اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدContext-Aware RCNN: A Baseline for Action Detection in Videos
90
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Video action detection approaches usually conduct actor-centric action recognition over RoI-pooled features following the standard pipeline of Faster-RCNN. In this work, we first empirically find the recognition accuracy is highly correlated with the bounding box size of an actor, and thus higher resolution of actors contributes to better performance. However, video models require dense sampling in time to achieve accurate recognition. To fit in GPU memory, the frames to backbone network must be kept low-resolution, resulting in a coarse feature map in RoI-Pooling layer. Thus, we revisit RCNN for actor-centric action recognition via cropping and resizing image patches around actors before feature extraction with I3D deep network. Moreover, we found that expanding actor bounding boxes slightly and fusing the context features can further boost the performance. Consequently, we develop a surpringly effective baseline (Context-Aware RCNN) and it achieves new state-of-the-art results on two challenging action detection benchmarks of AVA and JHMDB. Our observations challenge the conventional wisdom of RoI-Pooling based pipeline and encourage researchers rethink the importance of resolution in actor-centric action recognition. Our approach can serve as a strong baseline for video action detection and is expected to inspire new ideas for this filed. The code is available at url{https://github.com/MCG-NJU/CRCNN-Action}.
قيم البحث
اقرأ أيضاً
This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop. The goal of our task is to locate the start time and the end time of the action in the long untr
immed video, and predict action category. We adopt sliding window strategy to generate proposals, which can better adapt to short-duration actions. In addition, we show that classification and proposals are conflict in the same network. The separation of the two tasks boost the detection performance with high efficiency. By simply employing these strategy, we achieved 16.10% performance on the test set of EPIC-KITCHENS-100 Action Detection challenge using a single model, surpassing the baseline method by 11.7% in terms of average mAP.
Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines. While detecting non-temporal HOIs (e.g., sitting on a chair) from static images is feasible, it is unlikely even for humans to gue
ss temporal-related HOIs (e.g., opening/closing a door) from a single video frame, where the neighboring frames play an essential role. However, conventional HOI methods operating on only static images have been used to predict temporal-related interactions, which is essentially guessing without temporal contexts and may lead to sub-optimal performance. In this paper, we bridge this gap by detecting video-based HOIs with explicit temporal information. We first show that a naive temporal-aware variant of a common action detection baseline does not work on video-based HOIs due to a feature-inconsistency issue. We then propose a simple yet effective architecture named Spatial-Temporal HOI Detection (ST-HOI) utilizing temporal information such as human and object trajectories, correctly-localized visual features, and spatial-temporal masking pose features. We construct a new video HOI benchmark dubbed VidHOI where our proposed approach serves as a solid baseline.
Convolutional neural networks (CNN) have enabled significant improvements in pedestrian detection owing to the strong representation ability of the CNN features. Recently, aggregating features from multiple layers of a CNN has been considered as an e
ffective approach, however, the same approach regarding feature representation is used for detecting pedestrians of varying scales. Consequently, it is not guaranteed that the feature representation for pedestrians of a particular scale is optimised. In this paper, we propose a Scale-Aware Multi-resolution (SAM) method for pedestrian detection which can adaptively select multi-resolution convolutional features according to pedestrian sizes. The proposed SAM method extracts the appropriate CNN features that have strong representation ability as well as sufficient feature resolution, given the size of the pedestrian candidate output from a region proposal network. Moreover, we propose an enhanced SAM method, termed as SAM+, which incorporates complementary features channels and achieves further performance improvement. Evaluations on the challenging Caltech and KITTI pedestrian benchmarks demonstrate the superiority of our proposed method.
Currently, spatiotemporal features are embraced by most deep learning approaches for human action detection in videos, however, they neglect the important features in frequency domain. In this work, we propose an end-to-end network that considers the
time and frequency features simultaneously, named TFNet. TFNet holds two branches, one is time branch formed of three-dimensional convolutional neural network(3D-CNN), which takes the image sequence as input to extract time features; and the other is frequency branch, extracting frequency features through two-dimensional convolutional neural network(2D-CNN) from DCT coefficients. Finally, to obtain the action patterns, these two features are deeply fused under the attention mechanism. Experimental results on the JHMDB51-21 and UCF101-24 datasets demonstrate that our approach achieves remarkable performance for frame-mAP.
We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos. Previous methods aim to localize action starts by learning feature representations
that can directly separate the start point from its preceding background. It is challenging due to the subtle appearance difference near the action starts and the lack of training data. Instead, StartNet decomposes ODAS into two stages: action classification (using ClsNet) and start point localization (using LocNet). ClsNet focuses on per-frame labeling and predicts action score distributions online. Based on the predicted action scores of the past and current frames, LocNet conducts class-agnostic start detection by optimizing long-term localization rewards using policy gradient methods. The proposed framework is validated on two large-scale datasets, THUMOS14 and ActivityNet. The experimental results show that StartNet significantly outperforms the state-of-the-art by 15%-30% p-mAP under the offset tolerance of 1-10 seconds on THUMOS14, and achieves comparable performance on ActivityNet with 10 times smaller time offset.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
