Search Results for author:
Found 149 papers, 71 papers with code
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
For short-moment retrieval, FlashVTG increases mAP to 125% of previous SOTA performance.
Ranked #1 on
Highlight Detection
on TvSum
TEXGen: a Generative Diffusion Model for Mesh Textures
Instead, we focus on the fundamental problem of learning in the UV texture space itself.
BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery
We introduce the BioNeMo Framework to facilitate the training of computational biology and chemistry AI models across hundreds of GPUs.
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models
We believe our benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning.
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
Experiment results indicate that MM-WLAuslan is a challenging ISLR dataset, and we hope this dataset will contribute to the development of Auslan and the advancement of sign languages worldwide.
Diverse Sign Language Translation
In this work, we introduce a Diverse Sign Language Translation (DivSLT) task, aiming to generate diverse yet accurate translations for sign language videos.
The Effect of Personalization in FedProx: A Fine-grained Analysis on Statistical Accuracy and Communication Efficiency
FedProx is a simple yet effective federated learning method that enables model personalization via regularization.
MVGS: Multi-view-regulated Gaussian Splatting for Novel View Synthesis
3) Built on top of our multi-view regulated training, we further propose a cross-ray densification strategy, densifying more Gaussian kernels in the ray-intersect regions from a selection of views.
Ranked #1 on
Novel View Synthesis
on Mip-NeRF 360
TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm
Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners.
EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition
First, we define a supernet and propose a global and local alternate Neural Architecture Search method to search the optimal architecture alternately with a differentiable neural architecture search.
FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model
In the facial animation transfer component, we propose a novel Expression-driven Multi-avatar Animator, which first maps expressive semantics to the facial control parameters of 3D avatars and then imposes perceptual constraints between the input and output images to maintain expression consistency.
StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads
To address this challenge, we propose a one-shot style-controllable talking face generation method that can obtain speaking styles from reference speaking videos and drive the one-shot portrait to speak with the reference speaking styles and another piece of audio.
CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction
In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting.
PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation
(2) Image source: Unlike typical datasets that contain images from laboratory settings, PlantSeg primarily comprises in-the-wild plant disease images.
Snap and Diagnose: An Advanced Multimodal Retrieval System for Identifying Plant Diseases in the Wild
Plant disease recognition is a critical task that ensures crop health and mitigates the damage caused by diseases.
Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baseline
Motivated by this observation, we propose an in-the-wild multimodal plant disease recognition dataset that contains the largest number of disease classes but also text-based descriptions for each disease.
Affective Behaviour Analysis via Progressive Learning
To advance this, the 7th Affective Behavior Analysis in-the-wild (ABAW) competition establishes two tracks: i. e., the Multi-task Learning (MTL) Challenge and the Compound Expression (CE) challenge based on Aff-Wild2 and C-EXPR-DB datasets.
DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction
With this dataset, we make the generative model more robust to cars.
Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks
This approach enables agents to form a global consensus from local observations, using it as an additional piece of information to guide collaborative actions during execution.
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20. 1% in AR and achieving a 21. 3% AP improvement over SAM.
Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation
2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure.
RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation
These ranked documents sufficiently cover various query aspects and are aware of the generator's preferences, hence incentivizing it to produce rich and comprehensive responses for users.
3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
(1) \textbf{High-Volume}: 2, 500 cars are meticulously scanned by 3D scanners, obtaining car images and point clouds with real-world dimensions; (2) \textbf{High-Quality}: Each car is captured in an average of 200 dense, high-resolution 360-degree RGB-D views, enabling high-fidelity 3D reconstruction; (3) \textbf{High-Diversity}: The dataset contains various cars from over 100 brands, collected under three distinct lighting conditions, including reflective, standard, and dark.
QGait: Toward Accurate Quantization for Gait Recognition with Binarized Input
Minor variations in silhouette sequences can be diminished in the network's intermediate layers due to the accumulation of quantization errors.
3D MR Fingerprinting for Dynamic Contrast-Enhanced Imaging of Whole Mouse Brain
We present the first dynamic and multi-parametric approach for quantitatively tracking contrast agent transport in the mouse brain using 3D MRF.
Machine Unlearning via Null Space Calibration
Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data.
Affective Behaviour Analysis via Integrating Multi-Modal Knowledge
Affective Behavior Analysis aims to facilitate technology emotionally smart, creating a world where devices can understand and react to our emotions as humans do.
GO-NeRF: Generating Objects in Neural Radiance Fields for Virtual Reality Content Creation
Virtual environments (VEs) are pivotal for virtual, augmented, and mixed reality systems.
Super-resolution multi-contrast unbiased eye atlases with deep probabilistic refinement
These variations limit the feasibility and robustness of generalizing population-wise features of eye organs to an unbiased spatial reference.
EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Priors
This limitation leads to the Janus problem where multi-faced 3D models are generated under the guidance of such diffusion models.
Benchmarking Audio Visual Segmentation for Long-Untrimmed Videos
Considering that pixel-level annotations are difficult to achieve in some complex scenes we also provide the bounding boxes to indicate the sounding regions.
Text-Guided 3D Face Synthesis - From Generation to Editing
In the editing stage we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts.
GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy
To address this limitation, this paper presents GraphRARE, a general framework built upon node relative entropy and deep reinforcement learning, to strengthen the expressive capability of GNNs.
Ranked #3 on
Node Classification
on Cornell
UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects.
OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection
OpenSight utilizes 2D-3D geometric priors for the initial discernment and localization of generic objects, followed by a more specific semantic interpretation of the detected objects.
Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications.
Text-Guided 3D Face Synthesis -- From Generation to Editing
In the editing stage, we first employ a pre-trained diffusion model to update facial geometry or texture based on the texts.
Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
To generalize Tucker decomposition to such scenarios, we propose Functional Bayesian Tucker Decomposition (FunBaT).
Text-to-3D with Classifier Score Distillation
In this paper, we re-evaluate the role of classifier-free guidance in score distillation and discover a surprising finding: the guidance alone is enough for effective text-to-3D generation tasks.
Open-CRB: Towards Open World Active Learning for 3D Object Detection
This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts.
CBARF: Cascaded Bundle-Adjusting Neural Radiance Fields from Imperfect Camera Poses
Existing volumetric neural rendering techniques, such as Neural Radiance Fields (NeRF), face limitations in synthesizing high-quality novel views when the camera poses of input images are imperfect.
Divide and Ensemble: Progressively Learning for the Unknown
In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions.
DeformUX-Net: Exploring a 3D Foundation Backbone for Medical Image Segmentation with Depthwise Deformable Convolution
We hypothesize that deformable convolution can be an exploratory alternative to combine all advantages from the previous operators, providing long-range dependency, adaptive spatial aggregation and computational efficiency as a foundation backbone.
Multi-Resolution Active Learning of Fourier Neural Operators
To overcome this problem, we propose Multi-Resolution Active learning of FNO (MRA-FNO), which can dynamically select the input functions and resolutions to lower the data cost as much as possible while optimizing the learning efficiency.
Baichuan 2: Open Large-scale Language Models
Large language models (LLMs) have demonstrated remarkable performance on a variety of natural language tasks based on just a few examples of natural language instructions, reducing the need for extensive feature engineering.
Deep conditional generative models for longitudinal single-slice abdominal computed tomography harmonization
We further evaluate our method's capability to harmonize longitudinal positional variation on 1033 subjects from the Baltimore Longitudinal Study of Aging (BLSA) dataset, which contains longitudinal single abdominal slices, and confirmed that our method can harmonize the slice positional variance in terms of visceral fat area.
Enhancing Hierarchical Transformers for Whole Brain Segmentation with Intracranial Measurements Integration
Subsequently, the model is finetuned with 45 T1w 3D volumes from Open Access Series Imaging Studies (OASIS) where both 133 whole brain classes and TICV/PFV labels are available.
When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervision
CIP-WPIS leverages pretrained knowledge embedded in the 2D foundation model SAM and 3D geometric prior to achieve accurate point-wise instance labels from the bounding box annotations.
EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior
This limitation leads to the Janus problem, where multi-faced 3D models are generated under the guidance of such diffusion models.
Texture Generation on 3D Meshes with Point-UV Diffusion
In this work, we focus on synthesizing high-quality textures on 3D meshes.
BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge
In a nutshell, our BAVS is designed to eliminate the interference of background noise or off-screen sounds in segmentation by establishing the audio-visual correspondences in an explicit manner.
Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics
However, we observed that prior arts are prone to segment a certain salient object in a video regardless of the audio information.
ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning
In addition, the proposed framework is model-agnostic and can be applied to most of the current MARL algorithms.
Boosting Model Inversion Attacks with Adversarial Examples
Hence, in this paper, we propose a new training paradigm for a learning-based model inversion attack that can achieve higher attack accuracy in a black-box setting.
Robust Multi-Agent Control via Maximum Entropy Heterogeneous-Agent Reinforcement Learning
Finally, we generalize a unified template for MaxEnt algorithmic design named \emph{Maximum Entropy Heterogeneous-Agent Mirror Learning} (MEHAML), which provides any induced method with the same guarantees as HASAC.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Multi-Contrast Computed Tomography Atlas of Healthy Pancreas
Briefly, DEEDs affine and non-rigid registration are performed to transfer patient abdominal volumes to a fixed high-resolution atlas template.
EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation
In this work, we propose EmotionGesture, a novel framework for synthesizing vivid and diverse emotional co-speech 3D gestures from audio.
Autonomous Stabilization of Retinal Videos for Streamlining Assessment of Spontaneous Venous Pulsations
Both of the evaluations support its effectiveness in facilitating the observation of SVPs.
Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
Rendering novel view images is highly desirable for many applications.
TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles
Leveraging the proposed dataset, we introduce a CLIP-based style encoder that projects natural language-based descriptions to the representations of expressions.
2D Semantic Segmentation task 3 (25 classes)
Talking Head Generation
NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination
Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images.
Ranked #2 on
Surface Normals Estimation
on Stanford-ORB
DyGait: Exploiting Dynamic Representations for High-performance Gait Recognition
This is the first framework on gait recognition that is designed to focus on the extraction of dynamic features.
Low-frequency Image Deep Steganography: Manipulate the Frequency Distribution to Hide Secrets with Tenacious Robustness
By avoiding high-frequency artifacts and manipulating the frequency distribution of the embedded feature map, LIDS achieves improved robustness against attacks that distort the high-frequency components of container images.
Scaling Up 3D Kernels with Bayesian Frequency Re-parameterization for Medical Image Segmentation
We hypothesize that convolution with LK sizes is limited to maintain an optimal convergence for locality learning.
Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand Disentanglement
Considering the asymmetric gestures and motions of two hands, we introduce a Spatial-Residual Memory (SRM) module to model spatial interaction between the body and each hand by residual learning.
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition
Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game.
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
To achieve maximum deviation in victim policies under complex agent-wise interactions, our unilateral attack aims to characterize and maximize the impact of the adversary on the victims.
Exploring Active 3D Object Detection from a Generalization Perspective
To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance.
Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regions
One surprising trait of neural networks is the extent to which their connections can be pruned with little to no effect on accuracy.
StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles
In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio.
Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States
In HiNL, we propose a History-aware State Estimation (HaSE) module to alleviate the impacts of dominant historical states on the current state estimation.
FlowFace: Semantic Flow-guided Shape-aware Face Swapping
Unlike most previous methods that focus on transferring the source inner facial features but neglect facial contours, our FlowFace can transfer both of them to a target face, thus leading to more realistic face swapping.
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models.
Single Slice Thigh CT Muscle Group Segmentation with Domain Adaptation and Self-Training
The proposed pipeline is effective and robust in extracting muscle groups on 2D single slice CT thigh images. The container is available for public use at https://github. com/MASILab/DA_CT_muscle_seg
Evidence-based Match-status-Aware Gait Recognition for Out-of-Gallery Gait Identification
We measure the uncertainty and predict the match status of the recognition results, and thus determine whether the probe is an OOG query. To the best of our knowledge, our method is the first attempt to tackle OOG queries in gait recognition.
Facial Action Units Detection Aided by Global-Local Expression Embedding
We find that AUs and facial expressions are highly associated, and existing facial expression datasets often contain a large number of identities.
Batch Multi-Fidelity Active Learning with Budget Constraints
However, this method only queries at one pair of fidelity and input at a time, and hence has a risk to bring in strongly correlated examples to reduce the learning efficiency.
Adaptive Contrastive Learning with Dynamic Correlation for Multi-Phase Organ Segmentation
We evaluate our proposed approach on multi-organ segmentation with both non-contrast CT (NCCT) datasets and the MICCAI 2015 BTCV Challenge contrast-enhance CT (CECT) datasets.
Is synthetic data from generative models ready for image recognition?
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images.
Deep Idempotent Network for Efficient Single Image Blind Deblurring
Single image blind deblurring is highly ill-posed as neither the latent sharp image nor the blur kernel is known.
Meta Knowledge Condensation for Federated Learning
In this work, we first introduce a meta knowledge representation method that extracts meta knowledge from distributed clients.
Reducing Positional Variance in Cross-sectional Abdominal CT Slices with Deep Conditional Generative Models
External experiments on 20 subjects from the Baltimore Longitudinal Study of Aging (BLSA) dataset that contains longitudinal single abdominal slices validate that our method can harmonize the slice positional variance in terms of muscle and visceral fat area.
UNesT: Local Spatial Representation Learning with Hierarchical Transformer for Efficient Medical Segmentation
Transformer-based models, capable of learning better global dependencies, have recently demonstrated exceptional representation learning capabilities in computer vision and medical image analysis.
Longitudinal Variability Analysis on Low-dose Abdominal CT with Deep Learning-based Segmentation
Metabolic health is increasingly implicated as a risk factor across conditions from cardiology to neurology, and efficiency assessment of body composition is critical to quantitatively characterizing these relationships.
CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization
The critical challenge of this task is to learn a powerful global feature descriptor for the sequential ground-view images while considering its domain alignment with reference satellite images.
Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
In this work, we propose a new online VIS paradigm named Instance As Identity (IAI), which models temporal information for both detection and tracking in an efficient way.
GaitGL: Learning Discriminative Global-Local Feature Representations for Gait Recognition
GFR extractor aims to extract contextual information, e. g., the relationship among various body parts, and the mask-based LFR extractor is presented to exploit the detailed posture changes of local regions.
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i. e., ultra-high-definition) images.
Ranked #1 on
Image Restoration
on UHDM
MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views
We propose MHR-Net, a novel method for recovering Non-Rigid Shapes from Motion (NRSfM).
"Understanding Robustness Lottery": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches
We decomposed and evaluated a set of critical geometric concepts from the common adopted classification loss, and used them to design a visualization system to compare and highlight the impact of pruning on model performance and feature representation.
Recall Distortion in Neural Network Pruning and the Undecayed Pruning Algorithm
In this work, we study such relative distortions in recall by hypothesizing an intensification effect that is inherent to the model.
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.
Ranked #3 on
3D Action Recognition
on NTU RGB+D
Pseudo-Label Guided Multi-Contrast Generalization for Non-Contrast Organ-Aware Segmentation
In this paper, we propose a novel unsupervised approach that leverages pairwise contrast-enhanced CT (CECT) context to compute non-contrast segmentation without ground-truth label.
Video Demoireing with Relation-Based Temporal Consistency
Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
We address the problem of ground-to-satellite image geo-localization, that is, estimating the camera latitude, longitude and orientation (azimuth angle) by matching a query image captured at the ground level against a large-scale database with geotagged satellite images.
The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks
We propose a tractable heuristic for solving the combinatorial extension of OBS, in which we select weights for simultaneous removal, as well as a systematic update of the remaining weights.
GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework
ECM consists of the Spatial-Temporal feature extractor (ST), the Frame-Level feature extractor (FL) and SPB, and has two obvious advantages: First, each branch focuses on a specific representation, which can be used to improve the robustness of the network.
Gait Recognition with Mask-based Regularization
Also, we design an Inception-like ReverseMask Block, which has three branches composed of a global branch, a feature dropping branch, and a feature scaling branch.
Ranked #4 on
Gait Recognition
on OUMVLP
Characterizing Renal Structures with 3D Block Aggregate Transformers
Efficiently quantifying renal structures can provide distinct spatial context and facilitate biomarker discovery for kidney morphology.
Learning Implicit Body Representations from Double Diffusion Based Neural Radiance Fields
In this paper, we present a novel double diffusion based neural radiance field, dubbed DD-NeRF, to reconstruct human body geometry and render the human body appearance in novel views from a sparse set of images.
One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning
Hence, we propose a novel one-shot talking face generation framework by exploring consistent correlations between audio and visual motions from a specific speaker and then transferring audio-driven motion fields to a reference image.
Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph
We use a coarse graph, derived from a dense graph, to estimate the human's 3D pose, and the dense graph to estimate the 3D shape.
Ranked #269 on
3D Human Pose Estimation
on Human3.6M
RGB-D Saliency Detection via Cascaded Mutual Information Minimization
In this paper, we introduce a novel multi-stage cascaded learning framework via mutual information minimization to "explicitly" model the multi-modal information between RGB image and depth data.
FDA: Feature Decomposition and Aggregation for Robust Airway Segmentation
Compared to other state-of-the-art transfer learning methods, our method accurately segmented more bronchi in the noisy CT scans.
PR-RRN: Pairwise-Regularized Residual-Recursive Networks for Non-rigid Structure-from-Motion
As NRSfM is a highly under-constrained problem, we propose two new pairwise regularization to further regularize the reconstruction.
Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails
Specifically, we design a novel cross-modal transformer module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively.
Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion
As this keypoint based representation models the motions of facial regions, head, and backgrounds integrally, our method can better constrain the spatial and temporal consistency of the generated videos.
Removing Raindrops and Rain Streaks in One Go
First, we propose a complementary cascaded network architecture, namely CCN, to remove rain streaks and raindrops in a unified framework.
Ranked #5 on
Video deraining
on Video Waterdrop Removal Dataset
Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation
Medical image segmentation, or computing voxelwise semantic masks, is a fundamental yet challenging task to compute a voxel-level semantic mask.
VidFace: A Full-Transformer Solver for Video FaceHallucination with Unaligned Tiny Snapshots
In this paper, we investigate the task of hallucinating an authentic high-resolution (HR) human face from multiple low-resolution (LR) video snapshots.
VTNet: Visual Transformer Network for Object Goal Navigation
In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation.
Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation
To be specific, our framework consists of a speaker-independent stage and a speaker-specific stage.
DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistency
In the first step, the framework learns to segment objects from real and synthetic data in a weakly-supervised fashion, and the segmentation masks will act as a prior for pose estimation.
Self-Supervised Visibility Learning for Novel View Synthesis
We then warp and aggregate source view pixels to synthesize a novel view based on the estimated source-view visibility and target-view depth.
Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
By iteratively updating the latent representations and our decoder, our DAP-FSR will be adapted to the target domain, thus achieving authentic and high-quality upsampled HR faces.
ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions.
Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
Specifically, we observe that when a 3D point in the real world is visible in both views, there is a deterministic mapping between the projected points in the two-view images given the height information of this 3D point.
Scaling Up Exact Neural Network Compression by ReLU Stability
We can compress a rectifier network while exactly preserving its underlying functionality with respect to a given input domain if some of its neurons are stable.
Modeling the Probabilistic Distribution of Unlabeled Data forOne-shot Medical Image Segmentation
Thus, it is more desirable to employ only a few labeled data in pursuing high segmentation performance.
Iterative Optimisation with an Innovation CNN for Pose Refinement
Object pose estimation from a single RGB image is a challenging problem due to variable lighting conditions and viewpoint changes.
RFNet: Region-Aware Fusion Network for Incomplete Multi-Modal Brain Tumor Segmentation
In this work, we propose a Region-aware Fusion Network (RFNet) that is able to exploit different combinations of multi-modal data adaptively and effectively for tumor segmentation.
Ranked #75 on
Semantic Segmentation
on NYU Depth v2
Uncertainty-Aware Deep Calibrated Salient Object Detection
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy.
Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation
Towards this goal, we take advantage of both global visual information and local region details and develop a Global and Local Feature Extractor (GLFE).
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
Sign language translation (SLT) aims to interpret sign video sequences into text-based natural language sentences.
Mapping of Sparse 3D Data using Alternating Projection
We propose a novel technique to register sparse 3D scans in the absence of texture.
Learning Object Relation Graph and Tentative Policy for Visual Navigation
Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN).
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks.
Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
Cross-view geo-localization is the problem of estimating the position and orientation (latitude, longitude and azimuth angle) of a camera at ground level given a large-scale database of geo-tagged aerial (e. g., satellite) images.
Weakly-Supervised Salient Object Detection via Scribble Annotations
In this paper, we propose a weakly-supervised salient object detection model to learn saliency from such annotations.
Transferring Cross-domain Knowledge for Video Sign Language Recognition
To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features.
Copy and Paste GAN: Face Hallucination from Shaded Thumbnails
This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination.
6DoF Object Pose Estimation via Differentiable Proxy Voting Loss
In this paper, we aim to reduce such errors by incorporating the distances between pixels and keypoints into our objective.
Face Hallucination with Finishing Touches
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
The first step is to apply a regular polar transform to warp an aerial image such that its domain is closer to that of a ground-view panorama.
Ranked #5 on
Image-Based Localization
on VIGOR Cross Area
Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
Based on this new large-scale dataset, we are able to experiment with several deep learning methods for word-level sign recognition and evaluate their performances in large scale scenarios.
Ranked #4 on
Sign Language Recognition
on WLASL100
Optimal Feature Transport for Cross-View Image Geo-Localization
This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.
Can generalised relative pose estimation solve sparse 3D registration?
In contrast to correspondence based methods, we take a different viewpoint and formulate the sparse 3D registration problem based on the constraints from the intersection of line segments from adjacent scans.
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors.
Identity-preserving Face Recovery from Stylized Portraits
We develop an Identity-preserving Face Recovery from Portraits (IFRP) method that utilizes a Style Removal network (SRN) and a Discriminative Network (DN).
Recovering Faces from Portraits with Auxiliary Facial Attributes
%Our method can recover high-quality photorealistic faces from unaligned portraits while preserving the identity of the face images as well as it can reconstruct a photorealistic face image with a desired set of attributes.
High Frame Rate Video Reconstruction based on an Event Camera
Based on the abundant event data alongside a low frame rate, easily blurred images, we propose a simple yet effective approach to reconstruct high-quality and high frame rate sharp videos.
Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera
In this paper, we propose a simple and effective approach, the \textbf{Event-based Double Integral (EDI)} model, to reconstruct a high frame-rate, sharp video from a single blurry frame and its event data.