English
Related papers

Related papers: VTok: A Unified Video Tokenizer with Decoupled Spa…

200 papers

Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yunpeng Qu , Kaidong Zhang , Yukang Ding , Ying Chen , Jian Wang

Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Tianxiong Zhong , Xingye Tian , Boyuan Jiang , Xuebo Wang , Xin Tao , Pengfei Wan , Zhiwei Zhang

Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with the inherent conflict between these tasks, as a single token space is forced to support…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Yiwei Guo , Shaobin Zhuang , Zhipeng Huang , Canmiao Fu , Chen Li , Jing Lyu , Yali Wang

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Junhao Du , Jialong Xue , Anqi Li , Jincheng Dai , Guo Lu

Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Wencheng Zhu , Yuexin Wang , Hongxuan Li , Pengfei Zhu , Qinghua Hu

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

Efficient tokenization of videos remains a challenge in training vision models that can process long videos. One promising direction is to develop a tokenizer that can encode long video clips, as it would enable the tokenizer to leverage…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Huiwon Jang , Sihyun Yu , Jinwoo Shin , Pieter Abbeel , Younggyo Seo

Typical video modeling methods, such as LLava, represent videos as sequences of visual tokens, which are then processed by the LLM backbone for effective video understanding. However, this approach leads to a massive number of visual…

Computation and Language · Computer Science 2025-06-05 Hongzhi Zhang , Jingyuan Zhang , Xingguang Ji , Qi Wang , Fuzheng Zhang

VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstruction. However, improved tokenization in the first stage does…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Bin Wu , Mengqi Huang , Weinan Jia , Zhendong Mao

Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by…

Image and Video Processing · Electrical Eng. & Systems 2023-11-03 Xihua Sheng , Li Li , Dong Liu , Houqiang Li

In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. This is realized through two key designs: (1) multi-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Cong Chen , Ziyuan Huang , Cheng Zou , Muzhi Zhu , Kaixiang Ji , Jiajia Liu , Jingdong Chen , Hao Chen , Chunhua Shen

In this work, we explore the largely unexplored direction of building a generalist image tokenizer directly on top of a frozen vision foundation model (VFM). To build this tokenizer, we utilize a frozen VFM as the encoder and introduce two…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Anlin Zheng , Qi Han , Xin Wen , Chuofan Ma , Lanxi Gong , Gang Yu , Xiangyu Zhang , Xiaojuan Qi

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Jiaming Han , Hao Chen , Yang Zhao , Hanyu Wang , Qi Zhao , Ziyan Yang , Hao He , Xiangyu Yue , Lu Jiang

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Junke Wang , Dongdong Chen , Chong Luo , Bo He , Lu Yuan , Zuxuan Wu , Yu-Gang Jiang

Temporal localization in untrimmed videos, which aims to identify specific timestamps, is crucial for video understanding but remains challenging. This task encompasses several subtasks, including temporal action localization, temporal…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Chen-Lin Zhang , Lin Sui , Shuming Liu , Fangzhou Mu , Zhangcheng Wang , Bernard Ghanem

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Peiran Wu , Zhuorui Yu , Yunze Liu , Chi-Hao Wu , Enmin Zhou , Junxiao Shen

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Kevin Qinghong Lin , Pengchuan Zhang , Joya Chen , Shraman Pramanick , Difei Gao , Alex Jinpeng Wang , Rui Yan , Mike Zheng Shou

We present SceneTok, a novel tokenizer for encoding view sets of scenes into a compressed and diffusable set of unstructured tokens. Existing approaches for 3D scene representation and generation commonly use 3D data structures or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Mohammad Asim , Christopher Wewer , Jan Eric Lenssen

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Rong Fan , Kaiyan Xiao , Minghao Zhu , Liuyi Wang , Kai Dai , Zhao Yang

Vision-Language Models (VLMs) demonstrate impressive performance in understanding visual content with language instruction by converting visual inputs to vision tokens. However, redundancy in vision tokens results in the degraded inference…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Sixun Dong , Juhua Hu , Mian Zhang , Ming Yin , Yanjie Fu , Qi Qian