Article

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Descriptions to Comprehensive Video Understanding

2025-02-04

Abstract excerpt

We introduce Tarsier2, a state-of-the-art large vision-language model (LVLM) designed for generating detailed and accurate video descriptions, while also exhibiting superior general video understanding capabilities. Tarsier2 achieves significant advancements through three key upgrades: (1) Scaling pre-training data from 11M to 40M video-text pairs, enriching both volume and diversity; (2) Performing fine-grained t...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 5d395ca1-cdba-589f-a65e-6f31fcce0994
DOI: 10.32388/x26ilu

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Descriptions to Comprehensive Video UnderstandingDOI 10.32388/x26iluRead

A Review of Multimodal Vision–Language Models: Foundations, Applications, and Future DirectionsSemantic proximity Read

Rethinking Convolutional Semantics for Image Caption Generation Beyond Recurrent ParadigmsSemantic proximity Read

A Sentence retrieval generation network guided video captioningSemantic proximity Read

Vision–Language Foundation Models and Multimodal Large Language Models: A Comprehensive Survey of Architectures, Benchmarks, and Open ChallengesSemantic proximity Read

Vision–Language Foundation Models and Multimodal Large Language Models: A Comprehensive Survey of Architectures, Benchmarks, and Open ChallengesSemantic proximity Read

FineRegion-LM: Enhancing Large Vision-Language Models for Fine-Grained Region-Level UnderstandingSemantic proximity Read

Context-Aware Feature Integration for Enhanced Fine-Grained Understanding in Vision-Language ModelsSemantic proximity Read

RobustVLM: Enhancing Large Vision-Language Models through Adaptive Visual Context Learning, Weak-to-Strong Robust Transfer, and Domain-Adaptive FeedbackSemantic proximity Read

A Review of Multimodal Vision-Language Models: Foundations, Applications, and Future DirectionsSemantic proximity Read

RNIC-A Retrospect Network for image captioningSemantic proximity Read

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic VideosSemantic proximity Read

Enhancing Caption Fidelity via Explanation-Guided Captioning with Vision-Language Fine-TuningSemantic proximity Read