English
Related papers

Related papers: PAS: A Training-Free Stabilizer for Temporal Encod…

200 papers

Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mitigate data labelling constraints by adapting from a labelled…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Yun Xing , Dayan Guan , Jiaxing Huang , Shijian Lu

Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process…

Computation and Language · Computer Science 2025-10-07 Jinyi Han , Xinyi Wang , Haiquan Zhao , Tingyun li , Zishang Jiang , Sihang Jiang , Jiaqing Liang , Xin Lin , Weikang Zhou , Zeye Sun , Fei Yu , Yanghua Xiao

Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Xinyu Chen , Yuyi Qian , Jiang Lin , Shenyi Wang , Gao Wang , Zhiqiu Zhang , Jizhi Zhang , Mingjie Wang , Qiang Tang , Qian Wang , Song Wu , Zili Yi

Image and video quality in Long Range Observation Systems (LOROS) suffer from atmospheric turbulence that causes small neighbourhoods in image frames to chaotically move in different directions and substantially hampers visual analysis of…

Optics · Physics 2010-07-27 Barak Fishbain , Leonid P. Yaroslavsky , Ianir A. Ideses

Many recent text-to-speech (TTS) systems are built on transformer architectures and employ cross-attention mechanisms for text-speech alignment. Within these systems, rotary position embedding (RoPE) is commonly used to encode positional…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Hyeongju Kim , Juheon Lee , Jinhyeok Yang , Jacob Morton

In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Shaofei Huang , Rui Ling , Hongyu Li , Tianrui Hui , Zongheng Tang , Xiaoming Wei , Jizhong Han , Si Liu

Current state-of-the-art approaches to video understanding adopt temporal jittering to simulate analyzing the video at varying frame rates. However, this does not work well for multirate videos, in which actions or subactions occur at…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Yi Zhu , Shawn Newsam

Video generation, while capable of generating realistic videos, is computationally expensive and slow, prohibiting real-time applications. In this paper, we observe that video latents encoded via an autoencoder under the Latent Diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Dennis Menn , Chih-Hsien Chou

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ming Nie , Dan Ding , Chunwei Wang , Yuanfan Guo , Jianhua Han , Hang Xu , Li Zhang

Video anomaly detection (VAD) aims to identify abnormal events in videos. Traditional VAD methods generally suffer from the high costs of labeled data and full training, thus some recent works have explored leveraging frozen multi-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Zhaolin Cai , Fan Li , Huiyu Duan , Lijun He , Guangtao Zhai

Magnetic Resonance Imaging (MRI) is a cornerstone in medicine and healthcare but suffers from long acquisition times. Traditional accelerated MRI methods optimize for generic image quality, lacking adaptability for specific clinical tasks.…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Fangmao Ju , Yuzhu He , Zhiwen Xue , Chunfeng Lian , Jianhua Ma

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-21 Mirco Ravanelli , Jianyuan Zhong , Santiago Pascual , Pawel Swietojanski , Joao Monteiro , Jan Trmal , Yoshua Bengio

Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Jangho Park , Geon Yeong Park , Gihyun Kwon , Jong Chul Ye

Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging due to interleaved inference and noisy log-probability…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Xiaoxiao Ma , Jiachen Lei , Tianfei Ren , Jie Huang , Siming Fu , Aiming Hao , Jiahong Wu , Xiangxiang Chu , Feng Zhao

Randomized Smoothing (RS) offers formal $\ell_2$ guarantees for arbitrary base classifiers but faces two key practical bottlenecks: (i) it often relies on noise-augmented training to achieve nontrivial certificates, which increases training…

Machine Learning · Computer Science 2026-04-29 Miao Lin , MD Saifur Rahman Mazumder , Feng Yu , Daniel Takabi , Rui Ning

We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Hanyu Wang , Saksham Suri , Yixuan Ren , Hao Chen , Abhinav Shrivastava

Video large language models (LLMs) achieve strong video understanding by leveraging a large number of spatio-temporal tokens, but suffer from quadratic computational scaling with token count. To address this, we propose a training-free…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Jeongseok Hyun , Sukjun Hwang , Su Ho Han , Taeoh Kim , Inwoong Lee , Dongyoon Wee , Joon-Young Lee , Seon Joo Kim , Minho Shim

Videos captured by consumer cameras often exhibit temporal variations in color and tone that are caused by camera auto-adjustments like white-balance and exposure. When such videos are sub-sampled to play fast-forward, as in the…

Graphics · Computer Science 2017-10-02 Xuaner Cecilia Zhang , Joon-Young Lee , Kalyan Sunkavalli , Zhaowen Wang

Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs). While various methods have been proposed to adapt RoPE to longer contexts, their guiding principles generally fall into two…

Computation and Language · Computer Science 2026-02-06 Haoran Li , Sucheng Ren , Alan Yuille , Feng Wang

The video composition task aims to integrate specified foregrounds and backgrounds from different videos into a harmonious composite. Current approaches, predominantly trained on videos with adjusted foreground color and lighting, struggle…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Jiaqi Guo , Sitong Su , Junchen Zhu , Lianli Gao , Jingkuan Song