Pith. sign in

REVIEW 6 cited by

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.12496 v2 pith:6QI2M25I submitted 2025-03-16 cs.CV

Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?

classification cs.CV
keywords samplinglsdbenchlvlmsaddressbenchmarkchallengesdensedensity
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The rise of Large Vision-Language Models (LVLMs) has significantly advanced video understanding. However, efficiently processing long videos remains a challenge due to the ``Sampling Dilemma'': low-density sampling risks missing critical information, while high-density sampling introduces redundancy. To address this issue, we introduce LSDBench, the first benchmark designed to evaluate LVLMs on long-video tasks by constructing high Necessary Sampling Density (NSD) questions, where NSD represents the minimum sampling density required to accurately answer a given question. LSDBench focuses on dense, short-duration actions to rigorously assess the sampling strategies employed by LVLMs. To tackle the challenges posed by high-NSD questions, we propose a novel Reasoning-Driven Hierarchical Sampling (RHS) framework, which combines global localization of question-relevant cues with local dense sampling for precise inference. Additionally, we develop a lightweight Semantic-Guided Frame Selector to prioritize informative frames, enabling RHS to achieve comparable or superior performance with significantly fewer sampled frames. Together, our LSDBench and RHS framework address the unique challenges of high-NSD long-video tasks, setting a new standard for evaluating and improving LVLMs in this domain. Our benchmark and evaluation codes has been released at: https://github.com/dvlab-research/LSDBench

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. How Well Can Your Video Model Remember? Measuring Memory-Budget Trade-offs in Long Video Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    Fits a model where logit-accuracy scales linearly in log frame budget B with distance-dependent exponent α(D) that decays log-linearly with temporal distance D, based on 155k binary predictions across ten models.

  2. Video-Zero: Self-Evolution Video Understanding

    cs.CV 2026-05 unverdicted novelty 6.0

    Video-Zero is an annotation-free Questioner-Solver co-evolution framework that centers self-evolution on temporally localized evidence to improve video VLMs.

  3. Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

    cs.LG 2026-05 unverdicted novelty 6.0

    Uni-OPD unifies on-policy distillation across LLMs and MLLMs with dual-perspective strategies that promote student exploration and enforce order-consistent teacher supervision based on outcome rewards.

  4. Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe

    cs.LG 2026-05 conditional novelty 6.0

    Uni-OPD improves on-policy distillation via student-side data balancing for informative rollouts and teacher-side outcome-guided margin calibration that restores order consistency with rewards.

  5. Mitigating Object Hallucinations via Sentence-Level Early Intervention

    cs.CV 2025-07 conditional novelty 6.0

    SENTINEL reduces MLLM object hallucinations by over 90% via sentence-level early intervention with detector-bootstrapped preference data and C-DPO loss, outperforming prior SOTA on hallucination and capability benchmarks.

  6. EgoSelf: From Memory to Personalized Egocentric Assistant

    cs.CV 2026-04 unverdicted novelty 5.0

    EgoSelf uses graph-based memory of user interactions to derive personalized profiles and predict future behaviors for egocentric assistants.