Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks139 from public data
- An integrated UGV-UAV system for construction site data collection232
This paper designs a UAV-UGV team that integrates two custom-built mobile robots that is capable of autonomous navigation, and the performance of the system demonstrates the feasibility of developing and deploying a robust and automated data collection system for construction applications in the near future.
- Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection202
The key idea is that with the annotated 3D bounding boxes of objects in an image, there is a rich set of well-posed projected 2D supervision signals available in training, such as the projected corner keypoints and their associated offset vectors with respect to the center of 2D bounders, which should be exploited as auxiliary tasks in training.
- Image Synthesis From Reconfigurable Layout and Style166
This paper presents a layout- and style-based architecture for generative adversarial networks (termed LostGANs) that can be trained end-to-end to generate images from reconfigurable layout and style.
- Learning Attraction Field Representation for Robust Line Segment Detection161
A region-partition based attraction field dual representation for line segment maps, which poses the problem of line segment detection (LSD) as the region coloring problem and harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution.
- 145
- A stochastic graph grammar for compositional object representation and recognition140
A hierarchical generative model for representing and recognizing compositional object categories with large intra-category variance that combines the power of a stochastic context free grammar (SCFG) to express the variability of part configurations, and a Markov random field (MRF) to represent the pictorial spatial relationships between these parts.
- Holistically-Attracted Wireframe Parsing138
This paper presents a fast and parsimonious parsing method to accurately and robustly detect a vectorized wireframe in an input image with a single forward pass, and is thus called Holistically-Attracted Wireframe Parser (HAWP).
- Face Detection with End-to-End Integration of a ConvNet and a 3D Model132
This paper presents a method for face detection in the wild, which integrates a ConvNet and a 3D mean face model in an end-to-end multi-task discriminative learning framework and addresses two issues in adapting state-of-the-art generic object detection ConvNets.
- Vision-based integrated mobile robotic system for real-time applications in construction128
This paper proposes a mobile robotic platform that incorporates a stack of embedded platforms with integrated Graphical Processing Units (GPUs) to demonstrate the robustness and feasibility of developing and deploying an autonomous system in the near future.
- Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis97
An intuitive paradigm for the task, layout-to-mask- to-image, which learns to unfold object masks in a weakly-supervised way based on an input layout and object style codes is proposed and a method built on Generative Adversarial Networks (GANs) is presented.
- 97
- 88
- Online Object Tracking, Learning and Parsing with And-Or Graphs82
Three key issues in online inference and learning are addressed: (i) maintaining purity of positive and negative examples collected online, (ii) controling model complexity in latent structure learning, and (iii) identifying critical moments to re-learn the structure of AOG based on its intrackability.
- Integrating Context and Occlusion for Car Detection by Hierarchical And-Or Model81
A method of learning reconfigurable hierarchical And-Or models to integrate context and occlusion for car detection using Weak-Label Structural SVM and compares with state-of-the-art variants of deformable part-based models and other methods.
- Sign-Based Gradient Descent With Heterogeneous Data: Convergence and Byzantine Resilience75
A novel magnitude-driven stochastic-sign-based gradient compressor is proposed to address the non-convergence issue of SignSGD, and the convergence of the proposed method is established in the presence of arbitrary data heterogeneity.
- 69
- 65
- 63
- 58
- Recognizing Car Fluents from Video53
A spatial-temporal And-Or hierarchical model to represent car fluents is formulated under the latent structural SVM framework and outperforms several highly related baseline methods in terms of car fluent recognition and car part localization.
- PlaneTR: Structure-Guided Transformers for 3D Plane Recovery52
A neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image and achieves state-of-the-art performance on the ScanNet and NYUv2 datasets.
- 50
- Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation45
This paper proposes a multi-person pose estimation approach, dubbed as LOGO-CAP, by learning the LOcal-GlObal Contextual Adaptation for human Pose, which is end-to-end trainable with near real-time inference speed in a single forward pass, obtaining state-of-the-art performance on the COCO keypoint benchmark for bottom-up human pose estimation.
- 45
- CGBA: Curvature-aware Geometric Black-box Attack42
A novel query-efficient curvature-aware geometric decision-based black-box attack that conducts boundary search along a semicircular path on a restricted 2D plane to ensure finding a boundary point successfully irrespective of the boundary curvature is proposed.
- Face Video Retrieval via Deep Learning of Binary Hash Representations40
A new deep convolutional neural network to learn discriminative and compact binary representations of faces for face video retrieval and integrates feature extraction and hash learning into a unified optimization framework for the optimal compatibility of feature extractor and hash functions.
- Learning Regional Attraction for Line Segment Detection39
The problem of line segment detection (LSD) as a problem of region coloring is posed, and an end-to-end framework to learn attraction field maps for raw input images, followed by a squeeze module to detect line segments is developed.
- 38
- PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers36
The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks and is significantly more efficient than PVT models in MS-COCO and MIT-ADE20k due to the linear complexity.
- Zero-Shot Learning Posed as a Missing Data Problem36
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem, and explores a simple yet effective transductive framework in the reverse way.
- Attentive Normalization35
Attentive Normalization (AN) is presented which generalizes the common affine transformation component in the vanilla feature normalization, and can be used as a drop-in replacement for any featurenormalization technique which includes the affine Transformation component.
- 35
- NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction32
A novel Neural One-PlanE RANSAC framework (termed NOPE-SAC) that exerts excellent capability of neural networks to learn one-plane pose hypotheses from 3D plane correspondences that significantly improves the camera pose estimation for the two-view inputs with severe viewpoint changes.
- 32
- Decision Level Fusion: An Event Driven Approach29
This technique explores the extent of dependence between features being observed by the sensors, and generates more informed probability distributions over the events, and outperform other existing decision level fusion approaches that may not take into account the relationship between different features.
- 28
- 27
- AOGNets: Compositional Grammatical Architectures for Deep Learning26
Deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs are presented which integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way.
- 25
- Scene-Centric Joint Parsing of Cross-View Videos24
This paper introduces a joint parsing framework that integrates view-centric proposals into scene-centric parse graphs that represent a coherentscene-centric understanding of cross-view scenes.
- Bayesian Inference for Layer Representation with Mixed Markov Random Field24
This paper presents a Bayesian inference algorithm for image layer representation [26], 2.1D sketch [6], with mixed Markov random field, based on Swendsen-Wang Cut algorithm and satisfactory results are shown in the experiments.
- Neural Abstract Style Transfer for Chinese Traditional Painting23
A Neural Abstract Style Transfer method for Chinese traditional painting that learns to preserve abstraction and other style jointly end-to-end via a novel MXDoG-guided filter and three fully differentiable loss terms.
- Building an Integrated Mobile Robotic System for Real-Time Applications in Construction23
This paper proposes an integrated robotic computer vision system, which generates a real-world spatial map of the obstacles and traversable space present in the environment in near real-time, and presents the hardware utilization and performance of the aforementioned system for three different outdoor environments, which represent the applicability of this pipeline to diverse outdoor scenes in nearreal-time.
- 20
- Real-Time Scene Segmentation Using a Light Deep Neural Network Architecture for Autonomous Robot Navigation on Construction Sites19
This paper presents a light and efficient deep neural network architecture to run on an embedded platform in real-time for autonomous robotics systems and suggests possible improvements that could make the model even more efficient.
- 19
- 19
- Jointly social grouping and identification in visual dynamics with causality-induced hierarchical Bayesian model18
A causality-induced hierarchical Bayesian model to tackle the interaction activity video, referring to the “what” interaction activities happen, “where’ interaction atomic occurs in spatial, and “when” group interaction happens in temporal is proposed.
- Interpretable R-CNN18
The proposed AOGParsing operator aims to harness both the explainable rigor of top-down hierarchical and compositional grammar models and the discriminative power of bottom-up deep neural networks through end-to-end training.
- A global energy optimization framework for 2.1D sketch extraction from monocular images18
A global optimization framework for inferring the 2.1D sketch from a monocular image using a global energy optimization framework and a hybrid evolution algorithm is utilized to minimize the global energy function efficiently.
- NEAT: Distilling 3D Wireframes from Neural Attraction Fields17
The proposed NEAT enjoys the joint optimization of the neural fields and the global junctions from scratch, using view-dependent 2D observations without precomputed cross-view feature matching, demonstrating its superiority over state-of-the-art alternatives for 3D wireframe reconstruction.
- 17
- Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver17
A stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner, and shows that MonoXiver consistently achieves improvement with limited computation overhead.
- HoW-3D: Holistic 3D Wireframe Perception from a Single Image17
This paper presents a novel Deep Spatial Gestalt (DSG) model, which outperforms the previous wire-frame detectors in detecting the invisible line geometry in single-view images and is even very competitive with prior arts that take high-fidelity PointCloud as inputs on reconstructing 3D wireframes.
- 17
- Multi-View Attentive Contextualization for Multi-View 3D Object Detection16
The proposed Multi-View Attentive Contextualization (MvACon) hits the two birds with one stone using a representationally dense yet computationally sparse attentive feature contextualization scheme that is agnostic to specific 2D-to-3D feature lifting approaches.
- 15
- 14
- 14
- Preliminary Evaluation of Dog-Drone Technological Interfaces14
The challenges and opportunities learned during the efforts to include drones for computer-assisted interactions with working dogs are discussed, including the enabling technology and it's implications for ACI when dogs and drones work together.
- 14
- 13
- 11
- LNSNet: Lightweight Navigable Space Segmentation for Autonomous Robots on Construction Sites11
An efficient semantic segmentation method named LNSNet (lightweight navigable space segmentation network) that can run on embedded platforms to determinenavable space in real-time and demonstrates the effectiveness and efficiency that are necessary for the future development of the autonomous robotics systems.
- 11
- AOGNets: Deep AND-OR Grammar Networks for Visual Recognition10
AOGNets aim to harness the best of two worlds (grammar models and deep neural networks) in representation learning with end-to-end training and obtain better performance than the widely used Residual Net and its variants, and are tightly comparable to the Dense Net.
- 10
- 10
- Event driven sensor fusion9
This paper addresses the issue of coping with damaged sensors when using the model, by learning a hidden space between sensor modalities which can be exploited to safeguard detection performance.
- 8
- Coupling-and-decoupling: A hierarchical model for occlusion-free object detection8
The proposed method of learning a hierarchical model for X-to-X occlusion-free object detection is compared with state-of-the-art deformable part-based methods, and obtains comparable or better detection performance.
- Learning mixtures of Bernoulli templates by two-round EM with performance guarantee8
It is shown that the two-round EM algorithm can learn mixture of Bernoulli templates with near optimal precision with high probability, if the Bernouelli templates are sufficiently different and if the number of features is sufficiently high.
- ScaleLSD: Scalable Deep Line Segment Detection Streamlined7
This paper studies the problem of Line Segment Detection (LSD) for the characterization of line geometry in images and proposes a domain-agnostic robust LSD model that works well for any natural images, observed to be the first deep approach that outperforms the pioneered non-deep LSD in all aspects.
- Preliminary Evaluation of a System with On-Body and Aerial Sensors for Monitoring Working Dogs7
An initial effort towards deployment of on-body and aerial sensors to monitor the working dogs and their environments during scent detection and search and rescue tasks in order to ensure their welfare, enable novel dog-machine interfaces, and allow for higher success rate of remote and automated task performance is presented.
- 7
- Local Clustering with Mean Teacher for Semi-supervised learning7
This work proposes a simple yet effective method called Local Clustering (LC) to mitigate the effect of confirmation bias in the Mean Teacher model and demonstrates on semi-supervised benchmark datasets SVHN and CIFAR-10 that adding the LC loss to MT yields significant improvements compared to MT and performance comparable to the state of the art in semi- supervised learning.
- 7
- 7
- Zero-Shot Learning via Revealing Data Distribution.6
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem, and explores a simple yet effective transductive framework in the reverse mapping.
- 6
- ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents5
ShopGym is an integrated framework for realistic simulation and scalable benchmarking of e-commerce web agents that produces self-contained, resettable, inspectable, and stable evaluation artifacts that preserve structural properties and agent-evaluation signals relevant to shopping tasks.
- A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction5
The proposed Hierarchical Splatter Image method is tested on the ShapeNet-SRN and CO3D datasets with state-of-the-art performance obtained, especially showing promising capabilities of reconstructing occluded contents in the input view.
- 5
- Revisiting Non-Parametric Matching Cost Volumes for Robust and Generalizable Stereo Matching5
This paper proposes to learn DNN-contextualized binary-pattern-driven non-parametric cost-volumes that improves the adversarial robustness, while retaining accuracy performance comparable to state-of-the-art methods.
- Object Detection via End-to-End Integration of Aspect Ratio and Context Aware Part-based Models and Fully Convolutional Networks.5
The integrated framework is fully convolutional and enjoys end-to-end training, which is called the aspect ratio and context aware fully Convolutional network (ARC-FCN) and shows very competitive results on the PASCAL VOC datasets.
- Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation5
- 4
- 4
- Implicit Bayes Adaptation: A Collaborative Transport Approach3
It is shown that domain adaptation robustness is rooted in the intrinsic (latent) representations of the respective data, which are inherently lying in a non-linear submanifold embedded in a higher dimensional Euclidean space, and this is tantamount to an implicit Bayesian framework.
- 3
- 3
- Refining Self-Supervised Learning in Imaging: Beyond Linear Metric3
A new statistical perspective is introduced, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning.
- 3
- 3
- 3
- Real-Time Optimal Planning and Adaptive Sampling for Multi-Platform Operations in the Gulf of Mexico2
- CHEEM: Continual Learning by Reuse, New, Adapt and Skip -- A Hierarchical Exploration-Exploitation Approach2
The proposed method obtains consistently better performance than the prior art with sensible ArtiHippo learned continually and is tested on the challenging Visual Domain Decathlon benchmark and the recently proposed 5-Dataset benchmark.
- 2
- 2
- Coupling-and-Decoupling: A Hierarchical Model for Occlusion-Free Car Detection2
This paper addresses the problem of X-to-X-occlusion-free object detection by utilizing an intuitive coupling-and-decoupling strategy, and compares the model with the state-of-the-art deformable part-based model (DPM) and obtain better detection performance.
- Integration and goal-guided scheduling of bottom-up and top-down computing processes in hierarchical models2
A framework of integrating and scheduling bottom-up and top-down computing processes in a recursively defined hierarchical And-Or graph (AoG) to address the vision-goal-guided trade-off between accuracy performance and computational efficiency in both loss cost-insensitive and cost-sensitive situations is presented.
- An integrated bottom-up and top-down computing process for car parsing2
This paper presents an integrated bottom-up and top-down computing process for parsing cars, and proposed a star-like pictorial structural model based on the active basis model that is hierarchical and deformable.
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Recurrent Attentional Model for No-Reference Image Quality Assessment.1
A recurrent attentional model for general no-reference image quality assessment (NRIQA), that is to predict the perceptual quality score for an input image without using any reference image and/or prior knowledge regarding underlying distortions, is presented.
- Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs–
This work proposes concealment-aware variant construction, which greedily selects character-removed variants that are low in harmful-keyword alignment and mutually diverse, and instantiates them through five modality-aware prompting strategies, and introduces keyword-related distractor images that depict the harmful keyword in diverse contexts, providing more effective auxiliary visual context than generic distractor images.
- –
- –
- E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems–
E2E-GRec is proposed, a novel end-to-end training framework that unifies GNN training with the recommender system, and demonstrates that E2E-GRec consistently surpasses traditional approaches, yielding significant gains across multiple recommendation metrics.
- H$^3$GNNs: Harmonizing Heterophily and Homophily in GNNs via Joint Structural Node Encoding and Self-Supervised Learning–
This work proposes H$^3$GNNs, an end-to-end self-supervised learning framework that harmonizes both structural properties through two key innovations: Joint Structural Node Encoding and node-predictive-difficulty-based masking strategies.
- –
- QuadAttack: A Quadratic Programming Approach to Ordered Top-K Attacks–
A novel and rigorous quadratic programming (QP) method of learning ordered top-$K$ attacks with low computing cost, dubbed as QuadAttac K, which directly solves the attack constraint in the feature embedding space to satisfy the attack constraint in the feature embedding space.
- –
- –
- –
- –
- Towards Interpretable Image Synthesis by Learning Sparsely Connected AND-OR Networks.–
The results show that meaningful and interpretable hierarchical representations are learned with better qualities of image synthesis and reconstruction obtained than state-of-the-art baselines.
- –
- –
- How Aggressive Can Adversarial Attacks Be: Learning Ordered Top-k Attacks–
The problem of how aggressive white-box targeted attacks can be to go beyond widely used Top-1 attacks is studied and an adversarial distillation framework is presented, which obtains the best results when computation budget is limited.
- –
- –
- –
- Learning Deep Compositional Grammatical Architectures for Visual Recognition–
Deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs are presented which integrate composition-ality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way.
- Modeling and inferring 2.1D sketch with mixed Markov random field–
This paper presents a method of computing a 2.1D sketch from a single image with mixed Markov random field (MRF) under the Bayesian framework, and shows the efficiency and robustness of the approach.
- Joint Parsing of Cross-view Scenes with Spatio-temporal Semantic Parse Graphs.–
A joint parsing method that takes view-centric proposals from pre-trained computer vision models and produces spatio-temporal parse graphs that represents a coherent scene-centric understanding of cross-view scenes is introduced.
- Tang dynasty clothing folds information extraction based on single images–
To overcome the limitations of traditional information extraction and modeling of the Tang dynasty costumes of their own characteristics, the information extraction method of Tang dynasty clothing wrinkle is presented by using the gray value and achieves a realistic three-dimensional visualization.
- Tracking Pedestrian with Multi-component Online Deformable Part-Based Model–
A novel online algorithm to track pedestrian by integrating both the bottom-up and the top-down models of pedestrian, which has three advantages compared with other models: it can efficiently generate match penalty maps of parts preserving the 2bit binary pattern, and can search over all possible configurations in an image in linear-time by distance transforms algorithm.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.