首页/论文/1908.04519

arXiv 1908.045192019-08-13cs.CV

Three Branches: Detecting Actions With Richer Features

Shanghai Jiao Tong University（上海交通大学）

Jin Xia, Jiajun Tang, Cewu Lu

英文摘要：

We present our three branch solutions for International Challenge on Activity Recognition at CVPR2019. This model seeks to fuse richer information of global video clip, short human attention and long-term human activity into a unified model. We have participated in two tasks: Task A, the Kinetics challenge and Task B, spatio-temporal action localization challenge. For Kinetics, we achieve 21.59% error rate. For the AVA challenge, our final model obtains 32.49% mAP on the test sets, which outperforms all submissions to the AVA challenge at CVPR 2018 for more than 10% mAP. As the future work, we will introduce human activity knowledge, which is a new dataset including key information of human activity.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Alleviating Over-segmentation Errors by Detecting Action Boundaries

National Institute of Advanced Industrial Science and Technology (AIST)（日本国立产业技术综合研究所）；Keio University（庆应义塾大学）

We propose an effective framework for the temporal action segmentation task, namely an Action Segment Refinement Framework (ASRF). Our model architecture consists of a long-term feature extractor and two branches: the Action Segmentation Branch (ASB) and the Boundary Regression Branch (BRB). The long-term feature extractor provides shared features for the two branches with a wide temporal receptive field. The ASB classifies video frames with action classes, while the BRB regresses the action boundary probabilities. The action boundaries predicted by the BRB refine the output from the ASB, whic…

2020-07-14cs.CV

Progressive Attention on Multi-Level Dense Difference Maps for Generic Event Boundary Detection

Nanjing University（南京大学）；SenseTime Research（商汤科技研究院）

Generic event boundary detection is an important yet challenging task in video understanding, which aims at detecting the moments where humans naturally perceive event boundaries. The main challenge of this task is perceiving various temporal variations of diverse event boundaries. To this end, this paper presents an effective and end-to-end learnable framework (DDM-Net). To tackle the diversity and complicated semantics of event boundaries, we make three notable improvements. First, we construct a feature bank to store multi-level features of space and time, prepared for difference calculatio…

2022-04-01cs.CV

Scale Matters: Temporal Scale Aggregation Network for Precise Action Localization in Untrimmed Videos

Peking University（北京大学）；Tencent（腾讯）；Cloud and Smart Industries Group, Tencent（腾讯云与智慧产业事业群）

Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer from imprecise temporal boundaries of action proposals. This work proposes a novel integrated temporal scale aggregation network (TSA-Net). Our main insight is that ensembling convolution filters with different dilation rates can effectively enlarge the receptive field with low computational cost, which inspires us to devise multi-dilation temporal convolut…

2019-08-02cs.CV

GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency

Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；University of Technology Sydney（悉尼科技大学）

Since detecting and recognizing individual human or object are not adequate to understand the visual world, learning how humans interact with surrounding objects becomes a core technology. However, convolution operations are weak in depicting visual interactions between the instances since they only build blocks that process one local neighborhood at a time. To address this problem, we learn from human perception in observing HOIs to introduce a two-stage trainable reasoning mechanism, referred to as GID block. GID block breaks through the local neighborhoods and captures long-range dependency…

2020-03-11cs.CV

Detecting Violence in Video Based on Deep Features Fusion Technique

Benha University（本哈大学）

With the rapid growth of surveillance cameras in many public places to mon-itor human activities such as in malls, streets, schools and, prisons, there is a strong demand for such systems to detect violence events automatically. Au-tomatic analysis of video to detect violence is significant for law enforce-ment. Moreover, it helps to avoid any social, economic and environmental damages. Mostly, all systems today require manual human supervisors to de-tect violence scenes in the video which is inefficient and inaccurate. in this work, we interest in physical violence that involved two persons o…

2022-04-15cs.CV

DDS：解耦动态场景图生成网络

DDS: Decoupled Dynamic Scene-Graph Generation Network

University of California Santa Barbara（加州大学圣巴巴拉分校）；Army Research Laboratory（陆军研究实验室）；Microsoft（微软公司）

提出解耦动态场景图生成网络DDS，通过两个独立分支解耦对象与关系特征，显著提升对未见三元组的检测性能。

2025-01-20cs.CV

更多相关论文收起更多论文

基于树式空间-通道注意力融合网络的驾驶员疲劳检测与人脸识别多任务学习

Multi-Task Learning for Fatigue Detection and Face Recognition of Drivers via Tree-Style Space-Channel Attention Fusion Network

Huaqiao University（华侨大学）；Key Laboratory of Computer Vision and Machine Learning of Fujian Provincial Universities（福建省高校计算机视觉与机器学习重点实验室）

针对驾驶场景下多单任务模型并行处理相似任务资源浪费的问题，提出树式多任务学习模型，通过共享骨干加空间-通道注意力分支，结合交替更新等技术用单任务数据训练，实现疲劳检测与人脸识别性能提升。

2024-05-13cs.CV

检测任意人-物交互关系：基于基础模型空间提示学习的通用HOI检测器

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

Southeast University（东南大学）；Nanjing Enbo Tech.（南京恩博科技）；University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）

针对开放世界HOI识别难题，提出UniHOI方法，结合HO提示学习、HOPD模块与GPT解读，释放VL基础模型和LLM潜力，在监督与零样本设置下均显著超越现有方法。

2023-11-07cs.CV

EqGAN：用于少样本图像生成的特征均衡化融合

EqGAN: Feature Equalization Fusion for Few-shot Image Generation

针对少样本图像生成缺乏精细结构与纹理的问题，提出EqGAN，通过双分支解耦融合结构与纹理并进行多尺度特征均衡化，显著提升了图像生成质量、多样性及下游分类准确率。

2023-07-27cs.CV

头锚点增强的拥挤行人跟踪检测与关联

Head Anchor Enhanced Detection and Association for Crowded Pedestrian Tracking

Macao Polytechnic University（澳门理工学院）；University of Coimbra（科英布拉大学）；Beihang University（北航大学）

针对拥挤场景下行人跟踪的遮挡难题，本文提出结合检测器双分支特征与头部关键点检测，并采用迭代卡尔曼滤波整合3D先验，以增强外观和运动建模，实现更稳健的多目标跟踪。

2025-08-07cs.CV

Deep Miner: A Deep and Multi-branch Network which Mines Rich and Diverse Features for Person Re-identification

Digeiz AI Lab（迪吉兹人工智能实验室）；Ecole Polytechnique（巴黎综合理工学院）

Most recent person re-identification approaches are based on the use of deep convolutional neural networks (CNNs). These networks, although effective in multiple tasks such as classification or object detection, tend to focus on the most discriminative part of an object rather than retrieving all its relevant features. This behavior penalizes the performance of a CNN for the re-identification task, since it should identify diverse and fine grained features. It is then essential to make the network learn a wide variety of finer characteristics in order to make the re-identification process of p…

2021-02-18cs.CV

Learning Object Location Predictors with Boosting and Grammar-Guided Feature Extraction

University of Cambridge（剑桥大学）

We present BEAMER: a new spatially exploitative approach to learning object detectors which shows excellent results when applied to the task of detecting objects in greyscale aerial imagery in the presence of ambiguous and noisy data. There are four main contributions used to produce these results. First, we introduce a grammar-guided feature extraction system, enabling the exploration of a richer feature space while constraining the features to a useful subset. This is specified with a rule-based generative grammar crafted by a human expert. Second, we learn a classifier on this data using a …

2009-07-24cs.CV

ActivityCLIP：通过从文本中挖掘互补信息以补充图像模态来增强群体活动识别

ActivityCLIP: Enhancing Group Activity Recognition by Mining Complementary Information from Text to Supplement Image Modality

School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（北京邮电大学智能工程与自动化学院）

提出即插即用的ActivityCLIP方法，通过知识蒸馏利用CLIP从动作标签中提取文本信息以补充图像模态，有效增强群体活动识别性能。

2024-07-29cs.CV

Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis

Max Planck Institute for Evolutionary Anthropology（马克斯·普朗克进化人类学研究所）；Univ. Bordeaux（波尔多大学）；CNRS（法国国家科学研究中心）；Bordeaux INP（波尔多国立理工学院）；LaBRI（波尔多计算机科学研究所）；MIA, La Rochelle University（拉罗谢尔大学MIA研究所）；IMS, University of Bordeaux（波尔多大学IMS研究所）

This paper proposes a fusion method of modalities extracted from video through a three-stream network with spatio-temporal and temporal convolutions for fine-grained action classification in sport. It is applied to TTStroke-21 dataset which consists of untrimmed videos of table tennis games. The goal is to detect and classify table tennis strokes in the videos, the first step of a bigger scheme aiming at giving feedback to the players for improving their performance. The three modalities are raw RGB data, the computed optical flow and the estimated pose of the player. The network consists of t…

2021-09-29cs.AIcs.CVcs.HC

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

Whiting School of Engineering, Johns Hopkins University（约翰斯·霍普金斯大学怀廷工程学院）；Rutgers, The State University of New Jersey（新泽西州立罗格斯大学）

Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of these "traditional" encoder-decoder based approaches, we observed that they perform poorly in detecting smaller structures and are unable to segment boundary regions precisely. This issue can be attributed to the increase in receptive field size as we go deeper into the encoder. The extra focus on learning high level features causes the U-Net based approaches to learn less information about low-level features which are crucial for detectin…

2021-10-14cs.CVeess.IV