7 citations · 21 across the 14 of their papers we have counts for
14 papers · 1 filter
DenseWorld-1M: Towards Detailed Dense Grounded Caption in the Real World
Xiangtai Li, Tao Zhang, Yanwei Li +13
Multimodal Large Language Models (MLLMs) demonstrate a complex understanding of scenes, benefiting from large-scale and high-quality datasets. Most existing caption datasets lack t…
MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
Wei Chow, Yuan Gao, Linfeng Li +15
Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular r…
On Path to Multimodal Generalist: General-Level and General-Bench
Hao Fei, Yuan Zhou, Juncheng Li +29
The Multimodal Large Language Model (MLLM) is currently experiencing rapid growth, driven by the advanced capabilities of LLMs. Unlike earlier specialists, existing MLLMs are evolv…
An Empirical Study of GPT-4o Image Generation Capabilities
Sixiang Chen, Jinbin Bai, Zhuoran Zhao +16
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to brid…
4th PVUW MeViS 3rd Place Report: Sa2VA
Haobo Yuan, Tao Zhang, Xiangtai Li +5
Referring video object segmentation (RVOS) is a challenging task that requires the model to segment the object in a video given the language description. MeViS is a recently propos…
Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
Yikang Zhou, Tao Zhang, Shilin Xu +7
Recent advancements in multimodal large language models (MLLM) have shown a strong ability in visual perception, reasoning abilities, and vision-language understanding. However, th…
Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos
Haobo Yuan, Xiangtai Li, Tao Zhang +8
This work presents Sa2VA, the first comprehensive, unified model for dense grounded understanding of both images and videos. Unlike existing multi-modal large language models, whic…
An Open and Comprehensive Pipeline for Unified Object Grounding and Detection
Xiangyu Zhao, Yicheng Chen, Shilin Xu +4
Grounding-DINO is a state-of-the-art open-set detection model that tackles multiple vision tasks including Open-Vocabulary Detection (OVD), Phrase Grounding (PG), and Referring Exp…
RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
Shilin Xu, Haobo Yuan, Qingyu Shi +9
Recent segmentation methods, which adopt large-scale data training and transformer architecture, aim to create one foundation model that can perform multiple tasks. However, most o…
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
Shilin Xu, Xiangtai Li, Size Wu +3
Open-vocabulary object detection (OVOD) aims to detect the objects beyond the set of classes observed during training. This work introduces a straightforward and efficient strategy…
Towards Open Vocabulary Learning: A Survey
Jianzong Wu, Xiangtai Li, Shilin Xu +9
In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However, most a…
PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang +6
Panoptic Part Segmentation (PPS) unifies panoptic and part segmentation into one task. Previous works utilize separate approaches to handle things, stuff, and part predictions with…
Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation
Xiangtai Li, Shilin Xu, Yibo Yang +3
Panoptic Part Segmentation (PPS) aims to unify panoptic segmentation and part segmentation into one task. Previous work mainly utilizes separated approaches to handle thing, stuff,…
Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition
Shilin Xu, Xiangtai Li, Jingbo Wang +3
Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation a…