Search Results for author:
Found 15 papers, 7 papers with code
SARatrX: Towards Building A Foundation Model for SAR Target Recognition
Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on the detection or classification of a specific and coarse category, e. g., vehicles, ships, airplanes, or buildings.
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
Ranked #2 on
2D Object Detection
on SARDet-100K
(using extra training data)
Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation
The experimental results demonstrate the effectiveness of our approach in improving the fidelity of generated videos.
AtomoVideo: High Fidelity Image-to-Video Generation
Recently, video generation has achieved significant rapid development based on superior text-to-image generation techniques.
A Category Agnostic Model for Visual Rearrangment
This paper presents a novel category agnostic model for visual rearrangement task which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration.
Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture
The growing Synthetic Aperture Radar (SAR) data has the potential to build a foundation model through Self-Supervised Learning (SSL) methods, which can achieve various SAR Automatic Target Recognition (ATR) tasks with pre-training in large-scale unlabeled data and fine-tuning in small labeled samples.
UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images
Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images.
Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
However, robustly recognizing vehicle targets is a challenging task in SAR due to the large intraclass variations and small interclass variations.
Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR
Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR.
Layout-Based Causal Inference for Object Navigation
The experience performs a positive effect on helping the agent infer the likely location of the goal when the layout gap between the unseen environments of the test and the prior knowledge obtained in training is minor.
STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing
Concretely, we propose two novel pre-training objectives which respectively explore the context-dependent interactions of NL utterances and SQL queries within each text-to-SQL conversation: (i) schema state tracking (SST) objective that tracks and explores the schema states of context-dependent SQL queries in the form of schema-states by predicting and updating the value of each schema slot during interaction; (ii) utterance dependency tracking (UDT) objective that employs weighted contrastive learning to pull together two semantically similar NL utterances and push away the representations of semantically dissimilar NL utterances within each conversation.
A Dynamic Subarray Structure in Reconfigurable Intelligent Surfaces for TeraHertz Communication Systems
In this study, we propose a dynamic RIS subarray structure to improve the performance of a THz MIMO communication system.
Hierarchical Object-to-Zone Graph for Object Navigation
In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments.
Highly tunable quadruple quantum dot in a narrow bandgap semiconductor InAs nanowire
It is shown that these current lines can be individually assigned as arising from resonant electron transport through the energy levels of different QDs.
Mesoscale and Nanoscale Physics
CORAL: Colored structural representation for bi-modal place recognition
In this way, we fuse the structural features and visual features in the consistent bird-eye view frame, yielding a semantic representation, namely CORAL.
