Search Results for author:
Found 30 papers, 5 papers with code
Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation
Moreover, to facilitate disentangled representation learning, we introduce four well-designed constraints: an auxiliary style classifier, an auxiliary inverse classifier, a content contrastive loss, and a pair of latent cycle losses, which can effectively contribute to the construction of the identity-related style space and semantic-related content space.
Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection
In this work, we build a modular-designed codebase, formulate strong training recipes, design an error diagnosis toolbox, and discuss current methods for image-based 3D object detection.
Visual Tuning
With the surprising development of pre-trained visual foundation models, visual tuning jumped out of the standard modus operandi that fine-tunes the whole pre-trained model or just the fully connected layer.
Hyperuniform disordered parametric loudspeaker array
A steerable parametric loudspeaker array is known for its directivity and narrow beam width.
Open-Set Fine-Grained Retrieval via Prompting Vision-Language Evaluator
PLEor could leverage pre-trained CLIP model to infer the discrepancies encompassing both pre-defined and unknown subcategories, called category-specific discrepancies, and transfer them to the backbone network trained in the close-set scenarios.
Anti-Delay Kalman Filter Fusion Algorithm for Vehicle-borne Sensor Network with Finite-Time Convergence
Intelligent vehicles in autonomous driving and obstacle avoidance, the precise relative state of vehicles put forward a higher demand.
TRUST: An Accurate and End-to-End Table structure Recognizer Using Splitting-based Transformers
The Vertex-based Merging Module is capable of aggregating local contextual information between adjacent basic grids, providing the ability to merge basic girds that belong to the same spanning cell accurately.
Ranked #5 on
Table Recognition
on PubTabNet
Semantic decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation
Therefore, we propose a semantic decomposition network (SDNet) that introduces two single-task branches to separately address the segmentation of teeth and dental plaque and designs additional constraints to learn category-specific features for each branch, thus facilitating the semantic decomposition and improving the performance of dental plaque segmentation.
Fine-grained Retrieval Prompt Tuning
In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation.
Cascading Residual Graph Convolutional Network for Multi-Behavior Recommendation
In particular, we design a cascading residual graph convolutional network structure, which enables our model to learn user preferences by continuously refining user embeddings across different types of behaviors.
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Finally, this LiDAR Net can serve as the teacher to transfer the learned knowledge to the baseline model.
An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset
Based on this dataset, we propose a semi-supervised underwater semantic segmentation network focusing on the boundaries(US-Net: Underwater Segmentation Network).
A Dataset And Benchmark Of Underwater Object Detection For Robot Picking
Towards these challenges we introduce a dataset, Detecting Underwater Objects (DUO), and a corresponding benchmark, based on the collection and re-annotation of all relevant datasets.
Delving into Localization Errors for Monocular 3D Object Detection
Estimating 3D bounding boxes from monocular images is an essential component in autonomous driving, while accurate 3D object detection from this kind of data is very challenging.
3D Object Detection From Monocular Images
Autonomous Driving
+3
Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution
First, we design a cross-task distillation scheme that encourages DSR and DE networks to learn from each other in a teacher-student role-exchanging fashion.
A Unified Joint Maximum Mean Discrepancy for Domain Adaptation
From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.
Direct Depth Learning Network for Stereo Matching
To make the Adaptive-Grained Depth Refinement stage robust to the coarse depth and adaptive to the depth range of the points, the Granularity Uncertainty is introduced to Adaptive-Grained Depth Refinement stage.
Full Matching on Low Resolution for Disparity Estimation
To this end, we first propose to decompose the full matching task into multiple stages of the cost aggregation module.
SIRI: Spatial Relation Induced Network For Spatial Description Resolution
Spatial Description Resolution, as a language-guided localization task, is proposed for target location in a panoramic street view, given corresponding language descriptions.
Category-specific Semantic Coherency Learning for Fine-grained Image Recognition
Existing deep learning based weakly supervised fine-grained image recognition (WFGIR) methods usually pick out the discriminative regions from the high-level feature (HLF) maps directly.
Rethink Maximum Mean Discrepancy for Domain Adaptation
On the other hand, we design two different strategies to boost the feature discriminability: 1) we directly impose a trade-off parameter on the implicit intra-class distance in MMD to regulate its change; 2) we impose the similar weights revealed in MMD on inter-class distance and maximize it, then a balanced factor could be introduced to quantitatively leverage the relative importance between the feature transferability and its discriminability.
Sparsely-Labeled Source Assisted Domain Adaptation
However, there are usually a large number of unlabeled data but only a few labeled data in the source domain, and how to transfer knowledge from this sparsely-labeled source domain to the target domain is still a challenge, which greatly limits their application in the wild.
Location-Aware Feature Selection Text Detection Network
However, they are behind in accuracy comparing with recent segmentation-based text detectors.
A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
We also propose a novel Poisson-blending Generative Adversarial Network (Poisson GAN) and an efficient object detection network (AquaNet) to address two common issues within related datasets: the class-imbalance problem and the problem of mass small object, respectively.
Graph-propagation based Correlation Learning for Weakly Supervised Fine-grained Image Classification
The key of Weakly Supervised Fine-grained Image Classification (WFGIC) is how to pick out the discriminative regions and learn the discriminative features from them.
Ranked #25 on
Fine-Grained Image Classification
on FGVC Aircraft
Importance Filtered Cross-Domain Adaptation
Firstly, an importance filtered mechanism is devised to generate filtered soft labels to mitigate negative transfer desirably.
Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving
To this end, we first leverage a stand-alone module to transform the input data from 2D image plane to 3D point clouds space for a better input representation, then we perform the 3D detection using PointNet backbone net to obtain objects 3D locations, dimensions and orientations.
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack of authentic illustration-line art training pairs also increases difficulty of model generalization.
A Single Shot Text Detector with Scale-adaptive Anchors
Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances.
Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition
We develop dual deep networks with memorable gated recurrent units (GRUs), and sequentially feed these two types of features into the dual networks, respectively.
