AI Paper Atlas

Research map / Continual learning / Class-incremental

STSP: Spatial-Temporal Subspace Projection for Video Class-incremental Learning

Hao Cheng, SIYUAN YANG, Chong Wang, Joey Tianyi Zhou, Alex Kot, Bihan Wen

ECCV 2024 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 7 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 spatial-based gradient projection (SGP) in place of exemplar-based distillation (ablation)STSP with TSC · UCF101 (5x10 stages)accuracy: 71.50 -> 82.84Improved
add SGP to a model with no exemplars (ablation)linear classifier · UCF101 (5x10 stages)accuracy: 17.63 -> 77.66Improved
replace linear classifier with TSC (with SGP) (ablation)STSP · UCF101 (5x10 stages)accuracy: 77.66 -> 82.84Improved
replace linear classifier with TSC (with SGP) (ablation)STSP · UCF101 (2x25 stages)accuracy: 74.02 -> 79.25Improved
replace linear classifier with TSC (with exemplars) (ablation)exemplar-based distillation · UCF101 (5x10 stages)accuracy: 68.28 -> 71.50Improved
use TSC without SGP or exemplars (ablation)linear classifier baseline · UCF101 (5x10 stages)accuracy: 17.63 -> 8.78Hurt
use subspace basis size tau=8 instead of 16 (ablation)STSP TSC · UCF101 (5x10 stages)accuracy: 63.02 -> 82.84Improved
increase subspace basis size from 1 to 8 (ablation)STSP TSC · UCF101 (5x10 stages)accuracy: 66.75 -> 82.84Improved
STSP vs FrameMaker (exemplar-free vs exemplar-based)STSP · Something-Something V2 (10x9 stages)accuracy: 37.25 -> 69.68Improved
more incremental stages (2x25 instead of 5x10)STSP · UCF101accuracy: 82.84 -> 79.25Hurt

Later papers that compared with this method

1 later accepted paper reports STSP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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