pith. sign in

Adard-key: Adaptive relevance-diversity keyframe sampling for long-form video understanding

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Adaptive Greedy Frame Selection for Long Video Understanding

cs.CV · 2026-03-20 · unverdicted · novelty 6.0 · 2 refs

A question-adaptive greedy frame selector combines SigLIP relevance and DINOv2 coverage under a submodular objective with a text classifier routing to preset trade-offs, yielding accuracy gains on MLVU especially at low frame budgets.

Swift Sampling: Selecting Temporal Surprises via Taylor Series

cs.CV · 2026-05-21 · unverdicted · novelty 5.0

Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Adaptive Greedy Frame Selection for Long Video Understanding cs.CV · 2026-03-20 · unverdicted · none · ref 18 · 2 links

    A question-adaptive greedy frame selector combines SigLIP relevance and DINOv2 coverage under a submodular objective with a text classifier routing to preset trade-offs, yielding accuracy gains on MLVU especially at low frame budgets.

  • Swift Sampling: Selecting Temporal Surprises via Taylor Series cs.CV · 2026-05-21 · unverdicted · none · ref 49

    Swift Sampling is a training-free frame selection method that uses Taylor expansions on video latent trajectories to pick temporally surprising frames, outperforming uniform sampling on long-video QA tasks.