Pith. sign in

REVIEW 10 cited by

Lost in Time: A New Temporal Benchmark for VideoLLMs

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 2410.07752 v3 pith:ADZFYWQO submitted 2024-10-10 cs.CV

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

Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating video models presents its own unique challenges, for which several benchmarks have been proposed. In this paper, we show that the currently most used video-language benchmarks can be solved without requiring much temporal reasoning. We identified three main issues in existing datasets: (i) static information from single frames is often sufficient to solve the tasks (ii) the text of the questions and candidate answers is overly informative, allowing models to answer correctly without relying on any visual input (iii) world knowledge alone can answer many of the questions, making the benchmarks a test of knowledge replication rather than video reasoning. In addition, we found that open-ended question-answering benchmarks for video understanding suffer from similar issues while the automatic evaluation process with LLMs is unreliable, making it an unsuitable alternative. As a solution, we propose TVBench, a novel open-source video multiple-choice question-answering benchmark, and demonstrate through extensive evaluations that it requires a high level of temporal understanding. Surprisingly, we find that most recent state-of-the-art video-language models perform similarly to random performance on TVBench, with only a few models such as Qwen2-VL, and Tarsier clearly surpassing this baseline.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. AdaThinkV: Adaptive Thinking for Token-Efficient Video Reasoning

    cs.CV 2026-08 conditional novelty 7.0 of 10

    A video reasoning model learns per question whether to reason aloud or answer directly, improving accuracy by about 3 points over the best adaptive baseline while using about 23% fewer output tokens.

  2. EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models

    cs.CV 2025-06 conditional novelty 7.0 of 10

    EPFL-Smart-Kitchen-30 is a 29.7-hour multimodal cooking dataset with 60k action segments and four benchmarks, including a kinematic-focused VQA benchmark that shows current video-language models struggle with hand and...

  3. Do Video-LLMs Actually Watch? Diagnosing Character-Tracking Failures in Long-Form Video

    cs.CV 2026-07 conditional novelty 6.5 of 10

    Video-LLMs scoring 37–38% on InfiniBench global appearance change answers only 4–31% under character-name swaps, so the score is not character tracking.

  4. VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

    cs.CV 2026-07 conditional novelty 6.0 of 10

    An open 4B video MLLM with inflated-3D ViT tokenization and adaptive streaming perception outperforms comparable open models on general, long-video, and streaming benchmarks while using fewer visual tokens.

  5. Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A benchmark audit shows that video LLM accuracy and true visual grounding are separable, and that most apparent video understanding comes from frame diversity, not temporal order.

  6. EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

    cs.CV 2025-10 conditional novelty 6.0 of 10

    Most Video-LLMs answer temporal questions far less consistently when the same event is shown from ego and exo views, and a GRPO variant with a reasoning-similarity reward partially closes the gap.

  7. MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models

    cs.CV 2025-09 conditional novelty 6.0 of 10

    MESH, a three-layer video hallucination benchmark, shows LVMs ace basic objects and coarse traits but slip badly on fine character details and multi-subject actions in longer clips.

  8. VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos

    cs.CV 2025-06 conditional novelty 6.0 of 10

    VRBench is a benchmark of 960 long narrative videos with 8,243 human-written multi-step questions, plus a two-level evaluation of answer accuracy and reasoning quality for 31 large models.

  9. How Important are Videos for Training Video LLMs?

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Training video LLMs on ordered static images with temporal questions nearly matches real video training on TVBench, suggesting video data is underused.

  10. Fostering Video Reasoning via Next-Event Prediction

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Next-event prediction, training video language models to caption unseen future frames, improves their scores on several temporal benchmarks while roughly preserving general video understanding.

Pith tools