Search Results for author:
Found 139 papers, 46 papers with code
Object Tracking using Spatio-Temporal Networks for Future Prediction Location
To facilitate the future prediction ability, we follow three key observations: 1) object motion trajectory is affected significantly by camera motion; 2) the past trajectory of an object can act as a salient cue to estimate the object motion in the spatial domain; 3) previous frames contain the surroundings and appearance of the target object, which is useful for predicting the target object’s future locations.
Epona: Autoregressive Diffusion World Model for Autonomous Driving
In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiotemporal distribution modeling through two key innovations: 1) Decoupled spatiotemporal factorization that separates temporal dynamics modeling from fine-grained future world generation, and 2) Modular trajectory and video prediction that seamlessly integrate motion planning with visual modeling in an end-to-end framework.
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization
The framework employs a multi-stage spectral self-attention Transformer network (MTSIC) as the generator.
SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence
We propose SpatialLLM, a novel approach advancing spatial intelligence tasks in complex urban scenes.
CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation
This conditional multiview diffusion model not only allows the generation of 3D models part by part but also enables local editing of 3D models according to the local revision of the input image without changing other 3D parts.
A Two-Timescale Approach for Wireless Federated Learning with Parameter Freezing and Power Control
Based on this observation, we propose a two-timescale FL framework by joint optimization of freezing stabilized parameters and controlling transmit power for the unstable parameters to balance the energy consumption and convergence.
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
The compression performance of our method on original 3DGS is comparable to the dedicated Scaffold-GS-based compression methods, which demonstrate the huge potential of directly compressing original 3DGS with neural fields.
MMGen: Unified Multi-modal Image Generation and Understanding in One Go
A unified diffusion framework for multi-modal generation and understanding has the transformative potential to achieve seamless and controllable image diffusion and other cross-modal tasks.
OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning
Image Difference Captioning (IDC) aims to generate natural language descriptions of subtle differences between image pairs, requiring both precise visual change localization and coherent semantic expression.
CADDreamer: CAD Object Generation from Single-view Images
To address this gap, we introduce CADDreamer, a novel approach for generating boundary representations (B-rep) of CAD objects from a single image.
EquiBench: Benchmarking Large Language Models' Understanding of Program Semantics via Equivalence Checking
As large language models (LLMs) become integral to code-related tasks, a central question emerges: do LLMs truly understand program execution semantics?
MVTokenFlow: High-quality 4D Content Generation using Multiview Token Flow
To address this challenge, MVTokenFlow utilizes the multiview diffusion model to generate multiview images on different timesteps, which attains spatial consistency across different viewpoints and allows us to reconstruct a reasonable coarse 4D field.
WonderHuman: Hallucinating Unseen Parts in Dynamic 3D Human Reconstruction
In this paper, we present WonderHuman to reconstruct dynamic human avatars from a monocular video for high-fidelity novel view synthesis.
Implementing Finite Impulse Response Filters on Quantum Computers
While signal processing is a mature area, its connections with quantum computing have received less attention.
GaussianAvatar-Editor: Photorealistic Animatable Gaussian Head Avatar Editor
By integrating these methods, our GaussianAvatar-Editor achieves photorealistic and consistent results in animatable 4D Gaussian editing.
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction Attacks
Guided by the model, we further introduce: (1) a similarity-based training-free watermarking method for plug-and-play and flexible watermarking, and (2) a distribution-based multi-step watermark information transmission strategy for robust watermarking.
Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images.
PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions, especially on generated faces.
SolidGS: Consolidating Gaussian Surfel Splatting for Sparse-View Surface Reconstruction
Gaussian splatting has achieved impressive improvements for both novel-view synthesis and surface reconstruction from multi-view images.
GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting
3D open-vocabulary scene understanding, which accurately perceives complex semantic properties of objects in space, has gained significant attention in recent years.
POINTS1.5: Building a Vision-Language Model towards Real World Applications
Due to the scarcity of open-source Chinese datasets for vision-language models, we collect numerous images from the Internet and annotate them using a combination of manual and automatic methods.
ProtDAT: A Unified Framework for Protein Sequence Design from Any Protein Text Description
Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering.
Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
Recent developments in monocular depth estimation methods enable high-quality depth estimation of single-view images but fail to estimate consistent video depth across different frames.
GausSurf: Geometry-Guided 3D Gaussian Splatting for Surface Reconstruction
3D Gaussian Splatting has achieved impressive performance in novel view synthesis with real-time rendering capabilities.
SuperGaussians: Enhancing Gaussian Splatting Using Primitives with Spatially Varying Colors
However, the current Gaussian primitives only have a single view-dependent color and an opacity to represent the appearance and geometry of the scene, resulting in a non-compact representation.
MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
Once the Wavelet Manifold is built, WDM trains a diffusion model to generate human motions from Wavelet latent vectors.
Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
In this paper, we present a novel generalizable object pose estimation method to determine the object pose using only one RGB image.
EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
Our work aims to reconstruct hand-object interactions from a single-view image, which is a fundamental but ill-posed task.
Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play
Current reinforcement learning (RL) frameworks for large language models (LLM) post-training typically assume a fixed prompt distribution, which is sub-optimal and bottlenecks scalability.
Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds
In this paper, we propose the scaled-squared distance function (S$^{2}$DF), a novel implicit surface representation for modeling arbitrary surface types.
VistaDream: Sampling multiview consistent images for single-view scene reconstruction
Most existing methods only concentrate on building the consistency between the input image and the generated images while losing the consistency between the generated images.
MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks
We evaluate a wide variety of frontier vision-language models on MEGA-Bench to understand their capabilities across these dimensions.
OpenAnimals: Revisiting Person Re-Identification for Animals Towards Better Generalization
This paper addresses the challenge of animal re-identification, an emerging field that shares similarities with person re-identification but presents unique complexities due to the diverse species, environments and poses.
Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras
In this study, we propose a precise pose estimation method for dashcam images, leveraging the inherent camera motion prior.
FedGCA: Global Consistent Augmentation Based Single-Source Federated Domain Generalization
Federated Domain Generalization (FedDG) aims to train the global model for generalization ability to unseen domains with multi-domain training samples.
RRM: Robust Reward Model Training Mitigates Reward Hacking
Our RRM improves the performance of a pairwise reward model trained on Gemma-2-9b-it, on RewardBench, increasing accuracy from 80. 61% to 84. 15%.
PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion
Detailed and photorealistic 3D human modeling is essential for various applications and has seen tremendous progress.
POINTS: Improving Your Vision-language Model with Affordable Strategies
To address these issues, we propose the following contributions: 1) We trained a robust baseline model using the latest advancements in vision-language models, introducing effective improvements and conducting comprehensive ablation and validation for each technique.
Ranked #63 on
Visual Question Answering
on MM-Vet
GAS: Generative Activation-Aided Asynchronous Split Federated Learning
To address this issue, we consider an asynchronous SFL framework, where an activation buffer and a model buffer are embedded on the server to manage the asynchronously transmitted activations and client-side models, respectively.
Toward Mixed Analog-Digital Quantum Signal Processing: Quantum AD/DA Conversion and the Fourier Transform
We demonstrate the utility of this paradigm by showcasing how it naturally enables analog-digital conversion of quantum signals -- specifically, the transfer of states between DV and CV quantum systems.
TeethDreamer: 3D Teeth Reconstruction from Five Intra-oral Photographs
Orthodontic treatment usually requires regular face-to-face examinations to monitor dental conditions of the patients.
VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models
Based on the evaluation results obtained with the toolkit, we host OpenVLM Leaderboard, a comprehensive leaderboard to track the progress of multi-modality learning research.
Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion
In this paper, we explore a novel framework, EGIInet (Explicitly Guided Information Interaction Network), a model for View-guided Point cloud Completion (ViPC) task, which aims to restore a complete point cloud from a partial one with a single view image.
DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image
The first and only method for hand-face interaction recovery, Decaf, introduces a global fitting optimization guided by contact and deformation estimation networks trained on studio-collected data with 3D annotations.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention
Despite recent advancements in the Large Reconstruction Model (LRM) demonstrating impressive results, when extending its input from single image to multiple images, it exhibits inefficiencies, subpar geometric and texture quality, as well as slower convergence speed than expected.
MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors
In this paper, we propose MoDGS, a new pipeline to render novel views of dy namic scenes from a casually captured monocular video.
GECO: Generative Image-to-3D within a SECOnd
In the first stage, we train a single-step multi-view generative model with score distillation.
DreamMat: High-quality PBR Material Generation with Geometry- and Light-aware Diffusion Models
2D diffusion model, which often contains unwanted baked-in shading effects and results in unrealistic rendering effects in the downstream applications.
Part123: Part-aware 3D Reconstruction from a Single-view Image
However, all the existing methods represent the target object as a closed mesh devoid of any structural information, thus neglecting the part-based structure, which is crucial for many downstream applications, of the reconstructed shape.
Rethinking Overlooked Aspects in Vision-Language Models
Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial.
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
Specifically, these methods assume that the input images should comply with a predefined camera type, e. g. a perspective camera with a fixed focal length, leading to distorted shapes when the assumption fails.
SCALA: Split Federated Learning with Concatenated Activations and Logit Adjustments
Split Federated Learning (SFL) is a distributed machine learning framework which strategically divides the learning process between a server and clients and collaboratively trains a shared model by aggregating local models updated based on data from distributed clients.
IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination
This paper aims to recover object materials from posed images captured under an unknown static lighting condition.
An Evolutionary Network Architecture Search Framework with Adaptive Multimodal Fusion for Hand Gesture Recognition
To automatically adapt to various datasets, the ENAS framework is designed to automatically search a MHGR network with appropriate fusion positions and ratios.
Multiple Population Alternate Evolution Neural Architecture Search
Specifically, the global search space requires a significant amount of computational resources and time, the scalable search space sacrifices the diversity of network structures and the hierarchical search space increases the search cost in exchange for network diversity.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
Ranked #1 on
Zero-Shot Video Question Answer
on Zero-shot Video Question Answering on LongVideoBench
(using extra training data)
G-EvoNAS: Evolutionary Neural Architecture Search Based on Network Growth
The process begins from a shallow network, grows and evolves, and gradually deepens into a complete network, reducing the search complexity in the global space.
Closing the AI generalization gap by adjusting for dermatology condition distribution differences across clinical settings
Recently, there has been great progress in the ability of artificial intelligence (AI) algorithms to classify dermatological conditions from clinical photographs.
Extreme Two-View Geometry From Object Poses with Diffusion Models
Human has an incredible ability to effortlessly perceive the viewpoint difference between two images containing the same object, even when the viewpoint change is astonishingly vast with no co-visible regions in the images.
Coverage Axis++: Efficient Inner Point Selection for 3D Shape Skeletonization
We introduce Coverage Axis++, a novel and efficient approach to 3D shape skeletonization.
On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding
Sampling against this intrinsic frequency following the Nyquist-Sannon sampling theorem allows us to determine an appropriate training sampling rate.
Gemini: A Family of Highly Capable Multimodal Models
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding.
Ranked #1 on
Visual Question Answering (VQA)
on InfographicVQA
Disentangled Clothed Avatar Generation from Text Descriptions
In this paper, we introduce a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar.
Adaptive Multi-band Modulation for Robust and Low-complexity Faster-than-Nyquist Non-Orthogonal FDM IM-DD System
Faster-than-Nyquist non-orthogonal frequency-division multiplexing (FTN-NOFDM) is robust against the steep frequency roll-off by saving signal bandwidth.
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation.
Ranked #10 on
Motion Synthesis
on KIT Motion-Language
Combining Kernelized Autoencoding and Centroid Prediction for Dynamic Multi-objective Optimization
Evolutionary algorithms face significant challenges when dealing with dynamic multi-objective optimization because Pareto optimal solutions and/or Pareto optimal fronts change.
SparseDC: Depth Completion from sparse and non-uniform inputs
The key contributions of SparseDC are two-fold.
FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding
The structural embeddings can be used for fast and accurate protein search.
GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces
In this paper, we present GaussianShader, a novel method that applies a simplified shading function on 3D Gaussians to enhance the neural rendering in scenes with reflective surfaces while preserving the training and rendering efficiency.
Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
The experiments demonstrate the superior performance of Surf-D in shape generation across multiple modalities as conditions.
Asynchronous Wireless Federated Learning with Probabilistic Client Selection
Federated learning (FL) is a promising distributed learning framework where distributed clients collaboratively train a machine learning model coordinated by a server.
Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations
Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs).
Application of a Dense Fusion Attention Network in Fault Diagnosis of Centrifugal Fan
However, it is still a challenge to understand the correspondence between the structure and function of the model and the diagnosis process.
Accelerating Split Federated Learning over Wireless Communication Networks
The development of artificial intelligence (AI) provides opportunities for the promotion of deep neural network (DNN)-based applications.
Wonder3D: Single Image to 3D using Cross-Domain Diffusion
In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry.
Ranked #2 on
Single-View 3D Reconstruction
on GSO
Toward Intelligent Emergency Control for Large-scale Power Systems: Convergence of Learning, Physics, Computing and Control
Our developed methods and platform based on the convergence framework have been applied to a large (more than 3000 buses) Texas power system, and tested with 56000 scenarios.
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
In this paper, we present a novel diffusion model called that generates multiview-consistent images from a single-view image.
Ranked #3 on
Single-View 3D Reconstruction
on GSO
Local Structure-aware Graph Contrastive Representation Learning
Traditional Graph Neural Network (GNN), as a graph representation learning method, is constrained by label information.
Improving Pixel-based MIM by Reducing Wasted Modeling Capability
There has been significant progress in Masked Image Modeling (MIM).
A Blender-based channel simulator for FMCW Radar
The beat signal models of time division multiplexing (TDM)-MIMO are adapted to RT outputs.
MMBench: Is Your Multi-modal Model an All-around Player?
In response to these challenges, we propose MMBench, a bilingual benchmark for assessing the multi-modal capabilities of VLMs.
Evaluating AI systems under uncertain ground truth: a case study in dermatology
Our approach boils down to generating multiple samples of medical condition probabilities, then evaluating and averaging performance metrics based on these sampled probabilities.
NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
We present a neural rendering-based method called NeRO for reconstructing the geometry and the BRDF of reflective objects from multiview images captured in an unknown environment.
Hyperspectral Image Super-Resolution via Dual-domain Network Based on Hybrid Convolution
Moreover, to further improve the perceptual quality of HSI, a frequency loss(HFL) is introduced to optimize the model in the frequency domain.
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses.
F$^{2}$-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories
Based on our analysis, we further propose a novel space-warping method called perspective warping, which allows us to handle arbitrary trajectories in the grid-based NeRF framework.
Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction
This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses.
PixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling
Masked Image Modeling (MIM) has achieved promising progress with the advent of Masked Autoencoders (MAE) and BEiT.
Intrinsic Bayesian Optimisation on Complex Constrained Domain
Motivated by the success of Bayesian optimisation algorithms in the Euclidean space, we propose a novel approach to construct Intrinsic Bayesian optimisation (In-BO) on manifolds with a primary focus on complex constrained domains or irregular-shaped spaces arising as submanifolds of R2, R3 and beyond.
F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories
Existing fast grid-based NeRF training frameworks, like Instant-NGP, Plenoxels, DVGO, or TensoRF, are mainly designed for bounded scenes and rely on space warping to handle unbounded scenes.
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning
Learning effective motion features is an essential pursuit of video representation learning.
Modeling Global Distribution for Federated Learning with Label Distribution Skew
It introduces a global Generative Adversarial Network to model the global data distribution without access to local datasets, so the global model can be trained using the global information of data distribution without privacy leakage.
Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning
This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids.
Client Selection for Federated Bayesian Learning
Distributed Stein Variational Gradient Descent (DSVGD) is a non-parametric distributed learning framework for federated Bayesian learning, where multiple clients jointly train a machine learning model by communicating a number of non-random and interacting particles with the server.
Target Detection Framework for Lobster Eye X-Ray Telescopes with Machine Learning Algorithms
Then an algorithm based on morphological operations and two neural networks would be used to detect candidates of celestial objects with different flux from these 2D images.
Efficient Learning of Voltage Control Strategies via Model-based Deep Reinforcement Learning
We propose a novel model-based-DRL framework where a deep neural network (DNN)-based dynamic surrogate model, instead of a real-world power-grid or physics-based simulation, is utilized with the policy learning framework, making the process faster and sample efficient.
Gradient Domain Weighted Guided Image Filtering
Guided image filter is a well-known local filter in image processing.
SNAF: Sparse-view CBCT Reconstruction with Neural Attenuation Fields
Cone beam computed tomography (CBCT) has been widely used in clinical practice, especially in dental clinics, while the radiation dose of X-rays when capturing has been a long concern in CBCT imaging.
NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies
In this paper, we propose to represent surfaces as the Unsigned Distance Function (UDF) and develop a new volume rendering scheme to learn the neural UDF representation.
Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
The video background is clearly a source of static bias, but the video foreground, such as the clothing of the actor, can also provide static bias.
General non-linear imitation leads to limit cycles in eco-evolutionary dynamics
We extrapolate from the linear imitation function to general imitation function, which can be non-linear.
Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction
Data-driven predictive methods which can efficiently and accurately transform protein sequences into biologically active structures are highly valuable for scientific research and medical development.
Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing
Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities.
Progressively-connected Light Field Network for Efficient View Synthesis
ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses.
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.
Robust and Efficient Medical Imaging with Self-Supervision
These results suggest that REMEDIS can significantly accelerate the life-cycle of medical imaging AI development thereby presenting an important step forward for medical imaging AI to deliver broad impact.
Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images
In this paper, we present a generalizable model-free 6-DoF object pose estimator called Gen6D.
False Data Injection Attack on Electric Vehicle-Assisted Voltage Regulation
With the large scale penetration of electric vehicles (EVs) and the advent of bidirectional chargers, EV aggregators will become a major player in the voltage regulation market.
Diagnosing failures of fairness transfer across distribution shift in real-world medical settings
Diagnosing and mitigating changes in model fairness under distribution shift is an important component of the safe deployment of machine learning in healthcare settings.
ApolloRL: a Reinforcement Learning Platform for Autonomous Driving
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving.
Harmonic Modeling, Data Generation, and Analysis of Power Electronics-Interfaced Residential Loads
Integration of electronics-based residential appliances and distributed energy resources in homes is expected to rise with grid decarbonization.
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
In this paper, we propose a novel local descriptor-based framework, called You Only Hypothesize Once (YOHO), for the registration of two unaligned point clouds.
Ranked #5 on
Point Cloud Registration
on ETH (trained on 3DMatch)
(Recall (30cm, 5 degrees) metric)
Improving 3D Object Detection with Channel-wise Transformer
Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors.
AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds
Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points.
Ranked #5 on
Surface Normals Estimation
on PCPNet
A Contract Theory based Incentive Mechanism for Federated Learning
It is challenging to design proper incentives for the FL clients due to the fact that the task is privately trained by the clients.
Neural Rays for Occlusion-aware Image-based Rendering
On such a 3D point, these generalization methods will include inconsistent image features from invisible views, which interfere with the radiance field construction.
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
In NeuS, we propose to represent a surface as the zero-level set of a signed distance function (SDF) and develop a new volume rendering method to train a neural SDF representation.
Ranked #6 on
Novel View Synthesis
on RefRef
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
We develop and rigorously evaluate a deep learning based system that can accurately classify skin conditions while detecting rare conditions for which there is not enough data available for training a confident classifier.
The Blessings of Unlabeled Background in Untrimmed Videos
The key challenge is how to distinguish the action of interest segments from the background, which is unlabelled even on the video-level.
Noise Is Useful: Exploiting Data Diversity for Edge Intelligence
Edge intelligence requires to fast access distributed data samples generated by edge devices.
Information Theory Information Theory
Supervised Transfer Learning at Scale for Medical Imaging
However, for medical imaging, the value of transfer learning is less clear.
Contrast and Order Representations for Video Self-Supervised Learning
To address this, we present a contrast-and-order representation (CORP) framework for learning self-supervised video representations that can automatically capture both the appearance information within each frame and temporal information across different frames.
Ranked #3 on
Self-Supervised Action Recognition Linear
on UCF101
Action Recognition
Self-Supervised Action Recognition Linear
+1
Point2Skeleton: Learning Skeletal Representations from Point Clouds
We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds.
Learnable Motion Coherence for Correspondence Pruning
We propose a novel formulation of fitting coherent motions with a smooth function on a graph of correspondences and show that this formulation allows a closed-form solution by graph Laplacian.
Object Tracking Using Spatio-Temporal Future Prediction
Our trajectory prediction module predicts the target object's locations in the current and future frames based on the object's past trajectory.
Addressing the Real-world Class Imbalance Problem in Dermatology
Class imbalance is a common problem in medical diagnosis, causing a standard classifier to be biased towards the common classes and perform poorly on the rare classes.
Intrinsic Gaussian Processes on Manifolds and Their Accelerations by Symmetry
The introduction of our strip algorithm, tailored for manifolds with extra symmetries, and the ball algorithm, designed for arbitrary manifolds, constitutes our significant contribution.
Accelerated Deep Reinforcement Learning Based Load Shedding for Emergency Voltage Control
Load shedding has been one of the most widely used and effective emergency control approaches against voltage instability.
FedCoin: A Peer-to-Peer Payment System for Federated Learning
In FedCoin, blockchain consensus entities calculate SVs and a new block is created based on the proof of Shapley (PoSap) protocol.
GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs
Instead of feature pooling, we use group convolutions to exploit underlying structures of the extracted features on the group, resulting in descriptors that are both discriminative and provably invariant to the group of transformations.
A deep learning system for differential diagnosis of skin diseases
In this paper, we developed a deep learning system (DLS) to provide a differential diagnosis of skin conditions for clinical cases (skin photographs and associated medical histories).
AI for Earth: Rainforest Conservation by Acoustic Surveillance
Saving rainforests is a key to halting adverse climate changes.
BIG-bench Machine Learning
Environmental Sound Classification
+2
Multi-granularity Generator for Temporal Action Proposal
In this paper, we propose a multi-granularity generator (MGG) to perform the temporal action proposal from different granularity perspectives, relying on the video visual features equipped with the position embedding information.
Ranked #2 on
Action Recognition
on THUMOS’14
An Attention-Based Approach for Single Image Super Resolution
We propose an attention-based approach to give a discrimination between texture areas and smooth areas.
Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos
This note describes the details of our solution to the dense-captioning events in videos task of ActivityNet Challenge 2018.
Une véritable approche $\ell_0$ pour l'apprentissage de dictionnaire
Sparse representation learning has recently gained a great success in signal and image processing, thanks to recent advances in dictionary learning.
