Xiaoteng Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xiaoteng Zhang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Pingge Hu
Department of Automation, Tsinghua University, Beijing 100084, China
4 shared publications - Li Shi
Tsinghua University Beijing China
3 shared publications - Haifeng Liu
State Key Laboratory of Engines, Tianjin University, Tianjin 300072, China
2 shared publications - Li Shi
Department of Automation, Tsinghua University, Beijing 100084, China
2 shared publications Mengmeng Li
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, 450001, China; Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology, Zhengzhou, 450001, China
2 shared publications- Xingtong Wang
Department of Automation, Tsinghua University, Beijing 100084, China
2 shared publications
Latest Publications
- Open Access
Product-Manifold Contrastive Learning for Characterizing Neural Representations of 3D Visual Transformations in the Avian Visual System
Most neural decoding methods prioritize predictive accuracy but provide limited means to test hypotheses about latent representational geometry. Guided by projection geometry, we recorded neural activity from the ENTO–MVL pathway of five pigeons performing matched 2D rotation, 2D stretch/compression, and 3D view-rotation tasks. Preliminary response analysis identified two groups with different 2D transformation preferences, both responsive during 3D view rotation, motivating a hypothesis of joint engagement. We introduce ProMaC, a product-manifold contrastive framework with specialist encoders and a prespecified S1 × coordinate prior, to test this hypothesis through cross-transformation generalization. Trained exclusively on 2D tasks, frozen branches recovered silhouette-derived projected rotation and log-scale descriptors from held-out 3D trials and aligned 2D and 3D centroids, outperforming matched controls (Holm-adjusted p < 0.001). Fixed-time-bin analyses supported correspondence beyond shared temporal progress, and leave-one-pigeon-out sensitivity analyses retained positive model advantages. Auxiliary analyses showed factor selectivity and greater projected-descriptor accuracy for direct ProMaC-Joint predictions than for angle-mediated predictions, without establishing information beyond physical angle. Persistent homology supported a stable loop but did not establish a complete product manifold. These findings support the generalization of factor-specific, 2D-derived coordinates along the tested one-parameter 3D view-rotation trajectories.Open AccessProduct-Manifold Contrastive Learning for Characterizing Neural Representations of 3D Visual Transformations in the Avian Visual System
Most neural decoding methods prioritize predictive accuracy but provide limited means to test hypotheses about latent representational geometry. Guided by projection geometry, we recorded neural activity from the ENTO–MVL pathway of five pigeons performing matched 2D rotation, 2D stretch/compression, and 3D view-rotation tasks. Preliminary response analysis identified two groups with different 2D transformation preferences, both responsive during 3D view rotation, motivating a hypothesis of joint engagement. We introduce ProMaC, a product-manifold contrastive framework with specialist encoders and a prespecified S1 × coordinate prior, to test this hypothesis through cross-transformation generalization. Trained exclusively on 2D tasks, frozen branches recovered silhouette-derived projected rotation and log-scale descriptors from held-out 3D trials and aligned 2D and 3D centroids, outperforming matched controls (Holm-adjusted p < 0.001). Fixed-time-bin analyses supported correspondence beyond shared temporal progress, and leave-one-pigeon-out sensitivity analyses retained positive model advantages. Auxiliary analyses showed factor selectivity and greater projected-descriptor accuracy for direct ProMaC-Joint predictions than for angle-mediated predictions, without establishing information beyond physical angle. Persistent homology supported a stable loop but did not establish a complete product manifold. These findings support the generalization of factor-specific, 2D-derived coordinates along the tested one-parameter 3D view-rotation trajectories. - 28 December 2024
- Published by Springer Nature
- p. 432-455
Bio-inspired Saliency Computing Neural Network for UAV Small Object Detection
- 28 December 2024
- Published by Springer Nature
- p. 432-455
Bio-inspired Saliency Computing Neural Network for UAV Small Object Detection
- Open Access
- 9 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106881
TSOM: Small object motion detection neural network inspired by avian visual circuit
- 9 November 2024
- Published by Elsevier in Neural Networks
- Vol. 182, 106881
Open AccessTSOM: Small object motion detection neural network inspired by avian visual circuit
- Open Access
TSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit
Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and its Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical modeling based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each layer corresponding to neurons in the visual pathway. The Retina layer is responsible for accurately projecting input content, the SGC dendritic layer perceives and encodes spatial-temporal information, the SGC Soma layer computes complex motion information and extracts small objects, and the Rt layer integrates and decodes motion information from multiple directions to determine the position of small objects. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.
Open AccessTSOM: Small Object Motion Detection Neural Network Inspired by Avian Visual Circuit
Detecting small moving objects in complex backgrounds from an overhead perspective is a highly challenging task for machine vision systems. As an inspiration from nature, the avian visual system is capable of processing motion information in various complex aerial scenes, and its Retina-OT-Rt visual circuit is highly sensitive to capturing the motion information of small objects from high altitudes. However, more needs to be done on small object motion detection algorithms based on the avian visual system. In this paper, we conducted mathematical modeling based on extensive studies of the biological mechanisms of the Retina-OT-Rt visual circuit. Based on this, we proposed a novel tectum small object motion detection neural network (TSOM). The neural network includes the retina, SGC dendritic, SGC Soma, and Rt layers, each layer corresponding to neurons in the visual pathway. The Retina layer is responsible for accurately projecting input content, the SGC dendritic layer perceives and encodes spatial-temporal information, the SGC Soma layer computes complex motion information and extracts small objects, and the Rt layer integrates and decodes motion information from multiple directions to determine the position of small objects. Extensive experiments on pigeon neurophysiological experiments and image sequence data showed that the TSOM is biologically interpretable and effective in extracting reliable small object motion features from complex high-altitude backgrounds.
- 10 August 2023
- Published by Elsevier in Fuel Processing Technology
- Vol. 250, 107928
Optical characterization of ethanol spray flame on a constant volume combustion chamber
- 10 August 2023
- Published by Elsevier in Fuel Processing Technology
- Vol. 250, 107928
Optical characterization of ethanol spray flame on a constant volume combustion chamber
- 16 January 2023
- Published by Elsevier in Fuel Processing Technology
- Vol. 242, 107668
Effects of different additives on physicochemical properties of gasoline and vehicle performance
- 16 January 2023
- Published by Elsevier in Fuel Processing Technology
- Vol. 242, 107668
Effects of different additives on physicochemical properties of gasoline and vehicle performance
- Open Access
- 4 November 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (21) , 4125
OTNet: A Small Object Detection Algorithm for Video Inspired by Avian Visual System
Small object detection is one of the most challenging and non-negligible fields in computer vision. Inspired by the location–focus–identification process of the avian visual system, we present our location-focused small-object-detection algorithm for video or image sequence, OTNet. The model contains three modules corresponding to the forms of saliency, which drive the strongest response of OT to calculate the saliency map. The three modules are responsible for temporal–spatial feature extraction, spatial feature extraction and memory matching, respectively. We tested our model on the AU-AIR dataset and achieved up to 97.95% recall rate, 85.73% precision rate and 89.94 F1 score with a lower computational complexity. Our model is also able to work as a plugin module for other object detection models to improve their performance in bird-view images, especially for detecting smaller objects. We managed to improve the detection performance by up to 40.01%. The results show that our model performs well on the common metrics on detection, while simulating visual information processing for object localization of the avian brain.
- 4 November 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (21) , 4125
Open AccessOTNet: A Small Object Detection Algorithm for Video Inspired by Avian Visual System
Small object detection is one of the most challenging and non-negligible fields in computer vision. Inspired by the location–focus–identification process of the avian visual system, we present our location-focused small-object-detection algorithm for video or image sequence, OTNet. The model contains three modules corresponding to the forms of saliency, which drive the strongest response of OT to calculate the saliency map. The three modules are responsible for temporal–spatial feature extraction, spatial feature extraction and memory matching, respectively. We tested our model on the AU-AIR dataset and achieved up to 97.95% recall rate, 85.73% precision rate and 89.94 F1 score with a lower computational complexity. Our model is also able to work as a plugin module for other object detection models to improve their performance in bird-view images, especially for detecting smaller objects. We managed to improve the detection performance by up to 40.01%. The results show that our model performs well on the common metrics on detection, while simulating visual information processing for object localization of the avian brain.