Pith. sign in

REVIEW 28 cited by

Tarsier: Recipes for Training and Evaluating Large Video Description Models

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 2407.00634 v2 pith:5QUREKRA submitted 2024-06-30 cs.CV cs.LG

Tarsier: Recipes for Training and Evaluating Large Video Description Models

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

Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\%$ advantage in human side-by-side evaluation over the strongest model. Additionally, they are comparable to state-of-the-art proprietary models, with a $+12.3\%$ advantage against GPT-4V and a $-6.7\%$ disadvantage against Gemini 1.5 Pro. When upgraded to Tarsier2 by building upon SigLIP and Qwen2-7B, it further improves significantly with a $+4.8\%$ advantage against GPT-4o. Besides video description, Tarsier proves to be a versatile generalist model, achieving new state-of-the-art results across nine public benchmarks, including multi-choice VQA, open-ended VQA, and zero-shot video captioning. Our second contribution is the introduction of a new benchmark -- DREAM-1K (https://tarsier-vlm.github.io/) for evaluating video description models, consisting of a new challenging dataset featuring videos from diverse sources and varying complexity, along with an automatic method specifically designed to assess the quality of fine-grained video descriptions. We make our models and evaluation benchmark publicly available at https://github.com/bytedance/tarsier.

discussion (0)

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

Forward citations

Cited by 28 Pith papers

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

  1. MentalThink: Shaping Thoughts in Mental SVG World

    cs.AI 2026-07 conditional novelty 7.0

    MLLMs that generate and render SVG sketches as multi-turn intermediate reasoning steps reach 55.1% on VSIBench and 76.0% on MindCube, far above the Qwen2.5-VL-7B backbone.

  2. CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning

    cs.CV 2026-06 unverdicted novelty 7.0

    CapRL++ applies reinforcement learning with verifiable rewards to dense image and video captioning by scoring captions via the accuracy of a vision-free LLM answering MCQs from the caption alone.

  3. AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

    cs.CV 2026-06 unverdicted novelty 7.0

    AVI-Bench is a cognitively inspired benchmark that evaluates Omni-MLLMs on joint audio-visual tasks and reveals substantial limitations in current models.

  4. CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 7.0

    Proposes Spatial Narrative Score (SNS) evaluation for VLMs' camera motion understanding and introduces CaMo model achieving consistent performance on SNS and direct QA.

  5. SCP: Spatial Causal Prediction in Video

    cs.CV 2026-03 unverdicted novelty 7.0

    SCP defines a new benchmark task for predicting spatial causal outcomes beyond direct observation and shows that 23 leading models lag far behind humans on it.

  6. CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning

    cs.CV 2026-01 unverdicted novelty 7.0

    CamReasoner uses structured O-T-A reasoning and RL on 56k samples to lift camera movement classification from 73.8% to 78.4% and VQA from 60.9% to 74.5% on Qwen2.5-VL-7B.

  7. Adapting MLLMs for Nuanced Video Retrieval

    cs.CV 2025-12 unverdicted novelty 7.0

    Text-only contrastive fine-tuning of an MLLM with hard negatives produces embeddings that handle temporal, negation, and multimodal nuances in video retrieval and achieves SOTA performance.

  8. RefCaptioner: Multi-Reference Image-Grounded Video Captioning

    cs.CV 2026-07 conditional novelty 6.0

    Mixed-data SFT plus Hierarchical Coverage-Discounted GRPO yields open-source SOTA multi-reference image-grounded video captions on MRVBench without hurting general captioning.

  9. MotionAtlas: Detailed Region Captioning for Motion-Centric Videos

    cs.CV 2026-06 unverdicted novelty 6.0

    MotionAtlas supplies a 2,073-question benchmark, a self-bootstrap pipeline yielding 159k captions, and fine-tuned Video-MLLMs that deliver 5.2-point gains over Qwen3-VL-4B on motion tasks.

  10. CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning

    cs.AI 2026-06 unverdicted novelty 6.0

    CineCap combines structured reasoning and RL rewards to outperform baselines on cinematographic video captioning using a new 472-pair benchmark.

  11. Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA

    cs.CV 2026-06 unverdicted novelty 6.0

    CREDiT applies counterfactual reasoning via structural causal models to decompose video representations into causal and non-causal parts for more reliable VideoQA on datasets like NExT-GQA and SportsQA.

  12. MotionEnhancer: Leveraging Video Diffusion for Motion-Enhanced Vision-Language Models

    cs.CV 2026-06 unverdicted novelty 6.0

    MotionEnhancer distills motion priors from video diffusion models into VLMs via parameter-free attention alignment modules to improve motion-level video understanding.

  13. Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0

    CineNeuron improves fMRI-to-video reconstruction by combining bottom-up semantic enrichment with top-down Mixture-of-Memories integration and outperforms prior methods on benchmarks.

  14. 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...

  15. Progressive Video Condensation with MLLM Agent for Long-form Video Understanding

    cs.CV 2026-04 unverdicted novelty 6.0

    ProVCA progressively condenses long videos via segment localization, snippet selection, and keyframe refinement to achieve SOTA zero-shot accuracies on EgoSchema, NExT-QA, and IntentQA with fewer frames.

  16. MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding

    cs.CV 2025-05 unverdicted novelty 6.0

    MUSEG applies timestamp-aware multi-segment grounding with a phased-reward RL recipe to boost temporal grounding and time-sensitive video QA performance in MLLMs.

  17. LLaVA-Video: Video Instruction Tuning With Synthetic Data

    cs.CV 2024-10 unverdicted novelty 6.0

    LLaVA-Video-178K is a new synthetic video instruction dataset that, when combined with existing data to train LLaVA-Video, produces strong results on video understanding benchmarks.

  18. PercepCap: Video Captioner with Structured Spatio-Temporal Perception

    cs.CV 2026-07 conditional novelty 5.0

    Explicitly generating object trajectories and event timestamps before the final caption improves detailed video captioning on multiple benchmarks, though the improvement is largely driven by an external perception oracle.

  19. 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.

  20. VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

    cs.CV 2026-05 unverdicted novelty 5.0

    VCap pairs reference captions as witnesses with visual signals as adjudicators to deliver hypergeometric-precision rewards for RL in visual captioning, enabling an 8B model to outperform SOTA on benchmarks and improve...

  21. VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

    cs.CV 2025-04 unverdicted novelty 5.0

    Reinforcement fine-tuning with temporal rewards produces VideoChat-R1, a video MLLM showing large gains on spatio-temporal perception benchmarks such as +31.8 temporal grounding and +31.2 object tracking.

  22. Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning

    cs.CV 2026-07 unverdicted novelty 4.0

    TCA-Captioner introduces an Observer-Checker-Corrector refinement loop and TCA-Bench to address modality detachment and temporal incoherence in audiovisual video captioning.

  23. InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning

    cs.CV 2026-06 unverdicted novelty 4.0

    InternVideo3 introduces Multimodal Contextual Reasoning and M^2LA attention to enable closed-loop evidence accumulation in long-video understanding and agentic tool use, reporting strong benchmark results.

  24. 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.

  25. UNIVID: Unified Vision-Language Model for Video Moderation

    cs.MM 2026-06 unverdicted novelty 4.0

    UNIVID generates policy-aware captions for video moderation, reducing violation leakage by 42.7% and overkill rate by 37.0% while replacing over 1,000 policy-specific models with a single backbone.

  26. 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.

  27. Open-Sora Plan: Open-Source Large Video Generation Model

    cs.CV 2024-11 unverdicted novelty 4.0

    Open-Sora Plan presents an open-source large video generation model that combines a Wavelet-Flow VAE, Joint Image-Video Skiparse Denoiser, and multi-dimensional data curation to achieve high-quality video outputs with...

  28. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

    cs.CV 2024-06 unverdicted novelty 4.0

    VideoLLaMA 2 improves video LLMs via a new STC connector for spatial-temporal dynamics and joint audio training, reaching competitive results on video QA and captioning benchmarks.