Adaptive graph convolutional networks for weakly supervised anomaly
detection in videos
- URL: http://arxiv.org/abs/2202.06503v1
- Date: Mon, 14 Feb 2022 06:31:34 GMT
- Title: Adaptive graph convolutional networks for weakly supervised anomaly
detection in videos
- Authors: Congqi Cao, Xin Zhang, Shizhou Zhang, Peng Wang, Yanning Zhang
- Abstract summary: We propose a weakly supervised adaptive graph convolutional network (WAGCN) to model the contextual relationships among video segments.
We fully consider the influence of other video segments on the current segment when generating the anomaly probability score for each segment.
- Score: 42.3118758940767
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: For the weakly supervised anomaly detection task, most existing work is
limited to the problem of inadequate video representation due to the inability
to model long-time contextual information. We propose a weakly supervised
adaptive graph convolutional network (WAGCN) to model the contextual
relationships among video segments. And we fully consider the influence of
other video segments on the current segment when generating the anomaly
probability score for each segment. Firstly, we combine the temporal
consistency as well as feature similarity of video segments for composition,
which makes full use of the association information among spatial-temporal
features of anomalous events in videos. Secondly, we propose a graph learning
layer in order to break the limitation of setting topology manually, which
adaptively extracts sparse graph adjacency matrix based on data. Extensive
experiments on two public datasets (i.e., UCF-Crime dataset and ShanghaiTech
dataset) demonstrate the effectiveness of our approach.
Related papers
- Appearance-Based Refinement for Object-Centric Motion Segmentation [85.2426540999329]
We introduce an appearance-based refinement method that leverages temporal consistency in video streams to correct inaccurate flow-based proposals.
Our approach involves a sequence-level selection mechanism that identifies accurate flow-predicted masks as exemplars.
Its performance is evaluated on multiple video segmentation benchmarks, including DAVIS, YouTube, SegTrackv2, and FBMS-59.
arXiv Detail & Related papers (2023-12-18T18:59:51Z) - Dynamic Erasing Network Based on Multi-Scale Temporal Features for
Weakly Supervised Video Anomaly Detection [103.92970668001277]
We propose a Dynamic Erasing Network (DE-Net) for weakly supervised video anomaly detection.
We first propose a multi-scale temporal modeling module, capable of extracting features from segments of varying lengths.
Then, we design a dynamic erasing strategy, which dynamically assesses the completeness of the detected anomalies.
arXiv Detail & Related papers (2023-12-04T09:40:11Z) - CHAD: Charlotte Anomaly Dataset [2.6774008509840996]
We present the Charlotte Anomaly dataset (CHAD) for video anomaly detection.
CHAD is the first anomaly dataset to include bounding box, identity, and pose annotations for each actor.
With four camera views and over 1.15 million frames, CHAD is the largest fully annotated anomaly detection dataset.
arXiv Detail & Related papers (2022-12-19T06:05:34Z) - Mitigating Representation Bias in Action Recognition: Algorithms and
Benchmarks [76.35271072704384]
Deep learning models perform poorly when applied to videos with rare scenes or objects.
We tackle this problem from two different angles: algorithm and dataset.
We show that the debiased representation can generalize better when transferred to other datasets and tasks.
arXiv Detail & Related papers (2022-09-20T00:30:35Z) - Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action
Segmentation in Videos [0.40778318140713216]
This study introduces a graph-structured approach named Semantic2Graph, to model long-term dependencies in videos.
We have designed positive and negative semantic edges, accompanied by corresponding edge weights, to capture both long-term and short-term semantic relationships in video actions.
arXiv Detail & Related papers (2022-09-13T00:01:23Z) - Spatial-Temporal Correlation and Topology Learning for Person
Re-Identification in Videos [78.45050529204701]
We propose a novel framework to pursue discriminative and robust representation by modeling cross-scale spatial-temporal correlation.
CTL utilizes a CNN backbone and a key-points estimator to extract semantic local features from human body.
It explores a context-reinforced topology to construct multi-scale graphs by considering both global contextual information and physical connections of human body.
arXiv Detail & Related papers (2021-04-15T14:32:12Z) - Coherent Loss: A Generic Framework for Stable Video Segmentation [103.78087255807482]
We investigate how a jittering artifact degrades the visual quality of video segmentation results.
We propose a Coherent Loss with a generic framework to enhance the performance of a neural network against jittering artifacts.
arXiv Detail & Related papers (2020-10-25T10:48:28Z) - Localizing Anomalies from Weakly-Labeled Videos [45.58643708315132]
We propose a WeaklySupervised Anomaly localization (WSAL) method focusing on temporally localizing anomalous segments within anomalous videos.
Inspired by the appearance difference in anomalous videos, the evolution of adjacent temporal segments is evaluated for the localization of anomalous segments.
Our proposed method achieves new state-of-the-art performance on the UCF-Crime and TAD datasets.
arXiv Detail & Related papers (2020-08-20T12:58:03Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.