Pith. sign in

REVIEW 13 cited by

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

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 2410.03051 v4 pith:V5F2GF3F submitted 2024-10-04 cs.CV

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark

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

Video detailed captioning is a key task which aims to generate comprehensive and coherent textual descriptions of video content, benefiting both video understanding and generation. In this paper, we propose AuroraCap, a video captioner based on a large multimodal model. We follow the simplest architecture design without additional parameters for temporal modeling. To address the overhead caused by lengthy video sequences, we implement the token merging strategy, reducing the number of input visual tokens. Surprisingly, we found that this strategy results in little performance loss. AuroraCap shows superior performance on various video and image captioning benchmarks, for example, obtaining a CIDEr of 88.9 on Flickr30k, beating GPT-4V (55.3) and Gemini-1.5 Pro (82.2). However, existing video caption benchmarks only include simple descriptions, consisting of a few dozen words, which limits research in this field. Therefore, we develop VDC, a video detailed captioning benchmark with over one thousand carefully annotated structured captions. In addition, we propose a new LLM-assisted metric VDCscore for bettering evaluation, which adopts a divide-and-conquer strategy to transform long caption evaluation into multiple short question-answer pairs. With the help of human Elo ranking, our experiments show that this benchmark better correlates with human judgments of video detailed captioning quality.

discussion (0)

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

Forward citations

Cited by 13 Pith papers

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

  1. Balancing Image Compression and Generation with Bootstrapped Tokenization

    cs.LG 2026-06 unverdicted novelty 7.0

    SelfBootTok decomposes image tokens into global and local groups via self-bootstrapped learning, enabling generators to use only global tokens for ~40% less computation and a new SOTA gFID of 1.56 with 64 tokens.

  2. Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

    cs.CV 2025-01 unverdicted novelty 7.0

    Video-MMMU benchmark shows large multimodal models exhibit steep performance drops on higher cognitive tasks when learning from professional videos and lag significantly behind humans in knowledge acquisition.

  3. HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks

    cs.CV 2024-12 unverdicted novelty 7.0

    HumanVBench provides a 16-task benchmark for human-centric video understanding in MLLMs, created through automated annotation and distractor synthesis pipelines, and shows top models lag human performance on emotion p...

  4. CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales

    cs.CV 2026-06 unverdicted novelty 6.0

    CapRiCorn-1K benchmark shows current video captioning models produce inaccurate and inconsistent captions that worsen with longer videos, with proposed metrics correlating to downstream task performance.

  5. GOPAgen: Motion-Aware and Efficient Agentic Long-Video Understanding with Structural Memory and Hierarchical Reasoning

    cs.CV 2026-06 unverdicted novelty 6.0

    GOPAgen proposes integrating video codec GOPs with a motion agent, GOP tree reasoning, structural memory, and motion vector database to improve efficiency and motion detail in agentic long-video VQA, reporting gains o...

  6. Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation

    cs.CV 2026-06 unverdicted novelty 6.0

    Auteur formalizes human-centric camera framing as a DSL, uses a fine-tuned MLLM to map text and motion to DSL keyframes, and interpolates them into trajectories for video generators.

  7. MSD-Score: Multi-Scale Distributional Scoring for Reference-Free Image Caption Evaluation

    cs.CV 2026-05 unverdicted novelty 6.0

    MSD-Score introduces multi-scale distributional scoring on von Mises-Fisher mixtures to evaluate image captions without references and reports state-of-the-art correlation with human judgments.

  8. Building a Precise Video Language with Human-AI Oversight

    cs.CV 2026-04 unverdicted novelty 6.0

    CHAI framework pairs AI pre-captions with expert human critiques to produce precise video descriptions, enabling open models to outperform closed ones like Gemini-3.1-Pro and improve fine-grained control in video gene...

  9. ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

    cs.CV 2026-03 unverdicted novelty 6.0

    ForestPrune prunes 90% of visual tokens in video MLLMs like LLaVA-OneVision while retaining 95.8% accuracy by modeling tokens as spatial-temporal forests and scoring importance via tree depth and node roles.

  10. From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models

    cs.CL 2026-06 unverdicted novelty 5.0

    The survey formalizes MLLM perception as a unified vision-language capability and traces its evolution via a new five-stage taxonomy while outlining future challenges.

  11. Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models

    cs.CV 2026-03 unverdicted novelty 5.0

    AOT reduces visual tokens in VLLMs via intra-frame and inter-frame anchors with local-global optimal transport, delivering competitive benchmark performance and efficiency gains in a training-free way.

  12. Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models

    cs.CV 2025-03 unverdicted novelty 5.0

    TwigVLM adds a twig module to VLMs for twig-guided token pruning and self-speculative decoding, retaining 96% performance after pruning 88.9% visual tokens and delivering 154% speedup on long responses for LLaVA-1.5-7B.

  13. Watch, Remember, Reason: Human-View Video Understanding with MLLMs

    cs.CV 2026-06 unverdicted novelty 4.0

    This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.