AI Paper Atlas

Research map / Video / Video segmentation and tracking

DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video

Narek Tumanyan, Assaf Singer, Shai Bagon, Tali Dekel

ECCV 2024 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 50 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 pretrained DINOv2 features (vs training CNN from scratch without DINO) (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 71.4 -> 80.4Improved
predict residual with CNN Delta-DINO instead of LoRA fine-tuning DINOv2 (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 73.2 -> 80.4Improved
add DINO best-buddies loss (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 78.2 -> 80.4Improved
add prior preservation loss (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 79.2 -> 80.4Improved
add optical flow loss (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 78.3 -> 80.4Improved
add refined best-buddies and cycle-consistency losses (ablation)DINO-Tracker · TAP-Vid-DAVIS-480AJ: 63.2 -> 64.6Improved
refine DINO features with test-time training vs raw DINOv2 matchingDINOv2 · TAP-Vid-DAVIS-480delta_avg^x: 64.7 -> 80.4Improved
use DINOv2 layer 16 tokens rather than other layers/facets (ablation)raw DINOv2 tracking · TAP-Vid-DAVIS-480delta_avg^x: 59.9 -> 64.7Improved
train only on 50% of frames (every 2nd frame) (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 80.7 -> 80.6No clear effect
train only on 25% of frames (every 4th frame) (ablation)DINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 80.7 -> 79.1Hurt
combine test-time training with DINO prior vs OmnimotionDINO-Tracker · TAP-Vid-DAVIS-480delta_avg^x: 74.1 -> 80.4Improved

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