English
Related papers

Related papers: PNL: Efficient Long-Range Dependencies Extraction …

200 papers

Training deep neural networks (DNNs) using traditional backpropagation (BP) presents challenges in terms of computational complexity and energy consumption, particularly for on-device learning where computational resources are limited.…

Neural and Evolutionary Computing · Computer Science 2025-07-08 Marco Paul E. Apolinario , Arani Roy , Kaushik Roy

Temporal modeling still remains challenging for action recognition in videos. To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal…

Computer Vision and Pattern Recognition · Computer Science 2021-04-02 Limin Wang , Zhan Tong , Bin Ji , Gangshan Wu

Optical flow estimation is an important yet challenging problem in the field of video analytics. The features of different semantics levels/layers of a convolutional neural network can provide information of different granularity. To…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 Xiaolin Song , Yuyang Zhao , Jingyu Yang , Cuiling Lan , Wenjun Zeng

Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complexity and computational demands of video data. While…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Kai Han , Jianyuan Guo , Yehui Tang , Wei He , Enhua Wu , Yunhe Wang

The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks. Although having shown excellent performances, they lack the mechanism to encode the rich, structured information among…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Lei Zhu , Qi She , Lidan Zhang , Ping Guo

Inspired by the success of recent vision transformers and large kernel design in convolutional neural networks (CNNs), in this paper, we analyze and explore essential reasons for their success. We claim two factors that are critical for 3D…

Computer Vision and Pattern Recognition · Computer Science 2023-01-18 Xiang-Li Li , Meng-Hao Guo , Tai-Jiang Mu , Ralph R. Martin , Shi-Min Hu

This paper studies the joint learning of action recognition and temporal localization in long, untrimmed videos. We employ a multi-task learning framework that performs the three highly related steps of action proposal, action recognition,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-05 Yi Zhu , Shawn Newsam

With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…

Computer Vision and Pattern Recognition · Computer Science 2020-02-11 Qian Liu , Tao Wang , Jie Liu , Yang Guan , Qi Bu , Longfei Yang

Despite the success of deep learning for static image understanding, it remains unclear what are the most effective network architectures for the spatial-temporal modeling in videos. In this paper, in contrast to the existing CNN+RNN or…

Computer Vision and Pattern Recognition · Computer Science 2018-12-12 Dongliang He , Zhichao Zhou , Chuang Gan , Fu Li , Xiao Liu , Yandong Li , Limin Wang , Shilei Wen

Empowered by Large Language Models (LLMs), recent advancements in Video-based LLMs (VideoLLMs) have driven progress in various video understanding tasks. These models encode video representations through pooling or query aggregation over a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Yuetian Weng , Mingfei Han , Haoyu He , Xiaojun Chang , Bohan Zhuang

As one of the prevalent components, Feature Pyramid Network (FPN) is widely used in current object detection models for improving multi-scale object detection performance. However, its feature fusion mode is still in a misaligned and local…

Computer Vision and Pattern Recognition · Computer Science 2022-04-14 Yongxiang Gu , Xiaolin Qin , Yuncong Peng , Lu Li

Temporal action localization plays an important role in video analysis, which aims to localize and classify actions in untrimmed videos. The previous methods often predict actions on a feature space of a single-temporal scale. However, the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-17 Zan Gao , Xinglei Cui , Tao Zhuo , Zhiyong Cheng , An-An Liu , Meng Wang , Shenyong Chen

Video deblurring models exploit information in the neighboring frames to remove blur caused by the motion of the camera and the objects. Recurrent Neural Networks~(RNNs) are often adopted to model the temporal dependency between frames via…

Computer Vision and Pattern Recognition · Computer Science 2022-04-08 JoonKyu Park , Seungjun Nah , Kyoung Mu Lee

Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens.…

Computer Vision and Pattern Recognition · Computer Science 2017-08-04 Wei Yang , Shuang Li , Wanli Ouyang , Hongsheng Li , Xiaogang Wang

Large Vision-Language Models (LVLMs) demonstrate remarkable performance in short-video tasks such as video question answering, but struggle in long-video understanding. The linear frame sampling strategy, conventionally used by LVLMs, fails…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Joao Pereira , Vasco Lopes , David Semedo , Joao Neves

It has been found that temporal action proposal generation, which aims to discover the temporal action instances within the range of the start and end frames in the untrimmed videos, can largely benefit from proper temporal and semantic…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Shuaicheng Li , Feng Zhang , Rui-Wei Zhao , Rui Feng , Kunlin Yang , Lingbo Liu , Jun Hou

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

The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Zican Shi , Jing Hu , Jie Ren , Hengkang Ye , Xuyang Yuan , Yan Ouyang , Jia He , Bo Ji , Junyu Guo

Most of current Convolution Neural Network (CNN) based methods for optical flow estimation focus on learning optical flow on synthetic datasets with groundtruth, which is not practical. In this paper, we propose an unsupervised optical flow…

Computer Vision and Pattern Recognition · Computer Science 2019-07-29 Shuosen Guan , Haoxin Li , Wei-Shi Zheng

LBP is a successful hand-crafted feature descriptor in computer vision. However, in the deep learning era, deep neural networks, especially convolutional neural networks (CNNs) can automatically learn powerful task-aware features that are…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Zhuo Su , Matti Pietikäinen , Li Liu