视觉大模型 / VLM - arXivDaily 专题

2501.16981 2025-03-07 cs.CV 70%

Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection

Xiangyu Gao, Yu Dai, Benliu Qiu, Lanxiao Wang, Heqian Qiu, Hongliang Li

专题命中视觉定位与Grounding ：vision language model(abstract)；VLM(abstract)；分类 cs.CV

2503.01794 2025-03-04 cs.CV 70%

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

Junhyun Park, Chanyu Moon, Donghwan Lee, Kyungsu Kim, Minho Hwang

专题命中视觉定位与Grounding ：vision-language model(abstract)；grounding(abstract)；分类 cs.CV

Comments 10 pages, 3 figures, and 5 tables

2503.01785 2025-03-04 cs.CV 70%

Visual-RFT: Visual Reinforcement Fine-Tuning

Ziyu Liu, Zeyi Sun, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Haodong Duan, Dahua Lin, Jiaqi Wang

专题命中视觉定位与Grounding ：vision-language model(abstract)；grounding(abstract)；分类 cs.CV

Comments project page: https://github.com/Liuziyu77/Visual-RFT

2502.20698 2025-03-03 cs.CV 70%

Towards General Visual-Linguistic Face Forgery Detection(V2)

Ke Sun, Shen Chen, Taiping Yao, Ziyin Zhou, Jiayi Ji, Xiaoshuai Sun, Chia-Wen Lin, Rongrong Ji

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments 8 pages, 5 figures, Accpet by CVPR2025

2409.04796 2025-02-27 cs.CV 70%

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Fanhu Zeng, Zhen Cheng, Fei Zhu, Hongxin Wei, Xu-Yao Zhang

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted by The Thirteenth International Conference on Learning Representations (ICLR 2025). Code is available at https://github.com/AuroraZengfh/Local-Prompt

Journal ref The Thirteenth International Conference on Learning Representations (ICLR 2025)

2410.09855 2025-02-18 cs.CV 70%

Text4Seg: Reimagining Image Segmentation as Text Generation

Mengcheng Lan, Chaofeng Chen, Yue Zhou, Jiaxing Xu, Yiping Ke, Xinjiang Wang, Litong Feng, Wayne Zhang

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments ICLR 2025. Project page: https://mc-lan.github.io/Text4Seg/

2407.15795 2025-02-17 cs.CV 70%

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection

Yunkang Cao, Jiangning Zhang, Luca Frittoli, Yuqi Cheng, Weiming Shen, Giacomo Boracchi

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted by ECCV 2024

Journal ref European Conference on Computer Vision, 2024

2312.10417 2025-01-27 cs.AI 70%

M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base

Zhiwei Zha, Jiaan Wang, Zhixu Li, Xiangru Zhu, Wei Song, Yanghua Xiao

专题命中视觉定位与Grounding ：grounding(abstract)；multimodal large language model(abstract)；分类 cs.AI

Comments Accepted by CIKM2024. The code and data can be found at https://github.com/AwellmanZha/M2ConceptBase

2501.09218 2025-01-17 q-bio.QM cs.AI 70%

Interpretable Droplet Digital PCR Assay for Trustworthy Molecular Diagnostics

Yuanyuan Wei, Yucheng Wu, Fuyang Qu, Yao Mu, Yi-Ping Ho, Ho-Pui Ho, Wu Yuan, Mingkun Xu

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.AI

2407.14505 2025-01-16 cs.CV 70%

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

Kaiyue Sun, Kaiyi Huang, Xian Liu, Yue Wu, Zihan Xu, Zhenguo Li, Xihui Liu

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments Project page: https://t2v-compbench-2025.github.io/ Code: https://github.com/KaiyueSun98/T2V-CompBench/tree/V2

2501.07554 2025-01-14 cs.CV cs.CL 70%

SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing

Varun Biyyala, Bharat Chanderprakash Kathuria, Jialu Li, Youshan Zhang

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments WACV workshop

2409.14750 2025-01-14 cs.CV cs.CL 70%

FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension

Junzhuo Liu, Xuzheng Yang, Weiwei Li, Peng Wang

专题命中视觉定位与Grounding ：visual reasoning(abstract)；grounding(abstract)；分类 cs.CV

Comments 18 pages, EMNLP 2024 main

2501.03786 2025-01-08 cs.CV 70%

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

Chengyuan Li, Suyang Zhou, Jieping Kong, Lei Qi, Hui Xue

专题命中视觉定位与Grounding ：vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Accepted by ICASSP 2025

2412.16869 2024-12-24 cs.CV 70%

CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models

Yeyuan Wang, Dehong Gao, Bin Li, Rujiao Long, Lei Yi, Xiaoyan Cai, Libin Yang, Jinxia Zhang, Shanqing Yu, Qi Xuan

专题命中视觉定位与Grounding ：grounding(abstract)；MLLM(abstract)；分类 cs.CV

Comments 5 pages, Accepted by ICASSP2025, full paper

2307.02291 2024-12-24 cs.CV 70%

Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor

Junwen Chen, Yingcheng Wang, Keiji Yanai

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

2412.14145 2024-12-19 cs.CV 70%

Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation

Jianyu Zhang, Li Zhang, Shijian Li

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments 6 pages, 6 figures

2412.13947 2024-12-19 cs.CV 70%

Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition

Ethan Baron, Idan Tankel, Peter Tu, Guy Ben-Yosef

专题命中视觉定位与Grounding ：vision-language model(abstract)；grounding(abstract)；分类 cs.CV

2405.04788 2024-12-03 cs.CV 70%

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector

Kaiyu Li, Xiangyong Cao, Yupeng Deng, Jiayi Song, Junmin Liu, Deyu Meng, Zhi Wang

专题命中视觉定位与Grounding ：VLM(abstract)；visual language model(abstract)；分类 cs.CV

Comments 13 pages, 6 figures

2406.00307 2024-11-04 cs.CV 70%

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model

Khoa Vo, Thinh Phan, Kashu Yamazaki, Minh Tran, Ngan Le

专题命中视觉定位与Grounding ：visual reasoning(abstract)；grounding(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2024

2405.20141 2024-10-31 cs.CV 70%

OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation

Gonca Yilmaz, Songyou Peng, Marc Pollefeys, Francis Engelmann, Hermann Blum

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

2410.16163 2024-10-22 cs.CV 70%

Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models

Yufei Zhan, Hongyin Zhao, Yousong Zhu, Fan Yang, Ming Tang, Jinqiao Wang

专题命中视觉定位与Grounding ：visual question answering(abstract)；grounding(abstract)；分类 cs.CV

Comments This work has been submitted to the IEEE for possible publication. Codes and data will be later released at https://github.com/jefferyZhan/Griffon

2311.12015 2024-10-11 cs.RO cs.CL cs.CV 70%

GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration

Naoki Wake, Atsushi Kanehira, Kazuhiro Sasabuchi, Jun Takamatsu, Katsushi Ikeuchi

专题命中视觉定位与Grounding ：vision language model(abstract)；grounding(abstract)；分类 cs.CV

Comments 8 pages, 10 figures, 3 tables. Published in IEEE Robotics and Automation Letters (RA-L) (in press). Last updated on September 26th, 2024

2410.05963 2024-10-10 cs.CV 70%

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts

Zhiwei Lin, Yongtao Wang, Zhi Tang

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2024

2410.00436 2024-10-02 cs.RO cs.CV 70%

Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations

Miyu Goko, Motonari Kambara, Daichi Saito, Seitaro Otsuki, Komei Sugiura

专题命中视觉定位与Grounding ：multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments Accepted for presentation at CoRL2024

2407.20171 2024-08-27 cs.CV 70%

Diffusion Feedback Helps CLIP See Better

Wenxuan Wang, Quan Sun, Fan Zhang, Yepeng Tang, Jing Liu, Xinlong Wang

专题命中视觉定位与Grounding ：VLM(abstract)；multimodal large language model(abstract)；分类 cs.CV

2408.02261 2024-08-06 cs.CV 70%

Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs

Jeongkee Lim, Yusung Kim

专题命中视觉定位与Grounding ：vision language model(abstract)；visual language model(abstract)；分类 cs.CV

Comments ECCV 2024

2408.01433 2024-08-06 cs.CV cs.ET 70%

Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks

Malsha Ashani Mahawatta Dona, Beatriz Cabrero-Daniel, Yinan Yu, Christian Berger

专题命中视觉定位与Grounding ：LLaVA(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments Accepted in 27th IEEE International Conference on Intelligent Transportation Systems (ITSC) 2024

2408.00331 2024-08-02 cs.CV 70%

DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation

Rakshith Subramanyam, Kowshik Thopalli, Vivek Narayanaswamy, Jayaraman J. Thiagarajan

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted at ECCV (European Conference on Computer Vision) 2024

2407.21554 2024-08-01 cs.CV 70%

Conditioned Prompt-Optimization for Continual Deepfake Detection

Francesco Laiti, Benedetta Liberatori, Thomas De Min, Elisa Ricci

专题命中视觉定位与Grounding ：vision-language model(abstract)；VLM(abstract)；分类 cs.CV

Comments Accepted at ICPR 2024

2405.14815 2024-07-23 cs.CV 70%

Designing A Sustainable Marine Debris Clean-up Framework without Human Labels

Raymond Wang, Nicholas R. Record, D. Whitney King, Tahiya Chowdhury

专题命中视觉定位与Grounding ：vision-language model(abstract)；grounding(abstract)；分类 cs.CV

Comments 9 pages, 6 figures, 2 tables, In Proceedings of the 7th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies

1. 视觉定位与Grounding 7387 篇

Modulating CNN Features with Pre-Trained ViT Representations for Open-Vocabulary Object Detection

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

Visual-RFT: Visual Reinforcement Fine-Tuning

Towards General Visual-Linguistic Face Forgery Detection(V2)

Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection

Text4Seg: Reimagining Image Segmentation as Text Generation

AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection

M^2ConceptBase: A Fine-Grained Aligned Concept-Centric Multimodal Knowledge Base

Interpretable Droplet Digital PCR Assay for Trustworthy Molecular Diagnostics

T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation

SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing

FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models

Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor

Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation

Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition

SemiCD-VL: Visual-Language Model Guidance Makes Better Semi-supervised Change Detector

HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model

OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation

Griffon-G: Bridging Vision-Language and Vision-Centric Tasks via Large Multimodal Models

GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration

Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts

Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations

Diffusion Feedback Helps CLIP See Better

Cross-Domain Semantic Segmentation on Inconsistent Taxonomy using VLMs

Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks

DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation

Conditioned Prompt-Optimization for Continual Deepfake Detection

Designing A Sustainable Marine Debris Clean-up Framework without Human Labels