English
Related papers

Related papers: OmniTokenizer: A Joint Image-Video Tokenizer for V…

200 papers

Existing Image Manipulation Localization (IML) methods mostly rely heavily on task-specific designs, making them perform well only on the target IML task, while joint training on multiple IML tasks causes significant performance…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Chenfan Qu , Yiwu Zhong , Fengjun Guo , Lianwen Jin

Human visual recognition system shows astonishing capability of compressing visual information into a set of tokens containing rich representations without label supervision. One critical driving principle behind it is perceptual grouping.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-26 Zhiwei Deng , Ting Chen , Yang Li

Building joint representations across images and text is an essential step for tasks such as Visual Question Answering and Video Question Answering. In this work, we find that the representations must not only jointly capture features from…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Vardaan Pahuja , AJ Piergiovanni , Anelia Angelova

Vision transformers have been widely explored in various vision tasks. Due to heavy computational cost, much interest has aroused for compressing vision transformer dynamically in the aspect of tokens. Current methods mainly pay attention…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Fanhu Zeng , Deli Yu , Zhenglun Kong , Hao Tang

Masked Image Modeling (MIM) with Vector Quantization (VQ) has achieved great success in both self-supervised pre-training and image generation. However, most existing methods struggle to address the trade-off in shared latent space for…

Computer Vision and Pattern Recognition · Computer Science 2025-04-02 Siyuan Li , Luyuan Zhang , Zedong Wang , Juanxi Tian , Cheng Tan , Zicheng Liu , Chang Yu , Qingsong Xie , Haonan Lu , Haoqian Wang , Zhen Lei

This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control…

Machine Learning · Computer Science 2024-11-01 Zihao Wang , Shaofei Cai , Zhancun Mu , Haowei Lin , Ceyao Zhang , Xuejie Liu , Qing Li , Anji Liu , Xiaojian Ma , Yitao Liang

Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Risab Biswas , Swalpa Kumar Roy , Umapada Pal

Current vision systems typically assign fixed-length representations to images, regardless of the information content. This contrasts with human intelligence - and even large language models - which allocate varying representational…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Shivam Duggal , Phillip Isola , Antonio Torralba , William T. Freeman

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of…

Computation and Language · Computer Science 2024-06-21 Abul Hasan , Jinge Wu , Quang Ngoc Nguyen , Salomé Andres , Imane Guellil , Huayu Zhang , Arlene Casey , Beatrice Alex , Bruce Guthrie , Honghan Wu

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Yaqi Zhao , Wang Lin , Zijian Zhang , Miles Yang , Jingyuan Chen , Wentao Zhang , Zhao Zhong , Liefeng Bo

We present pure-transformer based models for video classification, drawing upon the recent success of such models in image classification. Our model extracts spatio-temporal tokens from the input video, which are then encoded by a series of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Anurag Arnab , Mostafa Dehghani , Georg Heigold , Chen Sun , Mario Lučić , Cordelia Schmid

Latent generative models have shown remarkable progress in high-fidelity image synthesis, typically using a two-stage training process that involves compressing images into latent embeddings via learned tokenizers in the first stage. The…

Computer Vision and Pattern Recognition · Computer Science 2025-09-12 Tejaswini Medi , Hsien-Yi Wang , Arianna Rampini , Margret Keuper

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

Vanilla autoregressive image generation models generate visual tokens step-by-step, limiting their ability to capture holistic relationships among token sequences. Moreover, because most visual tokenizers map local image patches into latent…

Computer Vision and Pattern Recognition · Computer Science 2025-07-14 Anlin Zheng , Haochen Wang , Yucheng Zhao , Weipeng Deng , Tiancai Wang , Xiangyu Zhang , Xiaojuan Qi

We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Yue Zhao , Yuanjun Xiong , Philipp Krähenbühl

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However, existing methods encounter challenges in…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Peng Jin , Ryuichi Takanobu , Wancai Zhang , Xiaochun Cao , Li Yuan

Solving image-to-3D from a single view is an ill-posed problem, and current neural reconstruction methods addressing it through diffusion models still rely on scene-specific optimization, constraining their generalization capability. To…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Christian Simon , Sen He , Juan-Manuel Perez-Rua , Mengmeng Xu , Amine Benhalloum , Tao Xiang

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire network. This process can…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Yi Tay , Mostafa Dehghani , Vamsi Aribandi , Jai Gupta , Philip Pham , Zhen Qin , Dara Bahri , Da-Cheng Juan , Donald Metzler

The practical deployment of medical vision-language models (Med-VLMs) necessitates seamless integration of textual data with diverse visual modalities, including 2D/3D images and videos, yet existing models typically employ separate…

Computation and Language · Computer Science 2025-04-22 Songtao Jiang , Yuan Wang , Sibo Song , Yan Zhang , Zijie Meng , Bohan Lei , Jian Wu , Jimeng Sun , Zuozhu Liu

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Yancheng Wang , Yingzhen Yang