Paper Detail

Video-Oasis: Rethinking Evaluation of Video Understanding

Geuntaek Lim, Sungjune Park, Jaeyun Lee, Inwoong Lee, Taeoh Kim, Dongyoon Wee, Minho Shim, Yukyung Choi

huggingface Score 10.5

Published 2026-07-02 · First seen 2026-07-10

General AI

Abstract

The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performance stems from visual perception, linguistic reasoning, or knowledge priors. While many benchmarks have emerged to assess high-level reasoning, shared criteria for evaluating video understanding remain largely overlooked. Instead of introducing yet another benchmark, we take a step back to re-examine the criteria for evaluating video understanding. In this work, we introduce Video-Oasis, a sustainable diagnostic suite for systematically auditing existing video understanding benchmarks. This audit reveals that 55\% of existing benchmark samples are solvable without visual input or temporal context. After filtering these shortcuts, the remaining video-native challenges expose a substantial capability gap: state-of-the-art models perform only marginally above random guessing. Building on these findings, we use the distilled challenges as a testbed to investigate which algorithmic design choices contribute to robust video understanding. We hope our work provides a practical foundation for constructing rigorous video benchmarks and evaluating future Video-LLMs. Code is available at https://github.com/sejong-rcv/Video-Oasis.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{lim2026video,
  title = {Video-Oasis: Rethinking Evaluation of Video Understanding},
  author = {Geuntaek Lim and Sungjune Park and Jaeyun Lee and Inwoong Lee and Taeoh Kim and Dongyoon Wee and Minho Shim and Yukyung Choi},
  year = {2026},
  abstract = {The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performance stems from visual perception, linguistic reasoning, or knowledge priors. While many benchmarks have emerged to assess high-level reasoning, shared criteria for evaluating video understanding remain largely overlooked. Instead of introducing yet another benchmark, we take a step back to re-examine the criteria for evaluating video understanding. In this work, we introduce Video-O},
  url = {https://huggingface.co/papers/2603.29616},
  keywords = {Video-LLM, video understanding, benchmark evaluation, diagnostic suite, video-native challenges, algorithmic design choices, visual perception, linguistic reasoning, knowledge priors, code available, huggingface daily},
  eprint = {2603.29616},
  archiveprefix = {arXiv},
}

Metadata

{}