7 citations · 23 across the 49 of their papers we have counts for
19 papers · 1 filter
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
Changli Wu, Qi Chen, Jiayi Ji +7
3D Referring Expression Segmentation (3D-RES) aims to segment 3D objects by correlating referring expressions with point clouds. However, traditional approaches frequently encounte…
Mixed Degradation Image Restoration via Local Dynamic Optimization and Conditional Embedding
Yubin Gu, Yuan Meng, Xiaoshuai Sun +3
Multiple-in-one image restoration (IR) has made significant progress, aiming to handle all types of single degraded image restoration with a single model. However, in real-world sc…
Any-to-3D Generation via Hybrid Diffusion Supervision
Yijun Fan, Yiwei Ma, Jiayi Ji +2
Recent progress in 3D object generation has been fueled by the strong priors offered by diffusion models. However, existing models are tailored to specific tasks, accommodating onl…
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
Yongdong Luo, Xiawu Zheng, Guilin Li +8
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employ…
MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
Yaxin Luo, Gen Luo, Jiayi Ji +4
Despite the significant progress in multimodal large language models (MLLMs), their high computational cost remains a barrier to real-world deployment. Inspired by the mixture of d…
I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
Yiwei Ma, Jiayi Ji, Ke Ye +6
Significant progress has been made in the field of Instruction-based Image Editing (IIE). However, evaluating these models poses a significant challenge. A crucial requirement in t…
TraDiffusion: Trajectory-Based Training-Free Image Generation
Mingrui Wu, Oucheng Huang, Jiayi Ji +6
In this work, we propose a training-free, trajectory-based controllable T2I approach, termed TraDiffusion. This novel method allows users to effortlessly guide image generation via…
3D-GRES: Generalized 3D Referring Expression Segmentation
Changli Wu, Yihang Liu, Jiayi Ji +6
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches…
INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model
Yiwei Ma, Zhibin Wang, Xiaoshuai Sun +4
With advancements in data availability and computing resources, Multimodal Large Language Models (MLLMs) have showcased capabilities across various fields. However, the quadratic c…
Evaluating and Analyzing Relationship Hallucinations in Large Vision-Language Models
Mingrui Wu, Jiayi Ji, Oucheng Huang +4
The issue of hallucinations is a prevalent concern in existing Large Vision-Language Models (LVLMs). Previous efforts have primarily focused on investigating object hallucinations,…
Multi-branch Collaborative Learning Network for 3D Visual Grounding
Zhipeng Qian, Yiwei Ma, Zhekai Lin +4
3D referring expression comprehension (3DREC) and segmentation (3DRES) have overlapping objectives, indicating their potential for collaboration. However, existing collaborative ap…
Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model
Danni Yang, Ruohan Dong, Jiayi Ji +4
Recently, diffusion models have increasingly demonstrated their capabilities in vision understanding. By leveraging prompt-based learning to construct sentences, these models have…
ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models
Mingrui Wu, Xinyue Cai, Jiayi Ji +7
In this work, we propose a training-free method to inject visual prompts into Multimodal Large Language Models (MLLMs) through test-time optimization of a learnable latent variable…
HRSAM: Efficient Interactive Segmentation in High-Resolution Images
You Huang, Wenbin Lai, Jiayi Ji +3
The Segment Anything Model (SAM) has advanced interactive segmentation but is limited by the high computational cost on high-resolution images. This requires downsampling to meet G…
Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval
Yiwei Ma, Xiaoshuai Sun, Jiayi Ji +3
Text-based person retrieval (TPR) is a challenging task that involves retrieving a specific individual based on a textual description. Despite considerable efforts to bridge the ga…
SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentation
Danni Yang, Jiayi Ji, Yiwei Ma +4
In this paper, we introduce SemiRES, a semi-supervised framework that effectively leverages a combination of labeled and unlabeled data to perform RES. A significant hurdle in appl…
Towards Semantic Equivalence of Tokenization in Multimodal LLM
Shengqiong Wu, Hao Fei, Xiangtai Li +4
Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in processing vision-language tasks. One of the crux of MLLMs lies in vision tokenization, which…
Image Captioning via Dynamic Path Customization
Yiwei Ma, Jiayi Ji, Xiaoshuai Sun +4
This paper explores a novel dynamic network for vision and language tasks, where the inferring structure is customized on the fly for different inputs. Most previous state-of-the-a…
X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation
Yiwei Ma, Zhekai Lin, Jiayi Ji +3
Recent advancements in automatic 3D avatar generation guided by text have made significant progress. However, existing methods have limitations such as oversaturation and low-quali…