Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2024
Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
MM '24: Proceedings of the 32nd ACM International Conference on MultimediaPages 4995–5004https://doi.org/10.1145/3664647.3681173Existing Transformer-based models for point cloud analysis suffer from quadratic complexity, leading to compromised point cloud resolution and information loss. In contrast, the newly proposed Mamba model, based on state space models (SSM), outperforms ...
- research-articleNovember 2024
Multiple-local feature and attention fused person re-identification method
Intelligent Data Analysis (INDA), Volume 28, Issue 6Pages 1679–1695https://doi.org/10.3233/IDA-230392Person re-identification (ReID) is widely used in intelligent security, monitoring, criminal investigation and other fields. Aiming at the problems of local occlusion, scale misalignment and attitude change of pedestrian images in actual scenes, we ...
- research-articleApril 2024
Robust And Discriminant Local Color Pattern (RADLCP): A novel color descriptor for face recognition
International Journal of Hybrid Intelligent Systems (IJHIS), Volume 20, Issue 1Pages 23–39https://doi.org/10.3233/HIS-230016In [1] Karanwal et al. introduced the novel color descriptor in Face Recognition (FR) called as Fused Local Color Pattern (FLCP). In FLCP, the RGB color format is utilized for extracting features. From R, G and B channels, the MRELBP-NI, 6 × 6 MB-LBP and ...
- surveyOctober 2023
3D Face Recognition: Two Decades of Progress and Prospects
ACM Computing Surveys (CSUR), Volume 56, Issue 3Article No.: 54, Pages 1–39https://doi.org/10.1145/3615863Three-dimensional (3D) face recognition has been extensively investigated in the last two decades due to its wide range of applications in many areas, such as security and forensics. Numerous methods have been proposed to deal with the challenges faced by ...
- research-articleJuly 2023JUST ACCEPTED
OLFF-Net: Robust Registration of 3D Point Cloud based on Overlapped Local Feature Fusion
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Just Accepted https://doi.org/10.1145/3609332Recent advance in high-accuracy sensors has made point cloud become the main data format to characterize the three-dimensional world. Since the sensor can only scan and capture the 3D data within a limited field of view, an alignment algorithm is needed ...
-
- research-articleJanuary 2023
Patch-local self-similar network for ground terrain recognition
International Journal of Intelligent Systems Technologies and Applications (IJISTA), Volume 21, Issue 3Pages 262–279https://doi.org/10.1504/ijista.2023.133696We proposed a patch-local self-similar network (PLoSNet) to exploit the inherent correlations between the patch-level features and the local features among the ground terrain texture for ground terrain recognition. Firstly, the early features extracted ...
- research-articleJanuary 2023
Unsupervised learning of local features for person re-identification with loss function
International Journal of Autonomous and Adaptive Communications Systems (IJAACS), Volume 16, Issue 6Pages 536–551https://doi.org/10.1504/ijaacs.2023.134829Many methods for person re-identification focus on making full use of local features, which typically requires either comprehensive manual labelling or complex pretreatment. This paper proposes a novel loss function, termed feature channels dropout and de-...
- research-articleJanuary 2021
Fast road scenarios recognition of intelligent vehicles by image processing
International Journal of Information and Communication Technology (IJICT), Volume 18, Issue 1Pages 1–15https://doi.org/10.1504/ijict.2021.111916Road scenarios recognition is a key point for intelligent vehicles (IVs) self-localisation. This paper proposes a fast road scenarios recognition method by image processing, which is based on a visual road model. First, a sequence of images is used to set ...
- research-articleJuly 2020
Binocular SLAM Based on Learning-based Feature Extraction
ICRSA '20: Proceedings of the 2020 3rd International Conference on Robot Systems and ApplicationsPages 25–29https://doi.org/10.1145/3402597.3402602The SLAM systems based on the deep learning feature extraction methods usually sacrifice efficiency for accuracy, and there are difficult to meet the system real-time requirements. To deal with such problem, this paper presents a binocular SLAM system ...
- research-articleJanuary 2020
Local and global features fusion to estimate expression invariant human age
International Journal of Intelligent Systems Technologies and Applications (IJISTA), Volume 19, Issue 2Pages 155–171https://doi.org/10.1504/ijista.2020.107224Human beings can easily estimate the age or age group of a person from a facial image where as this capability is not prominent in machines. This problem becomes more complex due to presence of different facial expressions and age progression. In this ...
- research-articleMarch 2018
Image classification by combining local and mid-level features
ICIAI '18: Proceedings of the 2nd International Conference on Innovation in Artificial IntelligencePages 101–105https://doi.org/10.1145/3194206.3194230It is meaningful to study high performance image classification algorithms for massive image management and effective organization. Image feature representations directly affect the performance of classification algorithm, however, in the current ...
- research-articleFebruary 2017
Detection, Alignment, and Recognition of Partially Occluded Human Face Based on Statistical Learning of Local Features
ICMLC '17: Proceedings of the 9th International Conference on Machine Learning and ComputingPages 289–293https://doi.org/10.1145/3055635.3056612This paper proposes an integrated method to detect, align, and recognize human face focusing on maintaining its stability under partial occlusions. The proposed framework is based on the combination of three probabilistic models: face model, variation ...
- articleDecember 2016
Face recognition by decision fusion of two-dimensional linear discriminant analysis and local binary pattern
Frontiers of Computer Science: Selected Publications from Chinese Universities (FCS), Volume 10, Issue 6Pages 1118–1129https://doi.org/10.1007/s11704-016-5024-6To investigate the robustness of face recognition algorithms under the complicated variations of illumination, facial expression and posture, the advantages and disadvantages of seven typical algorithms on extracting global and local features are ...
- posterAugust 2016
Scene Adaptive Object Tracking Combining Local Feature and Color Feature
ICIMCS'16: Proceedings of the International Conference on Internet Multimedia Computing and ServicePages 207–210https://doi.org/10.1145/3007669.3007675Scene changes like scale, rotation, illumination and occlusion often occur in video sequences, which raise challenges to robust object tracking. This paper presents a new on-line object tracking method adapting to different scene changes, by combining ...
- short-paperJune 2016
Accurate Aggregation of Local Features by using K-sparse Autoencoder for 3D Model Retrieval
ICMR '16: Proceedings of the 2016 ACM on International Conference on Multimedia RetrievalPages 293–297https://doi.org/10.1145/2911996.2912054Aggregating a set of local features has been used widely to realize recognition or retrieval of multimedia data including 2D images and 3D models. A number of feature aggregation algorithms (e.g., Bag-of-Features, Locality-constrained Linear coding, or ...
- research-articleFebruary 2016
Compact descriptor for local feature using dominating centre‐symmetric local binary pattern
The authors propose a terse texture feature, called the dominant centre‐symmetric local binary pattern (DCSLBP), which has similar distinctiveness and half dimension compared against original centre‐symmetric local binary pattern (CS‐LBP). On the basis of ...
- research-articleDecember 2015
Logo Spotting on Document Images using Local Features
SoICT '15: Proceedings of the 6th International Symposium on Information and Communication TechnologyPages 252–259https://doi.org/10.1145/2833258.2833292In this paper, we propose a framework for logo spotting by using local features. We present key-point matching methods to match local features of logo images to those of document images. For segmentation, a density-based clustering method is used to ...
- research-articleDecember 2015
Temporal Variance Analysis for Action Recognition
IEEE Transactions on Image Processing (TIP), Volume 24, Issue 12Pages 5904–5915https://doi.org/10.1109/TIP.2015.2490551Slow feature analysis (SFA) extracts slowly varying signals from input data and has been used to model complex cells in the primary visual cortex (V1). It transmits information to both ventral and dorsal pathways to process appearance and motion ...
- research-articleOctober 2015
Face Recognition by Using SURF Features with Block-Based Bag of Feature Models
HAI '15: Proceedings of the 3rd International Conference on Human-Agent InteractionPages 309–310https://doi.org/10.1145/2814940.2815005Face recognition is used to identify humans by their face image. Recently it becomes most common application in information security. Bag of features has been successfully applied in face recognition. In our research we use SURF features and try to ...
- research-articleOctober 2015
Food Image Recognition by Using Bag of SURF: Color Features
HAI '15: Proceedings of the 3rd International Conference on Human-Agent InteractionPages 207–208https://doi.org/10.1145/2814940.2814976The importance of researches in the old days is the retrieval of similar objects. Content-Based Image Retrieval (CBIR) system uses low-level features such as texture, color, and shape to extract the features, but when it comes to food images it is hard ...