Pith. sign in

REVIEW 16 cited by

OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

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 2501.05510 v2 pith:HTRKOA7D submitted 2025-01-09 cs.CV cs.AI

OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

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

Temporal Awareness, the ability to reason dynamically based on the timestamp when a question is raised, is the key distinction between offline and online video LLMs. Unlike offline models, which rely on complete videos for static, post hoc analysis, online models process video streams incrementally and dynamically adapt their responses based on the timestamp at which the question is posed. Despite its significance, temporal awareness has not been adequately evaluated in existing benchmarks. To fill this gap, we present OVO-Bench (Online-VideO-Benchmark), a novel video benchmark that emphasizes the importance of timestamps for advanced online video understanding capability benchmarking. OVO-Bench evaluates the ability of video LLMs to reason and respond to events occurring at specific timestamps under three distinct scenarios: (1) Backward tracing: trace back to past events to answer the question. (2) Real-time understanding: understand and respond to events as they unfold at the current timestamp. (3) Forward active responding: delay the response until sufficient future information becomes available to answer the question accurately. OVO-Bench comprises 12 tasks, featuring 644 unique videos and approximately human-curated 2,800 fine-grained meta-annotations with precise timestamps. We combine automated generation pipelines with human curation. With these high-quality samples, we further developed an evaluation pipeline to systematically query video LLMs along the video timeline. Evaluations of nine Video-LLMs reveal that, despite advancements on traditional benchmarks, current models struggle with online video understanding, showing a significant gap compared to human agents. We hope OVO-Bench will drive progress in video LLMs and inspire future research in online video reasoning. Our benchmark and code can be accessed at https://github.com/JoeLeelyf/OVO-Bench.

discussion (0)

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

Forward citations

Cited by 16 Pith papers

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

  1. VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance

    cs.CV 2026-07 conditional novelty 7.0

    VIABench provides 761 long-form egocentric videos from blind individuals with 14,526 annotations across three assistance tasks, and shows current multimodal LLMs achieve best overall scores below 30.

  2. Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction

    cs.CV 2026-05 conditional novelty 7.0

    Omni-DuplexEval creates a new benchmark and LLM-as-a-Judge framework for real-time duplex omni-modal interaction, revealing that current models score below 40% overall and struggle especially with proactive responses.

  3. Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?

    cs.CV 2025-11 unverdicted novelty 7.0

    Introduces the first dedicated benchmark for live multi-modal LLM task guidance with mistake detection and a streaming baseline model.

  4. MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding

    cs.CV 2026-07 unverdicted novelty 6.0

    MedStreamBench integrates 22 medical datasets into 5,419 QA instances across retrospective, present, future, and proactive temporal settings to evaluate streaming and proactive medical video understanding.

  5. Streaming Interventions: Can Video Large Language Models Correct Mistakes as They Occur?

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces Ego-MC-Bench benchmark and Ego-CoMist synthetic dataset showing that fine-tuning video LLMs on proactive mistake corrections improves performance especially for smaller models.

  6. Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding

    cs.CV 2026-06 unverdicted novelty 6.0

    LyraV uses FDTC and SToP for per-frame incremental decoding to reach 98.29% video synchrony at 3.89 FPS while preserving general understanding.

  7. MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

    cs.CV 2026-06 unverdicted novelty 6.0

    MOSS-Video-Preview introduces a cross-attention architecture and synthesized real-time QA data to enable continuous perception, answer revision, and faster inference in video-language models compared to decoder-only designs.

  8. Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction

    cs.CV 2026-05 unverdicted novelty 6.0

    Omni-DuplexEval provides a new benchmark and automatic evaluation method for real-time duplex omni-modal interaction, showing state-of-the-art models reach only 39.6% overall and 20% on proactive reminders.

  9. MTT-Bench: Predicting Social Dominance in Mice via Multimodal Large Language Models

    eess.IV 2026-04 unverdicted novelty 6.0

    Fine-tuned multimodal LLMs predict mouse social dominance from raw tube test videos with high agreement to traditional rankings.

  10. HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding

    cs.CV 2026-01 unverdicted novelty 6.0

    HERMES organizes the KV cache into a hierarchical memory to enable real-time streaming video understanding in MLLMs, achieving 10x faster TTFT and up to 11.4% accuracy gains on streaming benchmarks with 68% fewer tokens.

  11. Streaming Video Instruction Tuning

    cs.CV 2025-12 unverdicted novelty 6.0

    Streamo is a streaming video LLM trained end-to-end on the new Streamo-Instruct-465K dataset that unifies multiple real-time video tasks with claimed strong temporal reasoning and generalization.

  12. StreamingVLM: Real-Time Understanding for Infinite Video Streams

    cs.CV 2025-10 unverdicted novelty 6.0

    StreamingVLM enables stable real-time understanding of infinite video streams at up to 8 FPS using a streaming KV cache and aligned SFT on overlapped chunks, with a 66.18% win rate over GPT-4O mini on a new two-hour v...

  13. ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference

    cs.CV 2026-06 unverdicted novelty 5.0

    ViCoStream is a new coordinated pipeline framework for streaming VideoLLMs that achieves 134 FPS video throughput and less than 50 ms TTFT on A100 while keeping accuracy near full-history baselines.

  14. LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Horizon Streams

    cs.CV 2026-06 unverdicted novelty 5.0

    LiveStarPro uses SVeD for response timing via perplexity, SCAM for incremental alignment, and TSHM for event-chain memory to achieve 28.9% better semantic correctness and 1.58x speedup on long video streams.

  15. EasyVideoR1: Easier RL for Video Understanding

    cs.CV 2026-04 unverdicted novelty 4.0

    EasyVideoR1 delivers an optimized RL pipeline for video understanding in large vision-language models, achieving 1.47x throughput gains and aligned results on 22 benchmarks.

  16. Seed1.5-VL Technical Report

    cs.CV 2025-05 unverdicted novelty 4.0

    Seed1.5-VL is a compact multimodal model that sets new records on dozens of vision-language benchmarks and outperforms prior systems on agent-style tasks.