视觉大模型 / VLM - arXivDaily 专题

2409.08251 2024-09-13 cs.CV 79%

Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding

Hongyu Li, Tianrui Hui, Zihan Ding, Jing Zhang, Bin Ma, Xiaoming Wei, Jizhong Han, Si Liu

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

Comments Accepted by ACM MM 2024

2312.14206 2024-09-13 cs.CV 79%

LLM4VG: Large Language Models Evaluation for Video Grounding

Wei Feng, Xin Wang, Hong Chen, Zeyang Zhang, Houlun Chen, Zihan Song, Yuwei Zhou, Yuekui Yang, Haiyang Wu, Wenwu Zhu

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

2409.04999 2024-09-10 cs.CV cs.MM 79%

Visual Grounding with Multi-modal Conditional Adaptation

Ruilin Yao, Shengwu Xiong, Yichen Zhao, Yi Rong

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

Comments Accepted by ACM MM 2024 [Oral]

2308.09012 2024-09-10 cs.CV 79%

FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings

Zhen Wang, Da Li, Yulin Su, Min Yang, Minghui Qiu, Walton Wang

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

2303.16341 2024-09-10 cs.CV 79%

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Yuanhao Xiong, Long Zhao, Boqing Gong, Ming-Hsuan Yang, Florian Schroff, Ting Liu, Cho-Jui Hsieh, Liangzhe Yuan

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

Comments Accepted to ICLR2024, see https://openreview.net/forum?id=5dlfiJIXoh for more details

2404.13400 2024-09-06 cs.CV 79%

HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding

Linhui Xiao, Xiaoshan Yang, Fang Peng, Yaowei Wang, Changsheng Xu

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

Comments Accepted by ACM MM 2024. The project page: https://github.com/linhuixiao/HiVG

2409.03109 2024-09-06 cs.CV cs.CR 79%

FIDAVL: Fake Image Detection and Attribution using Vision-Language Model

Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Abdenour Hadid

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

2407.14491 2024-09-04 cs.CV 79%

PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding

Chenshu Hou, Liang Peng, Xiaopei Wu, Xiaofei He, Wenxiao Wang

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

2402.14154 2024-09-04 cs.CL cs.CV cs.CY 79%

MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms

Yiqiao Jin, Minje Choi, Gaurav Verma, Jindong Wang, Srijan Kumar

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

Comments In Proceedings of ACL 2024

2409.00556 2024-09-04 cs.CV 79%

FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model

Yuanwei Li, Elizaveta Ivanova, Martins Bruveris

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

Comments 13 pages, 2 figures, Accepted for BMVC 2024

2409.00238 2024-09-04 cs.CL cs.CV 79%

Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data

Spencer Whitehead, Jacob Phillips, Sean Hendryx

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

2408.16314 2024-08-30 cs.CV 79%

ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding

Minghang Zheng, Jiahua Zhang, Qingchao Chen, Yuxin Peng, Yang Liu

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

Comments Accepted by ACM MM 2024

2408.01024 2024-08-22 cs.AI 79%

Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments

Sangwoo Shin, Seunghyun Kim, Youngsoo Jang, Moontae Lee, Honguk Woo

专题命中视觉定位与Grounding ：grounding(title,abstract)；分类 cs.AI

Comments Findings of ACL-2024 Camera Ready Version

2408.09605 2024-08-20 cs.AI 79%

Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models

David J. Chalmers

专题命中视觉定位与Grounding ：grounding(title,abstract)；分类 cs.AI

Journal ref Proceedings and Addresses of the American Philosophical Association, 2023

2408.01669 2024-08-20 cs.CV cs.MM 79%

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses

Chaolei Tan, Zihang Lin, Junfu Pu, Zhongang Qi, Wei-Yi Pei, Zhi Qu, Yexin Wang, Ying Shan, Wei-Shi Zheng, Jian-Fang Hu

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

Comments Accepted to ACM MM 2024. Project page: https://synopground.github.io/

2408.07975 2024-08-16 cs.RO cs.CL cs.CV 79%

Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models

Tianyu Wang, Haitao Lin, Junqiu Yu, Yanwei Fu

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

Comments Accepted by IROS 2024. 8 pages, 5 figures. See https://star-uu-wang.github.io/Polaris/

2408.04961 2024-08-12 cs.CV 79%

In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation

Dahyun Kang, Minsu Cho

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

Comments Accepted to ECCV 2024

2408.04023 2024-08-09 cs.CL cs.AI 79%

Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity

Wrick Talukdar, Anjanava Biswas

专题命中视觉定位与Grounding ：grounding(title,abstract)；分类 cs.AI

Comments 14 pages

Journal ref World Journal of Advanced Engineering Technology and Sciences, 2023, 10(2), 283-296

2408.01120 2024-08-05 cs.CV 79%

An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding

Wei Chen, Long Chen, Yu Wu

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

Comments 21pages, 10 figures, 9 tables. Accepted to ECCV 2024

2408.00932 2024-08-05 cs.CV cs.CL 79%

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper)

Bin Han, Yiwei Yang, Anat Caspi, Bill Howe

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

2311.11273 2024-07-31 cs.CV 79%

Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection

Lv Tang, Peng-Tao Jiang, Zhihao Shen, Hao Zhang, Jinwei Chen, Bo Li

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

Comments Accepted by ACMMM2024

2407.18391 2024-07-29 cs.CV 79%

UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models

Xinyu Pi, Mingyuan Wu, Jize Jiang, Haozhen Zheng, Beitong Tian, Chengxiang Zhai, Klara Nahrstedt, Zhiting Hu

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

Comments 10 pages

2407.17035 2024-07-25 cs.CV 79%

Q-Ground: Image Quality Grounding with Large Multi-modality Models

Chaofeng Chen, Sensen Yang, Haoning Wu, Liang Liao, Zicheng Zhang, Annan Wang, Wenxiu Sun, Qiong Yan, Weisi Lin

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

Comments ACM Multimedia 2024 (Oral)

2407.15728 2024-07-25 eess.IV cs.CV 79%

SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection

Dimitrios Kollias, Anastasios Arsenos, James Wingate, Stefanos Kollias

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

2308.03725 2024-07-25 cs.CV 79%

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation

Renjie Liang, Yiming Yang, Hui Lu, Li Li

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

2407.15046 2024-07-23 cs.CV cs.CL cs.MM 79%

Audio-visual training for improved grounding in video-text LLMs

Shivprasad Sagare, Hemachandran S, Kinshuk Sarabhai, Prashant Ullegaddi, Rajeshkumar SA

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

2406.05785 2024-07-23 cs.CV 79%

A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions

Daizong Liu, Yang Liu, Wencan Huang, Wei Hu

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

2404.00801 2024-07-23 cs.CV 79%

$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Ye Liu, Jixuan He, Wanhua Li, Junsik Kim, Donglai Wei, Hanspeter Pfister, Chang Wen Chen

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

Comments ECCV 2024 Camera Ready

2312.14055 2024-07-23 cs.CV 79%

Multi-Sentence Grounding for Long-term Instructional Video

Zeqian Li, Qirui Chen, Tengda Han, Ya Zhang, Yanfeng Wang, Weidi Xie

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

2403.13589 2024-07-22 cs.CV 79%

ReGround: Improving Textual and Spatial Grounding at No Cost

Phillip Y. Lee, Minhyuk Sung

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

Comments Accepted to ECCV 2024. Project page: https://re-ground.github.io/

1. 视觉定位与Grounding 7473 篇

Dynamic Prompting of Frozen Text-to-Image Diffusion Models for Panoptic Narrative Grounding

LLM4VG: Large Language Models Evaluation for Video Grounding

Visual Grounding with Multi-modal Conditional Adaptation

FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding

FIDAVL: Fake Image Detection and Attribution using Vision-Language Model

PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding

MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms

FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model

Pre-Training Multimodal Hallucination Detectors with Corrupted Grounding Data

ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding

Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments

Does Thought Require Sensory Grounding? From Pure Thinkers to Large Language Models

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses

Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models

In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation

Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity

An Efficient and Effective Transformer Decoder-Based Framework for Multi-Task Visual Grounding

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper)

Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection

UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models

Q-Ground: Image Quality Grounding with Large Multi-modality Models

SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection

Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation

Audio-visual training for improved grounding in video-text LLMs

A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions

$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Multi-Sentence Grounding for Long-term Instructional Video

ReGround: Improving Textual and Spatial Grounding at No Cost