AI Paper Atlas

Research map / Video / Video-language understanding

Video OWL-ViT: Temporally-consistent Open-world Localization in Video

Georg Heigold, Matthias Minderer, Alexey Gritsenko, Alex Bewley, Daniel Keysers, Mario Lučić, Fisher Yu, Thomas Kipf

ICCV 2023 · Video › Video-language understanding · approach: Long video understanding · 13 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 end-to-end video decoder instead of appearance-matching tracking-by-detection (ablation)OWL-ViT · TAO-OW unknownOWTA: 31.0 -> 45.4Improved
add transformer decoder to OWL-ViT (encoder-only to enc-dec) (ablation)OWL-ViT L/14 · LVIS rareAP rare: 31.8 -> 28.9Hurt
train on 4-frame clips instead of 2-frame clips (ablation)Video OWL-ViT · TAO-OW unknownOWTA: 35.2 -> 45.3Improved
extend clip length from 4 to 6 frames (ablation)Video OWL-ViT · TAO-OW unknownOWTA: 45.3 -> 45.4No clear effect
train on pseudo-videos from images instead of only real videos (ablation)Video OWL-ViT · TAO-OW unknownOWTA: 33.9 -> 45.9Improved
combine real and pseudo-videos instead of pseudo-videos only (ablation)Video OWL-ViT · TAO-OW known vs unknownOWTA: known 56.9 -> 59.0; unknown 45.9 -> 45.4Mixed
add score calibration (per-track objectness threshold) (ablation)Video OWL-ViT · TAO-OW unknown short tracksOWTA: 12.5 -> 22.2Improved
add temporal video mosaic augmentation (ablation)Video OWL-ViT · TAO-OW known short tracksOWTA: 26.1 -> 31.3Improved
increase inference frame rate from 1 to 4 FPS (ablation)Video OWL-ViT · TAO-OWOWTA: known 59.0 -> 61.1; unknown 45.4 -> 46.1Improved
pre-train whole Enc-dec model on detection before video training (ablation)Video OWL-ViT · TAO-OWOWTANo clear effect

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