AI Paper Atlas

Research map / Video / Video segmentation and tracking

Day2Dark: Pseudo-Supervised Activity Recognition Beyond Silent Daylight

Yunhua Zhang, Hazel Doughty, Cees G. M. Snoek

IJCV 2024 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 5 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 pseudo-supervised day2dark learning (ablation)darkness-adaptive recognizer · EPIC-Kitchens (dark)top-1 accuracy: 29.3 -> 34.2Improved
add day2dark-mix finetuning (ablation)darkness-adaptive recognizer · EPIC-Kitchens (dark)top-1 accuracy: 34.2 -> 35.6Improved
add pseudo-supervised learning to visual-only model (ablation)visual encoder · Kinetics-Sound (dark)top-1 accuracy: 77.2 -> 78.5Improved
add darkness probe and adaptive encoder (ablation)vanilla multi-modal transformer · EPIC-Kitchens (dark)top-1 accuracy: 29.8 -> 31.8Improved
add adaptive prompts (ablation)recognizer · EPIC-Kitchens (dark)top-1 accuracy: 31.8 -> 34.3Improved
add adaptive classification heads (ablation)recognizer · EPIC-Kitchens (dark)top-1 accuracy: 34.3 -> 35.6Improved
add a second auxiliary task (both video-text matching and sound localization) (ablation)pseudo-supervised learning · EPIC-Kitchens (dark), auxiliary taskstop-1 accuracy: 33.3 -> 35.6Improved
use auxiliary-task predictions of target task as pseudo labels (ablation)pseudo-supervised learning · EPIC-Kitchens (dark)top-1 accuracy: 35.6 -> 30.4Hurt
use raw auxiliary predictions instead of autoencoder bottleneck (ablation)pseudo-supervised learning · EPIC-Kitchens (dark)top-1 accuracy: 35.6 -> 31.5Hurt
replace learned darkness probe with computed illuminance (ablation)recognizer · EPIC-Kitchens (dark)top-1 accuracy: -2.1%Hurt
increase lambda from 0.01 to 0.03 (ablation)pseudo-supervised learning · EPIC-Kitchens (dark), lambdatop-1 accuracy: 35.6 -> 35.2Hurt
use K=5 branches instead of K=1 (ablation)recognizer · EPIC-Kitchens (dark), branches Ktop-1 accuracy: 29.8 -> 35.6Improved

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