5Improved
train on FSVOD-500 (more diverse classes) instead of FSYTV-40Ours · FSYTV-40 testAP: 14.6 -> 17.8Improved
use joint end-to-end training of video baselinesCenterTrack · FSVOD-500 testAP: 20.6 -> 22.7Improved
use joint end-to-end training of video baselinesFairMOT · FSVOD-500 testAP: 20.3 -> 23.1Improved
increase number of shots from 1 to 5 in 1-way evaluationOurs · FSVOD-500 valAP: 44.0 -> 46.5Improved
increase number of ways from 1 to 5 in 1-shot evaluationOurs · FSVOD-500 valAP: 44.0 -> 31.9Hurt

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