Search Results for author:
Found 115 papers, 67 papers with code
ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidance
Though promising results have been achieved in single object generation, these methods often struggle to model complex 3D assets that inherently contain multiple objects.
Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration
This is because 3DGS treats each pixel as an isolated, single point rather than as an area, causing insensitivity to changes in the footprints of pixels.
Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
Deep Text-to-Image Synthesis (TIS) models such as Stable Diffusion have recently gained significant popularity for creative Text-to-image generation.
Sur2f: A Hybrid Representation for High-Quality and Efficient Surface Reconstruction from Multi-view Images
Technically, we learn two parallel streams of an implicit signed distance field and an explicit surrogate surface Sur2f mesh, and unify volume rendering of the implicit signed distance function (SDF) and surface rendering of the surrogate mesh with a shared, neural shader; the unified shading promotes their convergence to the same, underlying surface.
Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation
The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering.
SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation
Zero-shot 6D object pose estimation involves the detection of novel objects with their 6D poses in cluttered scenes, presenting significant challenges for model generalizability.
GS-IR: 3D Gaussian Splatting for Inverse Rendering
We propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results.
Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
Test-Time Adaptation aims to adapt source domain model to testing data at inference stage with success demonstrated in adapting to unseen corruptions.
PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud
Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.
On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
Existing approaches often focus on improving test-time training performance under well-curated target domain data.
VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations
We apply the proposed VI-Net to the challenging task of category-level 6D object pose estimation for predicting the poses of unknown objects without available CAD models; experiments on the benchmarking datasets confirm the efficacy of our method, which outperforms the existing ones with a large margin in the regime of high precision.
Improving Deep Representation Learning via Auxiliary Learnable Target Coding
Deep representation learning is a subfield of machine learning that focuses on learning meaningful and useful representations of data through deep neural networks.
ShuffleMix: Improving Representations via Channel-Wise Shuffle of Interpolated Hidden States
Inspired by good robustness of alternative dropout strategies against over-fitting on limited patterns of training samples, this paper introduces a novel concept of ShuffleMix -- Shuffle of Mixed hidden features, which can be interpreted as a kind of dropout operation in feature space.
Universal Domain Adaptation from Foundation Models: A Baseline Study
We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.
Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Pose
Domain gap between synthetic and real data in visual regression (e. g. 6D pose estimation) is bridged in this paper via global feature alignment and local refinement on the coarse classification of discretized anchor classes in target space, which imposes a piece-wise target manifold regularization into domain-invariant representation learning.
STFAR: Improving Object Detection Robustness at Test-Time by Self-Training with Feature Alignment Regularization
This motivates us to explore adapting an object detection model at test-time, a. k. a.
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
Key to Fantasia3D is the disentangled modeling and learning of geometry and appearance.
Ranked #4 on
Text to 3D
on T$^3$Bench
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available, and instant inference on the target domain is required.
A New Benchmark: On the Utility of Synthetic Data with Blender for Bare Supervised Learning and Downstream Domain Adaptation
Moreover, we use the simulation-to-reality adaptation as a downstream task for comparing the transferability between synthetic and real data when used for pre-training, which demonstrates that synthetic data pre-training is also promising to improve real test results.
HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization
Recovery of an underlying scene geometry from multiview images stands as a long-time challenge in computer vision research.
Unsupervised Domain Adaptation via Distilled Discriminative Clustering
Differently, motivated by the fundamental assumption for domain adaptability, we re-cast the domain adaptation problem as discriminative clustering of target data, given strong privileged information provided by the closely related, labeled source data.
Adversarial Style Augmentation for Domain Generalization
By updating the model against the adversarial statistics perturbation during training, we allow the model to explore the worst-case domain and hence improve its generalization performance.
RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models
More specifically, we maintain an intermediate surface mesh used for rendering new RGBD views, which subsequently becomes complete by an inpainting network; each rendered RGBD view is later back-projected as a partial surface and is supplemented into the intermediate mesh.
Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning
We also validate the effectiveness of affine transformation corruption with the Transformer backbones, where we decompose the reconstruction of the complete point cloud into the reconstructions of detailed local patches and rough global shape, alleviating the position leakage problem in the reconstruction.
TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition
Creation of 3D content by stylization is a promising yet challenging problem in computer vision and graphics research.
DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Establishment of point correspondence between camera and object coordinate systems is a promising way to solve 6D object poses.
Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
First, we show that the key assumption of support overlap of invariant features used in IB-IRM is strong for the guarantee of OOD generalization and it is still possible to achieve the optimal solution without this assumption.
Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
Such target coding schemes are less flexible to model inter-class correlation and are sensitive to sparse and imbalanced data distribution as well.
Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks
It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e. g., category-level 6D object pose and size estimation.
Masked Surfel Prediction for Self-Supervised Point Cloud Learning
In this work, we make the first attempt, to the best of our knowledge, to consider the local geometry information explicitly into the masked auto-encoding, and propose a novel Masked Surfel Prediction (MaskSurf) method.
Style Interleaved Learning for Generalizable Person Re-identification
This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains.
Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering
Test-time training (TTT) emerges as a solution to this adaptation under a realistic scenario where access to full source domain data is not available and instant inference on target domain is required.
Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving
3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV).
BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation
Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space.
Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning
Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning.
Surface Reconstruction from Point Clouds: A Survey and a Benchmark
For example, while deep learning methods are increasingly popular, our systematic studies suggest that, surprisingly, a few classical methods perform even better in terms of both robustness and generalization; our studies also suggest that the practical challenges of misalignment of point sets from multi-view scanning, missing of surface points, and point outliers remain unsolved by all the existing surface reconstruction methods.
Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding
We also demonstrate the feasibility of a more efficient training strategy.
VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention
These multi-view methods either refine the proposals predicted from single view via fused features, or fuse the features without considering the global spatial context; their performance is limited consequently.
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space.
Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
Such a challenge of Simulation-to-Reality (Sim2Real) domain gap could be mitigated via learning algorithms of domain adaptation; however, we argue that generation of synthetic point clouds via more physically realistic rendering is a powerful alternative, as systematic non-uniform noise patterns can be captured.
Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning
To answer these problems, we propose a novel Taylor expansion inspired filtration (TEIF) framework, which admits the samples of moderate confidence with similar feature or gradient to the respective one averaged over the labeled and highly confident unlabeled data.
Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance.
Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification
In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501.
Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds
The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.
Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks
State-of-the-art methods largely rely on a general pipeline that first learns point-wise features discriminative at semantic and instance levels, followed by a separate step of point grouping for proposing object instances.
Ranked #9 on
3D Instance Segmentation
on S3DIS
Content-Aware Convolutional Neural Networks
In practice, the convolutional operation on some of the windows (e. g., smooth windows that contain very similar pixels) can be very redundant and may introduce noises into the computation.
Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation
In this work, we investigate a collaborative fusion scheme called perception-aware multi-sensor fusion (PMF) to exploit perceptual information from two modalities, namely, appearance information from RGB images and spatio-depth information from point clouds.
Ranked #9 on
Semantic Segmentation
on KITTI-360
Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
More specifically, we identify from the linear regions, partitioned by an MLP based implicit function, the analytic cells and analytic faces that are associated with the function's zero-level isosurface.
Gradual Domain Adaptation via Self-Training of Auxiliary Models
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners
Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.
SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks
To this end, we propose to learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks, to simultaneously achieve advanced scalability to large-scale scenes, generality to novel shapes, and applicability to raw scans in a unified framework.
On Universal Black-Box Domain Adaptation
The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model.
Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction
This paper focuses on the task of 4D shape reconstruction from a sequence of point clouds.
3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding
The ability to understand the ways to interact with objects from visual cues, a. k. a.
Ranked #1 on
Affordance Detection
on 3D AffordanceNet
DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency
DualPoseNet stacks two parallel pose decoders on top of a shared pose encoder, where the implicit decoder predicts object poses with a working mechanism different from that of the explicit one; they thus impose complementary supervision on the training of pose encoder.
Ranked #4 on
6D Pose Estimation using RGBD
on REAL275
Vicinal and categorical domain adaptation
Unsupervised domain adaptation aims to learn a task classifier that performs well on the unlabeled target domain, by utilizing the labeled source domain.
Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach
Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets.
Unsupervised Domain Adaptation of Black-Box Source Models
Unsupervised domain adaptation (UDA) aims to learn models for a target domain of unlabeled data by transferring knowledge from a labeled source domain.
Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds
The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets.
Classification of Single-View Object Point Clouds
By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.
Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds
Motivated from a universal phenomenon that self-similar shape patterns of local surface patches repeat across the entire surface of an object, we aim to push forward the data-driven strategies and propose to learn a local implicit surface network for a shared, adaptive modeling of the entire surface for a direct surface reconstruction from raw point cloud; we also enhance the leveraging of surface self-similarities by improving correlations among the optimized latent codes of individual surface patches.
Learning Category-level Shape Saliency via Deep Implicit Surface Networks
Given the large shape variations among different instances of a same category, we are formally interested in developing a quantity defined for individual points on a continuous object surface; the quantity specifies how individual surface points contribute to the formation of the shape as the category.
Deep Optimized Priors for 3D Shape Modeling and Reconstruction
Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples.
Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering
To address this issue, we are motivated by a UDA assumption of structural similarity across domains, and propose to directly uncover the intrinsic target discrimination via constrained clustering, where we constrain the clustering solutions using structural source regularization that hinges on the very same assumption.
JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition
Skeleton-based action recognition has attracted research attentions in recent years.
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks
However, it is observed that such methods would lead to standard performance degradation, i. e., the degradation on natural examples.
A deep learning based interactive sketching system for fashion images design
In this work, we propose an interactive system to design diverse high-quality garment images from fashion sketches and the texture information.
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
To test GPNet, we contribute a synthetic dataset of 6-DOF object grasps; evaluation is conducted using rule-based criteria, simulation test, and real test.
CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsampling
Point set is arguably the most direct approximation of an object or scene surface, yet its practical acquisition often suffers from the shortcoming of being noisy, sparse, and possibly incomplete, which restricts its use for a high-quality surface recovery.
SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Images
However, they all have their own drawbacks, and cannot properly reconstruct the surface shapes of complex topologies, arguably due to a lack of constraints on the topologicalstructures in their learning frameworks.
Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation
To make the proposed A$^2$LP useful for UDA, we propose empirical schemes to generate such virtual instances.
MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL).
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
To alleviate this risk, we are motivated by the assumption of structural domain similarity, and propose to directly uncover the intrinsic target discrimination via discriminative clustering of target data.
HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation
Estimating 3D human pose from a single image is a challenging task.
Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains.
Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
This paper studies a problem of learning surface mesh via implicit functions in an emerging field of deep learning surface reconstruction, where implicit functions are popularly implemented as multi-layer perceptrons (MLPs) with rectified linear units (ReLU).
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors
Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from global configuration of local geometries in a supervised learning manner.
Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities.
Ranked #3 on
3D Object Detection
on KITTI Pedestrians Moderate
W-PoseNet: Dense Correspondence Regularized Pixel Pair Pose Regression
Solving 6D pose estimation is non-trivial to cope with intrinsic appearance and shape variation and severe inter-object occlusion, and is made more challenging in light of extrinsic large illumination changes and low quality of the acquired data under an uncontrolled environment.
Ranked #1 on
6D Pose Estimation using RGBD
on LineMOD
(Mean ADD-S metric)
Cascading Convolutional Color Constancy
Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy.
Geometry-Aware Generation of Adversarial Point Clouds
Regularizing the targeted attack loss with our proposed geometry-aware objectives results in our proposed method, Geometry-Aware Adversarial Attack ($GeoA^3$).
Discriminative Adversarial Domain Adaptation
Based on an integrated category and domain classifier, DADA has a novel adversarial objective that encourages a mutually inhibitory relation between category and domain predictions for any input instance.
Ranked #1 on
Synthetic-to-Real Translation
on Syn2Real-C
Multi-marginal Wasserstein GAN
Multiple marginal matching problem aims at learning mappings to match a source domain to multiple target domains and it has attracted great attention in many applications, such as multi-domain image translation.
HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation
Estimating 3D human pose from a single image is a challenging task.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric, using extra
training data)
Geometry-aware Generation of Adversarial and Cooperative Point Clouds
Recent studies show that machine learning models are vulnerable to adversarial examples.
PARN: Position-Aware Relation Networks for Few-Shot Learning
However, due to the inherent local connectivity of CNN, the CNN-based relation network (RN) can be sensitive to the spatial position relationship of semantic objects in two compared images.
Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks
The key to our approach is a novel progressive shaping framework that alternates between mesh deformation and topology modification.
Ranked #3 on
3D Shape Reconstruction
on Pix3D
Orthogonal Deep Neural Networks
To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks' weight matrices.
Deep Multi-View Learning using Neuron-Wise Correlation-Maximizing Regularizers
Such a perspective enables us to study deep multi-view learning in the context of regularized network training, for which we present control experiments of benchmark image classification to show the efficacy of our proposed CorrReg.
BIT: Biologically Inspired Tracker
Visual tracking is challenging due to image variations caused by various factors, such as object deformation, scale change, illumination change and occlusion.
A Skeleton-bridged Deep Learning Approach for Generating Meshesof Complex Topologies from Single RGB Image
To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge.
Domain-Symmetric Networks for Adversarial Domain Adaptation
Since target samples are unlabeled, we also propose a scheme of cross-domain training to help learn the target classifier.
A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images
To this end, we propose in this paper a skeleton-bridged, stage-wise learning approach to address the challenge.
Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection
We also propose component variants of F-ConvNet, including an FCN variant that extracts multi-resolution frustum features, and a refined use of F-ConvNet over a reduced 3D space.
Ranked #3 on
3D Object Detection
on KITTI Cyclists Easy
You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
Most state-of-the-art methods in VG operate in a two-stage manner, wherein the first stage an object detector is adopted to generate a set of object proposals from the input image and the second stage is simply formulated as a cross-modal matching problem that finds the best match between the language query and all region proposals.
Coupled Recurrent Network (CRN)
To learn from these heterogenous input sources, existing methods reply on two-stream architectural designs that contain independent, parallel streams of Recurrent Neural Networks (RNNs).
Action Recognition In Videos
Multi-Person Pose Estimation
+2
S-System, Geometry, Learning, and Optimization: A Theory of Neural Networks
We present a formal measure-theoretical theory of neural networks (NN) built on {\it probability coupling theory}.
Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image.
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples.
FBI-Pose: Towards Bridging the Gap between 2D Images and 3D Human Poses using Forward-or-Backward Information
Although significant advances have been made in the area of human poses estimation from images using deep Convolutional Neural Network (ConvNet), it remains a big challenge to perform 3D pose inference in-the-wild.
Ranked #227 on
3D Human Pose Estimation
on Human3.6M
Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network
In this work, we propose a Weakly Supervised Part Detection Network (PartNet) that is able to detect discriminative local parts for use of fine-grained categorization.
Deep Sampling Networks
With the powerful down-sampling process, the co-training DSN set a new state-of-the-art performance for image super-resolution.
A Joint Intrinsic-Extrinsic Prior Model for Retinex
We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image.
Lattice Long Short-Term Memory for Human Action Recognition
This method effectively enhances the ability to model dynamics across time and addresses the non-stationary issue of long-term motion dynamics without significantly increasing the model complexity.
Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups
The recent successful deep neural networks are largely trained in a supervised manner.
Improving training of deep neural networks via Singular Value Bounding
To this end, we propose to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieve this by a simple yet effective method called Singular Value Bounding (SVB).
DehazeNet: An End-to-End System for Single Image Haze Removal
The key to achieve haze removal is to estimate a medium transmission map for an input hazy image.
Ranked #7 on
Image Dehazing
on RS-Haze
Multi-task CNN Model for Attribute Prediction
Each CNN will generate attribute-specific feature representations, and then we apply multi-task learning on the features to predict their attributes.
Human Action Recognition using Factorized Spatio-Temporal Convolutional Networks
Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the involved humans and objects.
Robust Face Recognition by Constrained Part-based Alignment
By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression.
Partial Occlusion Handling for Visual Tracking via Robust Part Matching
The proposed part matching tracker (PMT) has a number of attractive properties.
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition
In this paper, we propose to combine SFA with deep learning techniques to learn hierarchical representations from the video data itself.
PCANet: A Simple Deep Learning Baseline for Image Classification?
In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.
Ranked #46 on
Image Classification
on MNIST
ROML: A Robust Feature Correspondence Approach for Matching Objects in A Set of Images
The task is to identify the inlier features and establish their consistent correspondences across the image set.
Learning by Associating Ambiguously Labeled Images
Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image.
