English
Related papers

Related papers: Cheers: Decoupling Patch Details from Semantic Rep…

200 papers

Achieving better alignment between vision embeddings and Large Language Models (LLMs) is crucial for enhancing the abilities of Multimodal LLMs (MLLMs), particularly for recent models that rely on powerful pretrained vision encoders and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Jiachen Jiang , Jinxin Zhou , Bo Peng , Xia Ning , Zhihui Zhu

Reference Expression Segmentation (RES) aims to segment image regions specified by referring expressions and has become popular with the rise of multimodal large models (MLLMs). While MLLMs excel in semantic understanding, their…

Computer Vision and Pattern Recognition · Computer Science 2025-08-20 Jingchao Wang , Zhijian Wu , Dingjiang Huang , Yefeng Zheng , Hong Wang

Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…

Computer Vision and Pattern Recognition · Computer Science 2020-08-19 Xiangtai Li , Xia Li , Li Zhang , Guangliang Cheng , Jianping Shi , Zhouchen Lin , Shaohua Tan , Yunhai Tong

Multimodal large language models (MLLMs) extend the success of language models to visual understanding, and recent efforts have sought to build unified MLLMs that support both understanding and generation. However, constructing such models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Hanyu Wang , Jiaming Han , Ziyan Yang , Qi Zhao , Shanchuan Lin , Xiangyu Yue , Abhinav Shrivastava , Zhenheng Yang , Hao Chen

Conceptual coding has been an emerging research topic recently, which encodes natural images into disentangled conceptual representations for compression. However, the compression performance of the existing methods is still sub-optimal due…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Jianhui Chang , Zhenghui Zhao , Lingbo Yang , Chuanmin Jia , Jian Zhang , Siwei Ma

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Neha Kalibhat , Priyatham Kattakinda , Sumit Nawathe , Arman Zarei , Nikita Seleznev , Samuel Sharpe , Senthil Kumar , Soheil Feizi

Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal tasks, while recent multi-encoder fusion methods introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yuchen Liu , Yaoming Wang , Bowen Shi , Xiaopeng Zhang , Wenrui Dai , Chenglin Li , Hongkai Xiong , Qi Tian

The fashion domain encompasses a variety of real-world multimodal tasks, including multimodal retrieval and multimodal generation. The rapid advancements in artificial intelligence generated content, particularly in technologies like large…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Xiangyu Zhao , Yuehan Zhang , Wenlong Zhang , Xiao-Ming Wu

Despite the success of vision-language models in various generative tasks, obtaining high-quality semantic representations for products and user intents is still challenging due to the inability of off-the-shelf models to capture nuanced…

Information Retrieval · Computer Science 2025-11-07 Omkar Gurjar , Kin Sum Liu , Praveen Kolli , Utsaw Kumar , Mandar Rahurkar

"Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression efficiency often correlates with improved model performance…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Xin Jin , Jinming Liu , Yuntao Wei , Junyan Lin , Zhicheng Wang , Jianguo Huang , Xudong Yang , Yanxiao Liu , Wenjun Zeng

The encode-decoder framework has shown recent success in image captioning. Visual attention, which is good at detailedness, and semantic attention, which is good at comprehensiveness, have been separately proposed to ground the caption on…

Computation and Language · Computer Science 2018-08-28 Fenglin Liu , Xuancheng Ren , Yuanxin Liu , Houfeng Wang , Xu Sun

Joint rendering and deformation of mesh and 3D Gaussian Splatting (3DGS) have significant value as both representa tions offer complementary advantages for graphics applica tions. However, due to differences in representation and ren dering…

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Robin Strudel , Ricardo Garcia , Ivan Laptev , Cordelia Schmid

High-quality image captions play a crucial role in improving the performance of cross-modal applications such as text-to-image generation, text-to-video generation, and text-image retrieval. To generate long-form, high-quality captions,…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ruotian Peng , Haiying He , Yake Wei , Yandong Wen , Di Hu

Semantic understanding of 3D scenes is essential for robots to operate effectively and safely in complex environments. Existing methods for semantic scene reconstruction and semantic-aware novel view synthesis often rely on dense multi-view…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Sheng Ye , Zhen-Hui Dong , Ruoyu Fan , Tian Lv , Yong-Jin Liu

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 Naifu Xue , Qi Mao , Zijian Wang , Yuan Zhang , Siwei Ma

Multi-sensor clues have shown promise for object segmentation, but inherent noise in each sensor, as well as the calibration error in practice, may bias the segmentation accuracy. In this paper, we propose a novel approach by mining the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Zongwei Wu , Jingjing Wang , Zhuyun Zhou , Zhaochong An , Qiuping Jiang , Cédric Demonceaux , Guolei Sun , Radu Timofte

Vision transformers (ViTs) encoding an image as a sequence of patches bring new paradigms for semantic segmentation.We present an efficient framework of representation separation in local-patch level and global-region level for semantic…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Yuanduo Hong , Huihui Pan , Weichao Sun , Xinghu Yu , Huijun Gao

Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling task. While various deep learning approaches have…

Machine Learning · Computer Science 2023-07-04 Gabriele Dominici , Pietro Barbiero , Lucie Charlotte Magister , Pietro Liò , Nikola Simidjievski