PANet: A Context Based Predicate Association Network for Scene Graph Generation

Chen, Yunian; Wang, Yanjie; Zhang, Yang; Guo, Yanwen

doi:10.1109/icme.2019.00094

Cited by 22 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is composed of two general parts: the local propagation within triplet items [26] and the global propagation among all the elements. The global items, according to its specific prior layout structure, can be further divided into the following forms: fully-connected graph [59], [77], chain [73], [74] and tree [78], [79]. contextual information.…”

Section: Message Passing Mechanismmentioning

confidence: 99%

See 1 more Smart Citation

Scene Graph Generation: A Comprehensive Survey

Zhu¹,

Zhang²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning techniques have led to remarkable breakthroughs in the field of generic object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful semantic representation and applications to scene understanding. Scene Graph Generation (SGG) refers to the task of automatically mapping an image into a semantic structural scene graph, which requires the correct labeling of detected objects and their relationships. Although this is a challenging task, the community has proposed a lot of SGG approaches and achieved good results. In this paper, we provide a comprehensive survey of recent achievements in this field brought about by deep learning techniques. We review 138 representative works that cover different input modalities, and systematically summarize existing methods of image-based SGG from the perspective of feature extraction and fusion. We attempt to connect and systematize the existing visual relationship detection methods, to summarize, and interpret the mechanisms and the strategies of SGG in a comprehensive way. Finally, we finish this survey with deep discussions about current existing problems and future research directions. This survey will help readers to develop a better understanding of the current research status and ideas.

show abstract

Section: Message Passing Mechanismmentioning

confidence: 99%

“…Many other message passing methods based on RNN have been developed. Chen et al [74] used an RNN module to capture instance-level context, including objects co-occurrence, spatial location dependency and label relation. Dai et al [76] used a Bi-directional RNN and Shin et al [73] used Bi-directional LSTM as a replacement.…”

Section: Message Passing Mechanismmentioning

confidence: 99%

Scene Graph Generation: A Comprehensive Survey

Zhu¹,

Zhang²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, SGG can be divided into two classes: 1) with facts alone and 2) introducing prior information. Besides, these SGG methods pay more attention to the methods with facts alone, including CRF-based (conditional random field) SGG [117,120] , VTransE-based (visual translation embedding) SGG [121,122] , RNN/LSTM-based SGG [123,124] , Faster RCNN-based SGG [125,126] , graph neural network (GNN) [127,128] , etc. Furthermore, SGG adds different types of prior information, such as language priors [129] , knowledge priors [130,131] , visual contextual information [132] , visual cue [133] , etc.…”

Section: Visual Representation Learning: Stateof-the-artmentioning

confidence: 99%

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

et al. 2022

View full text Add to dashboard Cite

Visual representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multimodal heterogeneous spatial/temporal/spatial-temporal data in the big data era, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the challenges of the existing visual models. The majority of the existing methods tend to fit the original data/variable distributions and ignore the essential causal relations behind the multi-modal knowledge, which lacks unified guidance and analysis about why modern visual representation learning methods easily collapse into data bias and have limited generalization and cognitive abilities. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good cognitive ability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for visual representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some prospective challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in visual representation learning. This paper aims to provide a comprehensive overview of this emerging field, attract attention, encourage discussions, bring to the forefront the urgency of developing novel causal reasoning methods, publicly available benchmarks, and consensus-building standards for reliable visual representation learning and related real-world applications more efficiently.

show abstract

“…SPP performs three maximum pooling operations of different sizes on the input, and concats the output results to splicing and splicing the output results, so that the output depth of the network is the same as the input depth. The third part is the feature fusion network Neck, which consists of Feature Pyramid Networks (FPN) [24] and Path Aggregation Networks (PAN) [25] structures. The FPN structure combines the category information of high-level large targets To the lower layer, the PAN structure transfers the location information of the low-level large target and the category and location features of the small target upwards.…”

Section: The Basic Principle Of Yolov5 Algorithmmentioning

confidence: 99%

Research on camouflage target detection method based on improved YOLOv5

Zhang

Zhou

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Objective: In the task of camouflage target detection, there is a problem that the target is highly integrated with the complex environment background, which is difficult to identify and leads to false detection and missed detection. A target detection algorithm CM-YOLOv5s is proposed for camouflage characteristics. Method: The algorithm uses YOLOv5s as the basic framework. First, a coordinated attention mechanism is embedded in the backbone feature extraction network, which enhances the network’s ability to extract camouflaged target features, weakens the attention to the surrounding background, and effectively improves the algorithm’s anti-background. Interference ability; secondly, the Mixup data enhancement strategy is used to simulate overlapping occlusion scenarios, which further strengthens the network model’s learning ability for complex samples. Results: The training and verification were carried out on the self-made Military Camouflage Target Dataset (MCTD), and the precision, recall, and average mAP of the improved CM-YOLOv5s algorithm reached 95.9%, 87.1%, and 94.1, respectively. %, compared with the original YOLOv5s model, the average accuracy rate is improved by 3.8 percentage points. Conclusion: The improved algorithm has better detection effect, and realizes accurate identification and rapid positioning of military camouflage targets in complex environments.

show abstract

PANet: A Context Based Predicate Association Network for Scene Graph Generation

Cited by 22 publications

References 18 publications

Scene Graph Generation: A Comprehensive Survey

Scene Graph Generation: A Comprehensive Survey

Causal Reasoning Meets Visual Representation Learning: A Prospective Study

Research on camouflage target detection method based on improved YOLOv5

Contact Info

Product

Resources

About