English
Related papers

Related papers: RefTok: Reference-Based Tokenization for Video Gen…

200 papers

Effective video tokenization is critical for scaling transformer models for long videos. Current approaches tokenize videos using space-time patches, leading to excessive tokens and computational inefficiencies. The best token reduction…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Chenhao Zheng , Jieyu Zhang , Mohammadreza Salehi , Ziqi Gao , Vishnu Iyengar , Norimasa Kobori , Quan Kong , Ranjay Krishna

Despite advancements in Text-to-Video (T2V) generation, producing videos with realistic motion remains challenging. Current models often yield static or minimally dynamic outputs, failing to capture complex motions described by text. This…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Penghui Ruan , Pichao Wang , Divya Saxena , Jiannong Cao , Yuhui Shi

Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow generation speed and large cumulative error. Furthermore,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Junbo Wang , Liangyu Fu , Yuke Li , Yining Zhu , Ya Jing , Xuecheng Wu , Jiangbin Zheng

Referring Video Object Segmentation (R-VOS) methods face challenges in maintaining consistent object segmentation due to temporal context variability and the presence of other visually similar objects. We propose an end-to-end R-VOS…

Computer Vision and Pattern Recognition · Computer Science 2024-10-14 Bo Miao , Mohammed Bennamoun , Yongsheng Gao , Mubarak Shah , Ajmal Mian

We present a novel perspective on learning video embedders for generative modeling: rather than requiring an exact reproduction of an input video, an effective embedder should focus on synthesizing visually plausible reconstructions. This…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yitian Zhang , Long Mai , Aniruddha Mahapatra , David Bourgin , Yicong Hong , Jonah Casebeer , Feng Liu , Yun Fu

In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two challenging visual contents: text and face. Visual tokenizers…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Junfeng Wu , Dongliang Luo , Weizhi Zhao , Zhihao Xie , Yuanhao Wang , Junyi Li , Xudong Xie , Yuliang Liu , Xiang Bai

Neural Representations for Videos(NeRV) have emerged as a promising paradigm for video compression by representing videos as compact neural networks with efficient decoding. Hybrid NeRV methods further improve reconstruction quality through…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Yunjie Xu , Xiang Feng , Chengkai Wang , Alan Wee-Chung Liew , Xuefei Yin , Yanming Zhu

Synthesizing motion-rich and temporally consistent videos remains a challenge in artificial intelligence, especially when dealing with extended durations. Existing text-to-video (T2V) models commonly employ spatial cross-attention for text…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Jiasong Feng , Ao Ma , Jing Wang , Ke Cao , Zhanjie Zhang

Robotic world models are a promising paradigm for forecasting future environment states, yet their inference speed and the physical plausibility of generated trajectories remain critical bottlenecks, limiting their real-world applications.…

Robotics · Computer Science 2025-09-26 Sibo Li , Qianyue Hao , Yu Shang , Yong Li

Point tracking aims to localize corresponding points across video frames, serving as a fundamental task for 4D reconstruction, robotics, and video editing. Existing methods commonly rely on shallow convolutional backbones such as ResNet…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Soowon Son , Honggyu An , Chaehyun Kim , Hyunah Ko , Jisu Nam , Dahyun Chung , Siyoon Jin , Jung Yi , Jaewon Min , Junhwa Hur , Seungryong Kim

We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech. The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding…

Graphics · Computer Science 2025-03-31 Yong Xie , Yunlian Sun , Hongwen Zhang , Yebin Liu , Jinhui Tang

The video generation task can be formulated as a prediction of future video frames given some past frames. Recent generative models for videos face the problem of high computational requirements. Some models require up to 512 Tensor…

Computer Vision and Pattern Recognition · Computer Science 2020-06-20 Ruslan Rakhimov , Denis Volkhonskiy , Alexey Artemov , Denis Zorin , Evgeny Burnaev

Autoregressive (AR) video diffusion has recently emerged as a promising paradigm for long video generation, enabling causal synthesis beyond the limits of bidirectional models. To address training-inference mismatch, a series of…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Zengqun Zhao , Yanzuo Lu , Ziquan Liu , Jifei Song , Jiankang Deng , Ioannis Patras

Packet loss during video conferencing often results in poor quality and video freezing. Retransmitting lost packets is often impractical due to the need for real-time playback, and using Forward Error Correction (FEC) for packet recovery is…

Networking and Internet Architecture · Computer Science 2024-10-08 Tianhong Li , Vibhaalakshmi Sivaraman , Pantea Karimi , Lijie Fan , Mohammad Alizadeh , Dina Katabi

Building on recent advances in video generation, generative video compression has emerged as a new paradigm for achieving visually pleasing reconstructions. However, existing methods exhibit limited exploitation of temporal correlations,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Xiaoyue Ling , Chuqin Zhou , Chunyi Li , Yunuo Chen , Yuan Tian , Guo Lu , Wenjun Zhang

Most text-video retrieval methods utilize the text-image pre-trained models like CLIP as a backbone. These methods process each sampled frame independently by the image encoder, resulting in high computational overhead and limiting…

Computer Vision and Pattern Recognition · Computer Science 2025-03-13 Leqi Shen , Tianxiang Hao , Tao He , Sicheng Zhao , Yifeng Zhang , Pengzhang Liu , Yongjun Bao , Guiguang Ding

This paper studies the BERT pretraining of video transformers. It is a straightforward but worth-studying extension given the recent success from BERT pretraining of image transformers. We introduce BEVT which decouples video representation…

Computer Vision and Pattern Recognition · Computer Science 2022-03-04 Rui Wang , Dongdong Chen , Zuxuan Wu , Yinpeng Chen , Xiyang Dai , Mengchen Liu , Yu-Gang Jiang , Luowei Zhou , Lu Yuan

Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-05 Juhun Lee , Simon S. Woo

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

Producing prompt-faithful videos that preserve a user-specified identity remains challenging: models need to extrapolate facial dynamics from sparse reference while balancing the tension between identity preservation and motion naturalness.…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Yixuan Lai , He Wang , Kun Zhou , Tianjia Shao