Search Results for author:
Found 147 papers, 52 papers with code
Human Interaction Learning on 3D Skeleton Point Clouds for Video Violence Recognition
This paper introduces a new method for recognizing violent behavior by learning contextual relationships between related people from human skeleton points.
Ranked #5 on
Activity Recognition
on RWF-2000
TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering
Compositional visual question answering requires reasoning over both semantic and geometry object relations.
Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation
Finally, by training the segmentation model with the masks generated by our Splitting vs Merging strategy, we achieve the state-of-the-art weakly-supervised segmentation results on the Pascal VOC 2012 benchmark.
Prim2Room: Layout-Controllable Room Mesh Generation from Primitives
We propose Prim2Room, a novel framework for controllable room mesh generation leveraging 2D layout conditions and 3D primitive retrieval to facilitate precise 3D layout specification.
3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing
Beyond texture augmentation, we propose a method to automatically alter the shape of objects within 2D images.
DeCo: Decoupled Human-Centered Diffusion Video Editing with Motion Consistency
Diffusion models usher a new era of video editing, flexibly manipulating the video contents with text prompts.
iControl3D: An Interactive System for Controllable 3D Scene Generation
To this end, a 3D creator interface has been developed to provide users with fine-grained control over the creation process.
Eliminating Feature Ambiguity for Few-Shot Segmentation
Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features.
Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization.
OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control
This process is achieved through the distillation of pretrained large-scale text-to-image diffusion models.
MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
Recently, 3D assets created via reconstruction and generation have matched the quality of manually crafted assets, highlighting their potential for replacement.
Text-to-Image Rectified Flow as Plug-and-Play Priors
Besides the generative capabilities of diffusion priors, motivated by the unique time-symmetry properties of rectified flow models, a variant of our method can additionally perform image inversion.
Sync4D: Video Guided Controllable Dynamics for Physics-Based 4D Generation
In this work, we introduce a novel approach for creating controllable dynamics in 3D-generated Gaussians using casually captured reference videos.
PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction
At each step, we provide two forms of geometric guidance.
REACTO: Reconstructing Articulated Objects from a Single Video
In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video.
Magic-Boost: Boost 3D Generation with Mutli-View Conditioned Diffusion
Benefiting from the rapid development of 2D diffusion models, 3D content creation has made significant progress recently.
Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
To this end, we explore the feasibility of self-supervised motion prediction with only unlabeled LiDAR point clouds.
Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior
In this paper, we present a new framework Sculpt3D that equips the current pipeline with explicit injection of 3D priors from retrieved reference objects without re-training the 2D diffusion model.
S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes
To address this limitation, we present S-DyRF, a reference-based spatio-temporal stylization method for dynamic neural radiance fields.
Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction
Lastly, to further improve the training process, FSS proposes a mesh thickness loss signal for pixel-aligned implicit models.
Style-Consistent 3D Indoor Scene Synthesis with Decoupled Objects
The core strength of our pipeline lies in its ability to generate 3D scenes that are not only visually impressive but also exhibit features like photorealism, multi-view consistency, and diversity.
R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization
To this end we propose R-Cyclic Diffuser a framework that adapts Zero-1-to-3's novel approach to clothed human data by fusing it with a pixel-aligned implicit model.
Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix
To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module.
Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting
We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks.
AttriHuman-3D: Editable 3D Human Avatar Generation with Attribute Decomposition and Indexing
We propose AttriHuman-3D, an editable 3D human generation model, which address the aforementioned problems with attribute decomposition and indexing.
Few-shot Image Generation via Style Adaptation and Content Preservation
Many works propose to fine-tune a pre-trained GAN model.
SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
To address this problem, we propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper.
DI-Net : Decomposed Implicit Garment Transfer Network for Digital Clothed 3D Human
3D virtual try-on enjoys many potential applications and hence has attracted wide attention.
GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting
3D editing plays a crucial role in many areas such as gaming and virtual reality.
Learning-Based Biharmonic Augmentation for Point Cloud Classification
Point cloud datasets often suffer from inadequate sample sizes in comparison to image datasets, making data augmentation challenging.
Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation
Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision.
Self-Supervised 3D Scene Flow Estimation and Motion Prediction using Local Rigidity Prior
By rigidly aligning each region with its potential counterpart in the target point cloud, we obtain a region-specific rigid transformation to generate its pseudo flow labels.
LCReg: Long-Tailed Image Classification with Latent Categories based Recognition
In this work, we tackle the challenging problem of long-tailed image recognition.
Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization
Recent neural networks based surface reconstruction can be roughly divided into two categories, one warping templates explicitly and the other representing 3D surfaces implicitly.
Improving Video Violence Recognition with Human Interaction Learning on 3D Skeleton Point Clouds
(ii) Global-SPIL: to better learn and refine the features of the unordered and unstructured skeleton points, Global-SPIL employs the self-attention layer that operates directly on the sampled points, which can help to make the output more permutation-invariant and well-suited for our task.
IT3D: Improved Text-to-3D Generation with Explicit View Synthesis
Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs).
StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
However, these datasets often exhibit domain bias, potentially constraining the generative capabilities of the models.
Ranked #78 on
Visual Question Answering
on MM-Vet
Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image
To animate the visual content, the feature point cloud is displaced based on the scene flow derived from motion estimation and the corresponding camera pose.
Unlimited Knowledge Distillation for Action Recognition in the Dark
To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper.
Self-Calibrated Cross Attention Network for Few-Shot Segmentation
Moreover, when calculating SCCA, we design a scaled-cosine mechanism to better utilize the support features for similarity calculation.
Ranked #8 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Weakly Supervised 3D Instance Segmentation without Instance-level Annotations
3D semantic scene understanding tasks have achieved great success with the emergence of deep learning, but often require a huge amount of manually annotated training data.
Neural Video Depth Stabilizer
Video depth estimation aims to infer temporally consistent depth.
Ranked #14 on
Monocular Depth Estimation
on NYU-Depth V2
(using extra training data)
StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation
The recent advancements in image-text diffusion models have stimulated research interest in large-scale 3D generative models.
OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields
This paper proposes a novel object-removing pipeline, named OR-NeRF, that can remove objects from 3D scenes with user-given points or text prompts on a single view, achieving better performance in less time than previous works.
MoDA: Modeling Deformable 3D Objects from Casual Videos
To solve this problem, we propose neural dual quaternion blend skinning (NeuDBS) to achieve 3D point deformation, which can perform rigid transformation without skin-collapsing artifacts.
StarNet: Style-Aware 3D Point Cloud Generation
This paper investigates an open research task of reconstructing and generating 3D point clouds.
Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes.
TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision
We conduct extensive experiments to analyze each of our proposed components and show the efficacy of our framework in generating high-fidelity 3D textured and text-relevant shapes.
3D Cinemagraphy from a Single Image
To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow.
Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points.
Neural Vector Fields: Implicit Representation by Explicit Learning
Deep neural networks (DNNs) are widely applied for nowadays 3D surface reconstruction tasks and such methods can be further divided into two categories, which respectively warp templates explicitly by moving vertices or represent 3D surfaces implicitly as signed or unsigned distance functions.
Effective End-to-End Vision Language Pretraining with Semantic Visual Loss
Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors.
Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds
To address this issue, we propose a new label-guided knowledge distillation (LGKD) loss, where the old model output is expanded and transplanted (with the guidance of the ground truth label) to form a semantically appropriate class correspondence with the new model output.
Ranked #1 on
Continual Semantic Segmentation
on ScanNet
Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving
To this end, we propose a two-stage weakly supervised approach, where the segmentation model trained with the incomplete binary masks in Stage1 will facilitate the self-supervised learning of the motion prediction network in Stage2 by estimating possible moving foregrounds in advance.
Generalizable Person Re-Identification via Viewpoint Alignment and Fusion
The key insight of this design is that the cross-attention mechanism in the transformer could be an ideal solution to align the discriminative texture clues from the original image with the canonical view image, which could compensate for the low-quality texture information of the canonical view image.
Domain Generalization
Generalizable Person Re-identification
+1
Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction
With $G$ as the basic component, we propose a cross consistency learning scheme and a dual reconstruction objective to learn the pose transfer without supervision.
IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction
We propose IntegratedPIFu, a new pixel aligned implicit model that builds on the foundation set by PIFuHD.
Indoor Smartphone SLAM with Learned Echoic Location Features
Indoor self-localization is a highly demanded system function for smartphones.
ManiCLIP: Multi-Attribute Face Manipulation from Text
In this paper we present a novel multi-attribute face manipulation method based on textual descriptions.
SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis
We study the problem of novel view synthesis of objects from a single image.
CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networks
Few-shot segmentation aims to learn a segmentation model that can be generalized to novel classes with only a few training images.
Collaborative Propagation on Multiple Instance Graphs for 3D Instance Segmentation with Single-point Supervision
Instance segmentation on 3D point clouds has been attracting increasing attention due to its wide applications, especially in scene understanding areas.
Ranked #22 on
3D Instance Segmentation
on ScanNet(v2)
Single-view 3D Mesh Reconstruction for Seen and Unseen Categories
Single-view 3D object reconstruction is a fundamental and challenging computer vision task that aims at recovering 3D shapes from single-view RGB images.
Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval
When we do online paired data augmentation, we first generate augmented text through random token replacement, then pass the augmented text into the latent space alignment module to output the latent codes, which are finally fed to StyleGAN2 to generate the augmented images.
3D Cartoon Face Generation with Controllable Expressions from a Single GAN Image
To this end, we discover the semantic meanings of StyleGAN latent space, such that we are able to produce face images of various expressions, poses, and lighting by controlling the latent codes.
Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation
Weakly supervised point cloud segmentation, i. e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training.
Few-shot Open-set Recognition Using Background as Unknowns
First, instead of learning the decision boundaries between seen classes, as is done in standard close-set classification, we reserve space for unseen classes, such that images located in these areas are recognized as the unseen classes.
Long-tailed Recognition by Learning from Latent Categories
Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes during the model training.
Ranked #9 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Efficient Few-Shot Object Detection via Knowledge Inheritance
Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.
A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection
Besides, they fail to take full advantage of the cues among inter- and intra-feature within a group of images.
Ranked #1 on
Video Salient Object Detection
on FBMS-59
Self-Training Vision Language BERTs with a Unified Conditional Model
We use the labeled image data to train a teacher model and use the trained model to generate pseudo captions on unlabeled image data.
RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior
In this work, we focus on scene flow learning on point clouds in a self-supervised manner.
Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Temporal Matching and Spatial Graph Propagation
We propose a novel temporal-spatial framework for effective weakly supervised learning to generate high-quality pseudo labels from these limited annotated data.
Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification
Through the proposed MI2P unit, we can inject the language information into the vision backbone by attending the word-wise textual features to different visual channels, as well as inject the visual information into the language backbone by attending the channel-wise visual features to different textual words.
Improving Tail-Class Representation with Centroid Contrastive Learning
ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes.
Ranked #22 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Learning Structural Representations for Recipe Generation and Food Retrieval
Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the learned tree structures into the recipe generation and food cross-modal retrieval procedure.
3D Pose Transfer with Correspondence Learning and Mesh Refinement
It aims to transfer the pose of a source mesh to a target mesh and keep the identity (e. g., body shape) of the target mesh.
Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learning
Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs.
Calibrating Class Activation Maps for Long-Tailed Visual Recognition
First, we present a Class Activation Map Calibration (CAMC) module to improve the learning and prediction of network classifiers, by enforcing network prediction based on important image regions.
Few-shot Segmentation with Optimal Transport Matching and Message Flow
In this work, we argue that every support pixel's information is desired to be transferred to all query pixels and propose a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module to mine out the correspondence between the query and support images.
Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
To improve the generality of the objective activation maps, we propose a region prototypical network RPNet to explore the cross-image object diversity of the training set.
MV-TON: Memory-based Video Virtual Try-on network
With the development of Generative Adversarial Network, image-based virtual try-on methods have made great progress.
Cross-Modal Graph with Meta Concepts for Video Captioning
Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions.
Few-Shot Segmentation with Global and Local Contrastive Learning
To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning.
Learning Meta-class Memory for Few-Shot Semantic Segmentation
To explicitly learn meta-class representations in few-shot segmentation task, we propose a novel Meta-class Memory based few-shot segmentation method (MM-Net), where we introduce a set of learnable memory embeddings to memorize the meta-class information during the base class training and transfer to novel classes during the inference stage.
M2IOSR: Maximal Mutual Information Open Set Recognition
In this work, we aim to address the challenging task of open set recognition (OSR).
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
In this work we propose PointDisc, a point discriminative learning method to leverage self-supervisions for data-efficient 3D point cloud classification and segmentation.
Cycle-Consistent Inverse GAN for Text-to-Image Synthesis
In this paper, we propose a novel unified framework of Cycle-consistent Inverse GAN (CI-GAN) for both text-to-image generation and text-guided image manipulation tasks.
Remember What You have drawn: Semantic Image Manipulation with Memory
Therefore, in this paper, we propose a memory-based Image Manipulation Network (MIM-Net), where a set of memories learned from images is introduced to synthesize the texture information with the guidance of the textual description.
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds
While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud segmentation methods to relieve the labeling cost by learning from simpler and cheaper labels.
Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal Sequences
In turn, it also collects the reinforced features from each modality and uses them to generate a reinforced common message.
Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk
Due to the scarcity of annotated scene flow data, self-supervised scene flow learning in point clouds has attracted increasing attention.
Self-Supervised Learning
Self-supervised Scene Flow Estimation
HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
Scene flow in 3D point clouds plays an important role in understanding dynamic environments.
CT-Net: Complementary Transfering Network for Garment Transfer with Arbitrary Geometric Changes
Garment transfer shows great potential in realistic applications with the goal of transfering outfits across different people images.
Few-Shot Incremental Learning with Continually Evolved Classifiers
First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations.
Ranked #8 on
Few-Shot Class-Incremental Learning
on CIFAR-100
Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation
Data augmentation is vital for deep learning neural networks.
Online Active Proposal Set Generation for Weakly Supervised Object Detection
Online proposal sampling is an intuitive solution to these issues.
Progressive Self-Guided Loss for Salient Object Detection
We present a simple yet effective progressive self-guided loss function to facilitate deep learning-based salient object detection (SOD) in images.
CycleSegNet: Object Co-segmentation with Cycle Refinement and Region Correspondence
Image co-segmentation is an active computer vision task that aims to segment the common objects from a set of images.
Self-Supervised 3D Skeleton Action Representation Learning With Motion Consistency and Continuity
Recently, self-supervised learning (SSL) has been proved very effective and it can help boost the performance in learning representations from unlabeled data in the image domain.
Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion
To this end, both the marginal distribution and the elements with high-confidence correlations are aligned over the common space of the query and key vectors which are computed from different modalities.
Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
Moreover, when we use our network to handle the long-tail problem in a fully supervised point cloud segmentation dataset, it can also effectively boost the performance of the few-shot classes.
On Lightweight Privacy-Preserving Collaborative Learning for Internet of Things by Independent Random Projections
This paper considers the design and implementation of a practical privacy-preserving collaborative learning scheme, in which a curious learning coordinator trains a better machine learning model based on the data samples contributed by a number of IoT objects, while the confidentiality of the raw forms of the training data is protected against the coordinator.
Learning Regional Purity for Instance Segmentation on 3D Point Clouds
In this paper, we define a novel concept of “regional purity” as the percentage of neighboring points belonging to the same instance within a fixed-radius 3D space.
Ranked #15 on
3D Instance Segmentation
on ScanNet(v2)
Feature Flow: In-network Feature Flow Estimation for Video Object Detection
Optical flow, which expresses pixel displacement, is widely used in many computer vision tasks to provide pixel-level motion information.
Structure-Aware Generation Network for Recipe Generation from Images
We investigate an open research task of generating cooking instructions based on only food images and ingredients, which is similar to the image captioning task.
Graph Edit Distance Reward: Learning to Edit Scene Graph
Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA.
Open Set Recognition with Conditional Probabilistic Generative Models
A typical challenge that hinders their real-world applications is that unknown samples may be fed into the system during the testing phase, but traditional deep neural networks will wrongly recognize these unknown samples as one of the known classes.
Decomposing Generation Networks with Structure Prediction for Recipe Generation
Recipe generation from food images and ingredients is a challenging task, which requires the interpretation of the information from another modality.
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds
To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network.
CRNet: Cross-Reference Networks for Few-Shot Segmentation
In this paper, we propose a cross-reference network (CRNet) for few-shot segmentation.
Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection
To reduce the human labeling effort, we propose a novel webly supervised object detection (WebSOD) method for novel classes which only requires the web images without further annotations.
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
We employ the Earth Mover's Distance (EMD) as a metric to compute a structural distance between dense image representations to determine image relevance.
Video Object Segmentation and Tracking: A Survey
Second, we provide a detailed discussion and overview of the technical characteristics of the different methods.
A Dilated Inception Network for Visual Saliency Prediction
In this work, we proposed an end-to-end dilated inception network (DINet) for visual saliency prediction.
Towards Robust Curve Text Detection with Conditional Spatial Expansion
It is challenging to detect curve texts due to their irregular shapes and varying sizes.
CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets.
Ranked #86 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
On Lightweight Privacy-Preserving Collaborative Learning for IoT Objects
This paper considers the design and implementation of a practical privacy-preserving collaborative learning scheme, in which a curious learning coordinator trains a better machine learning model based on the data samples contributed by a number of IoT objects, while the confidentiality of the raw forms of the training data is protected against the coordinator.
M2E-Try On Net: Fashion from Model to Everyone
Instead, we present a novel virtual Try-On network, M2E-Try On Net, which transfers the clothes from a model image to a person image without the need of any clean product images.
Correlation Propagation Networks for Scene Text Detection
In this work, we propose a novel hybrid method for scene text detection namely Correlation Propagation Network (CPN).
Keypoint Based Weakly Supervised Human Parsing
We develop an iterative learning method to generate pseudo part segmentation masks from keypoint labels.
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
In this work, we focus on weak supervision, developing a method for training a high-quality pixel-level classifier for semantic segmentation, using only image-level class labels as the provided ground-truth.
MoNet: Deep Motion Exploitation for Video Object Segmentation
In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i. e., frame representation learning and segmentation refinement.
Learning Markov Clustering Networks for Scene Text Detection
MCN predicts instance-level bounding boxes by firstly converting an image into a Stochastic Flow Graph (SFG) and then performing Markov Clustering on this graph.
Decoupled Spatial Neural Attention for Weakly Supervised Semantic Segmentation
In our work, we focus on the weakly supervised semantic segmentation with image label annotations.
Weakly Supervised Semantic Segmentation Based on Web Image Co-segmentation
Training a Fully Convolutional Network (FCN) for semantic segmentation requires a large number of masks with pixel level labelling, which involves a large amount of human labour and time for annotation.
Structured Learning of Tree Potentials in CRF for Image Segmentation
In this fashion, we easily achieve nonlinear learning of potential functions on both unary and pairwise terms in CRFs.
Efficient Dense Labeling of Human Activity Sequences from Wearables using Fully Convolutional Networks
We conduct extensive experiments and demonstrate that our proposed approach is able to outperform the state-of-the-arts in terms of classification and label misalignment measures on three challenging datasets: Opportunity, Hand Gesture, and our new dataset.
Learning Multi-level Region Consistency with Dense Multi-label Networks for Semantic Segmentation
Semantic image segmentation is a fundamental task in image understanding.
Sequential Person Recognition in Photo Albums with a Recurrent Network
In this work, we propose to model the relational information between people as a sequence prediction task.
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation.
Ranked #13 on
Semantic Segmentation
on Trans10K
Crowd Counting via Weighted VLAD on Dense Attribute Feature Maps
Crowd counting is an important task in computer vision, which has many applications in video surveillance.
Exploring Context with Deep Structured models for Semantic Segmentation
We formulate deep structured models by combining CNNs and Conditional Random Fields (CRFs) for learning the patch-patch context between image regions.
Fast Training of Triplet-based Deep Binary Embedding Networks
To solve the first stage, we design a large-scale high-order binary codes inference algorithm to reduce the high-order objective to a standard binary quadratic problem such that graph cuts can be used to efficiently infer the binary code which serve as the label of each training datum.
Structured Learning of Binary Codes with Column Generation
Our column generation based method can be further generalized from the triplet loss to a general structured learning based framework that allows one to directly optimize multivariate performance measures.
Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss
We exemplify the usefulness of the proposed model on multi-class semantic labelling (discrete) and the robust depth estimation (continuous) problems.
Deeply Learning the Messages in Message Passing Inference
The network output dimension for message estimation is the same as the number of classes, in contrast to the network output for general CNN potential functions in CRFs, which is exponential in the order of the potentials.
Efficient piecewise training of deep structured models for semantic segmentation
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs).
Ranked #54 on
Semantic Segmentation
on PASCAL Context
CRF Learning with CNN Features for Image Segmentation
The deep CNN is trained on the ImageNet dataset and transferred to image segmentations here for constructing potentials of superpixels.
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Therefore, here we present a deep convolutional neural field model for estimating depths from single monocular images, aiming to jointly explore the capacity of deep CNN and continuous CRF.
Deep Convolutional Neural Fields for Depth Estimation from a Single Image
Therefore, we in this paper present a deep convolutional neural field model for estimating depths from a single image, aiming to jointly explore the capacity of deep CNN and continuous CRF.
Supervised Hashing Using Graph Cuts and Boosted Decision Trees
The proposed framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
Optimizing Ranking Measures for Compact Binary Code Learning
Hashing has proven a valuable tool for large-scale information retrieval.
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
Here we propose to use boosted decision trees for achieving non-linearity in hashing, which are fast to train and evaluate, hence more suitable for hashing with high dimensional data.
Fast Training of Effective Multi-class Boosting Using Coordinate Descent Optimization
Different from most existing multi-class boosting methods, which use the same set of weak learners for all the classes, we train class specified weak learners (i. e., each class has a different set of weak learners).
A General Two-Step Approach to Learning-Based Hashing
This framework allows a number of existing approaches to hashing to be placed in context, and simplifies the development of new problem-specific hashing methods.
StructBoost: Boosting Methods for Predicting Structured Output Variables
Inspired by structured support vector machines (SSVM), here we propose a new boosting algorithm for structured output prediction, which we refer to as StructBoost.
