Tag-grounded Visual Instruction Tuning with Retrieval Augmentation
Daiqing Qi, Handong Zhao, Zijun Wei, Sheng Li
摘要
GPT4:This photo features four mangosteens on a wooden table.Three of them are uncut, showing their round, dark purple exterior.The fourth mangosteen is cut open, revealing its white, fleshy interior, which is divided into segments.The table surface has a natural wood grain pattern and adds a rustic touch to the image. LLaVA:The image features a close-up of three small, round, and purple fruits, possibly pomegranates, sitting on a wooden surface.The fruits are placed in a row, with one on the left, one in the middle, and one on the right.In addition to the fruits, there is a knife located on the right side of the image, likely used for cutting the fruits.The scene appears to be a still life composition, showcasing the vibrant color and texture of the fruits. ShareGPT4V:The image captures a close-up view of four lychee fruits, their vibrant colors standing out against the wooden surface they rest on.The fruits are arranged in a square formation, with one at each corner.The top left and bottom right corners each hold a whole lychee, their green tops contrasting with the deep purple of the fruit.The top right corner features a lychee that has been cut open, revealing the white interior that is characteristic of this tropical fruit.The background, though blurred, hints at the presence of green leaves, adding a touch of nature to the scene.What type of fruit is this?
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper2
- Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive DecodingDaiqing Qi, Dongliang Guo, Hanzhang Yuan, Handong Zhao 等NeurIPS 2025 · 被引用 5 次
- The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like PhotographersDaiqing Qi, Handong Zhao, Jing Shi, Simon Jenni 等CVPR 2025
它引用的顶会 Paper18
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Visual Instruction TuningHaotian Liu, Chunyuan Li, Qingyang Wu, Yong Jae LeeNeurIPS 2023 · 被引用 11,349 次
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsJunnan Li, Dongxu Li, Silvio Savarese, Steven C. H. HoiICML 2023 · 被引用 7,873 次
- BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationJunnan Li, Dongxu Li, Caiming Xiong, Steven C. H. HoiICML 2022 · 被引用 6,549 次
- InstructBLIP: Towards General-purpose Vision-Language Models with Instruction TuningWenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong 等NeurIPS 2023 · 被引用 4,013 次
相关 Paper
- Wi-Fruit: See Through Fruits with Smart DevicesYutong Liu, Landu Jiang, Linghe Kong, Qiao Xiang 等UbiComp 2022 · 被引用 39 次
- FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any GranularityHang Hua, Qing Liu, Lingzhi Zhang, Jing Shi 等CVPR 2025
- Metric Transforms and Low Rank Representations of Kernels for Fast AttentionTimothy Chu, Josh Alman, Gary L. Miller, Shyam Narayanan 等NeurIPS 2024 · 被引用 4 次
- VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame SelectionSonghao Han, Wei Huang, Hairong Shi, Le Zhuo 等CVPR 2025
- ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion ModelsOzgur Kara, Krishna Kumar Singh, Feng Liu, Duygu Ceylan 等CVPR 2025
