English
Related papers

Related papers: Uni-AdaFocus: Spatial-temporal Dynamic Computation…

200 papers

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods…

Computer Vision and Pattern Recognition · Computer Science 2024-04-26 Yang Luo , Zhineng Chen , Peng Zhou , Zuxuan Wu , Xieping Gao , Yu-Gang Jiang

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-30 Syed Talal Wasim , Muhammad Uzair Khattak , Muzammal Naseer , Salman Khan , Mubarak Shah , Fahad Shahbaz Khan

As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Gen Li , Jie Ji , Minghai Qin , Wei Niu , Bin Ren , Fatemeh Afghah , Linke Guo , Xiaolong Ma

In this paper, we present a new approach for model acceleration by exploiting spatial sparsity in visual data. We observe that the final prediction in vision Transformers is only based on a subset of the most informative tokens, which is…

Computer Vision and Pattern Recognition · Computer Science 2023-06-05 Yongming Rao , Zuyan Liu , Wenliang Zhao , Jie Zhou , Jiwen Lu

Unsupervised Domain Adaptive Semantic Segmentation (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain. The majority of existing UDA-SS works typically consider images whilst recent attempts…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Zhe Zhang , Gaochang Wu , Jing Zhang , Xiatian Zhu , Dacheng Tao , Tianyou Chai

Diffusion models are just at a tipping point for image super-resolution task. Nevertheless, it is not trivial to capitalize on diffusion models for video super-resolution which necessitates not only the preservation of visual appearance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Zhikai Chen , Fuchen Long , Zhaofan Qiu , Ting Yao , Wengang Zhou , Jiebo Luo , Tao Mei

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Gedas Bertasius , Heng Wang , Lorenzo Torresani

Sequential decision-making can be formulated as a text-conditioned video generation problem, where a video planner, guided by a text-defined goal, generates future frames visualizing planned actions, from which control actions are…

Computer Vision and Pattern Recognition · Computer Science 2025-01-31 Shuaiyi Huang , Mara Levy , Zhenyu Jiang , Anima Anandkumar , Yuke Zhu , Linxi Fan , De-An Huang , Abhinav Shrivastava

Deep-learning-based video processing has yielded transformative results in recent years. However, the video analytics pipeline is energy-intensive due to high data rates and reliance on complex inference algorithms, which limits its…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Yingying Zhao , Mingzhi Dong , Yujiang Wang , Da Feng , Qin Lv , Robert P. Dick , Dongsheng Li , Tun Lu , Ning Gu , Li Shang

We propose a dynamic computational time model to accelerate the average processing time for recurrent visual attention (RAM). Rather than attention with a fixed number of steps for each input image, the model learns to decide when to stop…

Computer Vision and Pattern Recognition · Computer Science 2017-09-08 Zhichao Li , Yi Yang , Xiao Liu , Feng Zhou , Shilei Wen , Wei Xu

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Yizeng Han , Zhihang Yuan , Yifan Pu , Chenhao Xue , Shiji Song , Guangyu Sun , Gao Huang

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…

Computer Vision and Pattern Recognition · Computer Science 2019-03-05 Chao Li , Qiaoyong Zhong , Di Xie , Shiliang Pu

Video-to-video synthesis poses significant challenges in maintaining character consistency, smooth temporal transitions, and preserving visual quality during fast motion. While recent fully cross-frame self-attention mechanisms have…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Tanvir Mahmud , Mustafa Munir , Radu Marculescu , Diana Marculescu

While transformers have shown great potential on video recognition with their strong capability of capturing long-range dependencies, they often suffer high computational costs induced by the self-attention to the huge number of 3D tokens.…

Computer Vision and Pattern Recognition · Computer Science 2022-11-23 Yuxuan Liang , Pan Zhou , Roger Zimmermann , Shuicheng Yan

Standard approaches for video recognition usually operate on the full input videos, which is inefficient due to the widely present spatio-temporal redundancy in videos. Recent progress in masked video modelling, i.e., VideoMAE, has shown…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Zhiwu Qing , Shiwei Zhang , Ziyuan Huang , Xiang Wang , Yuehuan Wang , Yiliang Lv , Changxin Gao , Nong Sang

Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…

Machine Learning · Computer Science 2020-08-21 Jinhua Liang , Tao Zhang , Guoqing Feng

A recent endeavor in one class of video anomaly detection is to leverage diffusion models and posit the task as a generation problem, where the diffusion model is trained to recover normal patterns exclusively, thus reporting abnormal…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Hang Zhou , Jiale Cai , Yuteng Ye , Yonghui Feng , Chenxing Gao , Junqing Yu , Zikai Song , Wei Yang

This paper identifies two kinds of redundancy in the current VideoQA paradigm. Specifically, the current video encoders tend to holistically embed all video clues at different granularities in a hierarchical manner, which inevitably…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Yicong Li , Xun Yang , An Zhang , Chun Feng , Xiang Wang , Tat-Seng Chua

Video anomaly detection is recently formulated as a multiple instance learning task under weak supervision, in which each video is treated as a bag of snippets to be determined whether contains anomalies. Previous efforts mainly focus on…

Computer Vision and Pattern Recognition · Computer Science 2022-08-12 Yujiang Pu , Xiaoyu Wu

In video segmentation, generating temporally consistent results across frames is as important as achieving frame-wise accuracy. Existing methods rely either on optical flow regularization or fine-tuning with test data to attain temporal…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Yizhe Zhang , Shubhankar Borse , Hong Cai , Fatih Porikli