Cover Image

DeRA: Decoupled Representation Alignment for Video Tokenization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Pengbo, Wang, Junke, Xing, Zhen, Liu, Chengxu, Dong, Daoguo, Qian, Xueming, Wu, Zuxuan
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

QueryCDR: Query-Based Controllable Distortion Rectification Network for Fisheye Images
by: Guo, Pengbo, et al.
Published: (2024)

Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera
by: Liu, Chengxu, et al.
Published: (2024)

OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
by: Wang, Junke, et al.
Published: (2024)

Exploring Spectral Characteristics for Single Image Reflection Removal
by: Guo, Pengbo, et al.
Published: (2025)

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
by: Li, Quanhao, et al.
Published: (2026)

UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling
by: Sun, Zhihao, et al.
Published: (2026)

VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
by: Shi, Jiapeng, et al.
Published: (2026)

Preserving Cross-Modal Consistency for CLIP-based Class-Incremental Learning
by: Chen, Haoran, et al.
Published: (2025)

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis
by: Zheng, Peng, et al.
Published: (2025)

AdaDiffSR: Adaptive Region-aware Dynamic Acceleration Diffusion Model for Real-World Image Super-Resolution
by: Fan, Yuanting, et al.
Published: (2024)

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
by: Xie, Yiweng, et al.
Published: (2026)

TempoMaster: Efficient Long Video Generation via Next-Frame-Rate Prediction
by: Ma, Yukuo, et al.
Published: (2025)

OmniVid: A Generative Framework for Universal Video Understanding
by: Wang, Junke, et al.
Published: (2024)

FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
by: Zheng, Peng, et al.
Published: (2025)

Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model
by: Liu, Chengxu, et al.
Published: (2025)

Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing
by: Liu, Chengxu, et al.
Published: (2025)

Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference
by: Leng, Jiaqi, et al.
Published: (2026)

DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning
by: Qian, Chengxuan, et al.
Published: (2025)

TSAL: Few-shot Text Segmentation Based on Attribute Learning
by: Li, Chenming, et al.
Published: (2025)

GenRec: Unifying Video Generation and Recognition with Diffusion Models
by: Weng, Zejia, et al.
Published: (2024)

VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
by: Wang, Feng, et al.
Published: (2026)

Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning
by: You, Zuyao, et al.
Published: (2025)

Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
by: Wu, Yihang, et al.
Published: (2026)

Dual Relation Alignment for Composed Image Retrieval
by: Jiang, Xintong, et al.
Published: (2023)

SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
by: Wang, Junke, et al.
Published: (2025)

GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting
by: Feng, Qijun, et al.
Published: (2024)

OmniTracker: Unifying Object Tracking by Tracking-with-Detection
by: Wang, Junke, et al.
Published: (2023)

PromptFusion: Decoupling Stability and Plasticity for Continual Learning
by: Chen, Haoran, et al.
Published: (2023)

Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
by: Tu, Xuezhen, et al.
Published: (2026)

TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation
by: Li, Ruineng, et al.
Published: (2025)

Decoupled Seg Tokens Make Stronger Reasoning Video Segmenter and Grounder
by: Jisheng, Dang, et al.
Published: (2025)

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
by: Zhao, Haoyu, et al.
Published: (2023)

CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization
by: Chen, Yitong, et al.
Published: (2026)

Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
by: Liu, Chengxu, et al.
Published: (2024)

RefAlign: Representation Alignment for Reference-to-Video Generation
by: Wang, Lei, et al.
Published: (2026)

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
by: Li, Quanhao, et al.
Published: (2025)

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation
by: Chen, Haoran, et al.
Published: (2022)

Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
by: Xiao, Junyuan, et al.
Published: (2026)

TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
by: Zhang, Bingqing, et al.
Published: (2024)

Multi-Prompt Progressive Alignment for Multi-Source Unsupervised Domain Adaptation
by: Chen, Haoran, et al.
Published: (2025)