6 citations · 18 across the 21 of their papers we have counts for
21 papers
X-SAM: From Segment Anything to Any Segmentation
Hao Wang, Limeng Qiao, Zequn Jie +6
Large Language Models (LLMs) demonstrate strong capabilities in broad knowledge representation, yet they are inherently deficient in pixel-level perceptual understanding. Although…
Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation
Jinlong Li, Dong Zhao, Qi Zang +3
Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios with changing target distributions. Existing CTTA met…
UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
Yang Jiao, Haibo Qiu, Zequn Jie +4
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integratio…
Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
Jiaming Li, Jiacheng Zhang, Zequn Jie +2
Large vision-language models (LVLMs) have shown remarkable capabilities in visual-language understanding. Despite their success, LVLMs still suffer from generating hallucinations i…
RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving
Zhijian Huang, Chengjian Feng, Feng Yan +5
Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despit…
TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability
Shimin Chen, Xiaohan Lan, Yitian Yuan +2
Rapid development of large language models (LLMs) has significantly advanced multimodal large language models (LMMs), particularly in vision-language tasks. However, existing video…
VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models
Xiaohan Lan, Yitian Yuan, Zequn Jie +1
Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of…
MRStyle: A Unified Framework for Color Style Transfer with Multi-Modality Reference
Jiancheng Huang, Yu Gao, Zequn Jie +3
In this paper, we introduce MRStyle, a comprehensive framework that enables color style transfer using multi-modality reference, including image and text. To achieve a unified styl…
3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance
Xiaoxu Xu, Yitian Yuan, Jinlong Li +6
In this paper, we propose 3DSS-VLG, a weakly supervised approach for 3D Semantic Segmentation with 2D Vision-Language Guidance, an alternative approach that a 3D model predicts den…
Making Large Language Models Better Planners with Reasoning-Decision Alignment
Zhijian Huang, Tao Tang, Shaoxiang Chen +5
Data-driven approaches for autonomous driving (AD) have been widely adopted in the past decade but are confronted with dataset bias and uninterpretability. Inspired by the knowledg…
OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion
Hao Wang, Pengzhen Ren, Zequn Jie +8
Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods…
MindBench: A Comprehensive Benchmark for Mind Map Structure Recognition and Analysis
Lei Chen, Feng Yan, Yujie Zhong +3
Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text…
Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization
Jinlong Li, Dong Zhao, Zequn Jie +3
Efficient fine-tuning of vision-language models (VLMs) like CLIP for specific downstream tasks is gaining significant attention. Previous works primarily focus on prompt learning t…
Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models
Shimin Chen, Yitian Yuan, Shaoxiang Chen +2
Amidst the advancements in image-based Large Vision-Language Models (image-LVLM), the transition to video-based models (video-LVLM) is hindered by the limited availability of quali…
AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
Duojun Huang, Xinyu Xiong, Jie Ma +4
Powered by massive curated training data, Segment Anything Model (SAM) has demonstrated its impressive generalization capabilities in open-world scenarios with the guidance of prom…
Matten: Video Generation with Mamba-Attention
Yu Gao, Jiancheng Huang, Xiaopeng Sun +3
In this paper, we introduce Matten, a cutting-edge latent diffusion model with Mamba-Attention architecture for video generation. With minimal computational cost, Matten employs sp…
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
Yang Jiao, Shaoxiang Chen, Zequn Jie +3
Large Multimodal Model (LMM) is a hot research topic in the computer vision area and has also demonstrated remarkable potential across multiple disciplinary fields. A recent trend…
InstaGen: Enhancing Object Detection by Training on Synthetic Dataset
Chengjian Feng, Yujie Zhong, Zequn Jie +2
In this paper, we present a novel paradigm to enhance the ability of object detector, e.g., expanding categories or improving detection performance, by training on synthetic datase…
LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs
Shaoxiang Chen, Zequn Jie, Lin Ma
Instruction finetuning on a variety of image-text instruction data is the key to obtaining a versatile Multimodal Large Language Model (MLLM), and different configurations of the i…
Instance-aware Multi-Camera 3D Object Detection with Structural Priors Mining and Self-Boosting Learning
Yang Jiao, Zequn Jie, Shaoxiang Chen +4
Camera-based bird-eye-view (BEV) perception paradigm has made significant progress in the autonomous driving field. Under such a paradigm, accurate BEV representation construction…
Weakly-Supervised 3D Visual Grounding based on Visual Language Alignment
Xiaoxu Xu, Yitian Yuan, Qiudan Zhang +4
Learning to ground natural language queries to target objects or regions in 3D point clouds is quite essential for 3D scene understanding. Nevertheless, existing 3D visual groundin…