中文
相关论文

相关论文: LoSA: Long-Short-range Adapter for Scaling End-to-…

200 篇论文

Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be…

计算机视觉与模式识别 · 计算机科学 2018-08-30 Swathikiran Sudhakaran , Oswald Lanz

Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative…

计算机视觉与模式识别 · 计算机科学 2025-10-14 Huaihai Lyu , Chaofan Chen , Senwei Xie , Pengwei Wang , Xiansheng Chen , Shanghang Zhang , Changsheng Xu

Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple independent stages, where initial spatio-temporal proposals are…

计算机视觉与模式识别 · 计算机科学 2022-10-25 Soufiane Belharbi , Ismail Ben Ayed , Luke McCaffrey , Eric Granger

We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Guodong Ding , Angela Yao

Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…

计算机视觉与模式识别 · 计算机科学 2023-01-03 Yizhou Zhao , Zhenyang Li , Xun Guo , Yan Lu

While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…

计算机视觉与模式识别 · 计算机科学 2023-09-22 Mohamed Afham , Satya Narayan Shukla , Omid Poursaeed , Pengchuan Zhang , Ashish Shah , Sernam Lim

Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…

计算机视觉与模式识别 · 计算机科学 2021-07-27 Quanfu Fan , Chun-Fu Chen , Hilde Kuehne , Marco Pistoia , David Cox

The rising popularity of large foundation models has led to a heightened demand for parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), which offer performance comparable to full model fine-tuning while requiring…

计算机视觉与模式识别 · 计算机科学 2025-02-05 Farzad Farhadzadeh , Debasmit Das , Shubhankar Borse , Fatih Porikli

The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Kun Xia , Le Wang , Sanping Zhou , Gang Hua , Wei Tang

Weakly supervised temporal action localization aims to localize temporal boundaries of actions and simultaneously identify their categories with only video-level category labels. Many existing methods seek to generate pseudo labels for…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Linjiang Huang , Liang Wang , Hongsheng Li

Face analysis has been studied from different angles to infer emotion, poses, shapes, and landmarks. Traditionally RGB cameras are used, yet for fine-grained tasks standard sensors might not be up to the task due to their latency, making it…

计算机视觉与模式识别 · 计算机科学 2024-10-30 Luca Cultrera , Federico Becattini , Lorenzo Berlincioni , Claudio Ferrari , Alberto Del Bimbo

Recent advancements in image understanding have benefited from the extensive use of web image-text pairs. However, video understanding remains a challenge despite the availability of substantial web video-text data. This difficulty…

计算机视觉与模式识别 · 计算机科学 2024-11-05 Wei Li , Hehe Fan , Yongkang Wong , Mohan Kankanhalli , Yi Yang

Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Thong Nguyen , Xiaobao Wu , Xinshuai Dong , Khoi Le , Zhiyuan Hu , Cong-Duy Nguyen , See-Kiong Ng , Luu Anh Tuan

Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize in several specific…

机器学习 · 计算机科学 2025-09-30 Jian Liang , Wenke Huang , Xianda Guo , Guancheng Wan , Bo Du , Mang Ye

Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion in the datasets, but tend to have the lowest performance.…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Chen Zhao , Ali Thabet , Bernard Ghanem

Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep…

计算机视觉与模式识别 · 计算机科学 2019-08-28 Yuqi Huo , Xiaoli Xu , Yao Lu , Yulei Niu , Zhiwu Lu , Ji-Rong Wen

This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist…

计算机视觉与模式识别 · 计算机科学 2017-08-07 Jiyang Gao , Chen Sun , Zhenheng Yang , Ram Nevatia

Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…

计算机视觉与模式识别 · 计算机科学 2022-03-30 Bo He , Xitong Yang , Zuxuan Wu , Hao Chen , Ser-Nam Lim , Abhinav Shrivastava

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Zhangkai Wu , Xuhui Fan , Zhongyuan Xie , Kaize Shi , Longbing Cao

Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation…

计算机视觉与模式识别 · 计算机科学 2021-02-19 Baifeng Shi , Qi Dai , Judy Hoffman , Kate Saenko , Trevor Darrell , Huijuan Xu