English
Related papers

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

200 papers

Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them susceptible to spurious variations -- changes in…

Machine Learning · Computer Science 2023-10-26 Chuning Zhu , Max Simchowitz , Siri Gadipudi , Abhishek Gupta

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term…

Computation and Language · Computer Science 2024-12-06 Yuhan Chen , Ang Lv , Jian Luan , Bin Wang , Wei Liu

Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Zichen Liu , Kunlun Xu , Bing Su , Xu Zou , Yuxin Peng , Jiahuan Zhou

Video stabilization is a fundamental and important technique for higher quality videos. Prior works have extensively explored video stabilization, but most of them involve cropping of the frame boundaries and introduce moderate levels of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-09 Jinsoo Choi , In So Kweon

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

Vision-Language Models (VLMs) have made significant progress in multimodal tasks. However, their performance often deteriorates in long-context scenarios, particularly long videos. While Rotary Position Embedding (RoPE) has been widely…

Machine Learning · Computer Science 2025-10-09 Haoran Li , Yingjie Qin , Baoyuan Ou , Lai Xu , Ruiwen Xu

Video diffusion models have made substantial progress in various video generation applications. However, training models for long video generation tasks require significant computational and data resources, posing a challenge to developing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yu Lu , Yuanzhi Liang , Linchao Zhu , Yi Yang

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Shaoguang Wang , Weiyu Guo , Ziyang Chen , Yijie Xu , Xuming Hu , Hui Xiong

We present \emph{Video-in-the-Loop} (ViTL), a two-stage long-video QA framework that preserves a fixed token budget by first \emph{localizing} question-relevant interval(s) with a low-fps skim and then \emph{answering} via span-aware…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Chendong Wang , Donglin Bai , Yifan Yang , Xiao Jin , Anlan Zhang , Rui Wang , Shiqi Jiang , Yuqing Yang , Hao Wu , Qi Dai , Chong Luo , Ting Cao , Lili Qiu , Suman Banerjee

Video Large Language Models (VideoLLMs) have made significant strides in video understanding but struggle with long videos due to the limitations of their backbone LLMs. Existing solutions rely on length extrapolation, which is…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xiao Wang , Qingyi Si , Jianlong Wu , Shiyu Zhu , Li Cao , Liqiang Nie

Multimodal large language models (MLLMs) represent images and video frames as visual tokens. Scaling from single images to hour-long videos, however, inflates the token budget far beyond practical limits. Popular pipelines therefore either…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Zirui Zhu , Hailun Xu , Yang Luo , Yong Liu , Kanchan Sarkar , Zhenheng Yang , Yang You

One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Nannan Zou , Honglei Zhang , Francesco Cricri , Hamed R. Tavakoli , Jani Lainema , Emre Aksu , Miska Hannuksela , Esa Rahtu

Video inpainting aims to fill spatio-temporal "corrupted" regions with plausible content. To achieve this goal, it is necessary to find correspondences from neighbouring frames to faithfully hallucinate the unknown content. Current methods…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Xueyan Zou , Linjie Yang , Ding Liu , Yong Jae Lee

Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Zhengkai Jiang , Yu Liu , Ceyuan Yang , Jihao Liu , Peng Gao , Qian Zhang , Shiming Xiang , Chunhong Pan

Despite significant advances in Multimodal Large Language Models (MLLMs), understanding complex temporal dynamics in videos remains a major challenge. Our experiments show that current Video Large Language Model (Video-LLM) architectures…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Ali Rasekh , Erfan Bagheri Soula , Omid Daliran , Simon Gottschalk , Mohsen Fayyaz

Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytically. While RS is well understood for classification, its…

Machine Learning · Computer Science 2025-09-22 Emmanouil Seferis , Changshun Wu , Stefanos Kollias , Saddek Bensalem , Chih-Hong Cheng

Non-stationary signals are ubiquitous in real life. Many techniques have been proposed in the last decades which allow decomposing multi-component signals into simple oscillatory mono-components, like the groundbreaking Empirical Mode…

Numerical Analysis · Mathematics 2024-01-30 Giovanni Barbarino , Antonio Cicone

Probabilistic amplitude shaping (PAS) is a practical means to achieve a shaping gain in optical fiber communication. However, PAS and shaping in general also affect the signal-dependent generation of nonlinear interference. This provides an…

Information Theory · Computer Science 2023-04-18 Mohammad Taha Askari , Lutz Lampe , Jeebak Mitra

Video object detection is challenging in the presence of appearance deterioration in certain video frames. Therefore, it is a natural choice to aggregate temporal information from other frames of the same video into the current frame.…

Computer Vision and Pattern Recognition · Computer Science 2021-09-14 Tao Gong , Kai Chen , Xinjiang Wang , Qi Chu , Feng Zhu , Dahua Lin , Nenghai Yu , Huamin Feng

Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Zhenghong Zhou , Jie An , Jiebo Luo