Search Results for author:
Found 74 papers, 39 papers with code
Instance-Aware Embedding for Point Cloud Instance Segmentation
However, these methods are unaware of the instance context and fail to realize the boundary and geometric information of an instance, which are critical to separate adjacent objects.
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
However, due to the lack of information from multiple views, these works encounter difficulties in generating controllable novel views.
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
Human-centric perception tasks, e. g., human mesh recovery, pedestrian detection, skeleton-based action recognition, and pose estimation, have wide industrial applications, such as metaverse and sports analysis.
Consistent Video-to-Video Transfer Using Synthetic Dataset
We introduce a novel and efficient approach for text-based video-to-video editing that eliminates the need for resource-intensive per-video-per-model finetuning.
GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection
It models the uncertainty propagation relationship of the geometry projection during training, improving the stability and efficiency of the end-to-end model learning.
Compatible Transformer for Irregularly Sampled Multivariate Time Series
To analyze multivariate time series, most previous methods assume regular subsampling of time series, where the interval between adjacent measurements and the number of samples remain unchanged.
UniPAD: A Universal Pre-training Paradigm for Autonomous Driving
In the context of autonomous driving, the significance of effective feature learning is widely acknowledged.
PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigm
In this paper, we introduce a comprehensive 3D pre-training framework designed to facilitate the acquisition of efficient 3D representations, thereby establishing a pathway to 3D foundational models.
Ranked #1 on
Semantic Segmentation
on S3DIS
(using extra training data)
LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection
We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds.
Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation
Furthermore, we propose a multi-view fusion layer based temporal module which is equipped with a set of object slots and interacts with features from different views by attention mechanism to fulfill sufficient object representation completion.
Unsupervised Open-Vocabulary Object Localization in Videos
In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization.
Object-Centric Multiple Object Tracking
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
Coarse-to-Fine Amodal Segmentation with Shape Prior
To address this issue, we propose a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation.
Boosting Residual Networks with Group Knowledge
Specifically, we implicitly divide all subnets into hierarchical groups by subnet-in-subnet sampling, aggregate the knowledge of different subnets in each group during training, and exploit upper-level group knowledge to supervise lower-level subnet groups.
Experts Weights Averaging: A New General Training Scheme for Vision Transformers
As Vision Transformers (ViTs) are gradually surpassing CNNs in various visual tasks, one may question: if a training scheme specifically for ViTs exists that can also achieve performance improvement without increasing inference cost?
When Hyperspectral Image Classification Meets Diffusion Models: An Unsupervised Feature Learning Framework
Learning effective spectral-spatial features is important for the hyperspectral image (HSI) classification task, but the majority of existing HSI classification methods still suffer from modeling complex spectral-spatial relations and characterizing low-level details and high-level semantics comprehensively.
SAM3D: Segment Anything in 3D Scenes
In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further training or finetuning.
Learning for Open-World Calibration with Graph Neural Networks
We tackle the problem of threshold calibration for open-world recognition by incorporating representation compactness measures into clustering.
PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer
The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries.
Stimulative Training++: Go Beyond The Performance Limits of Residual Networks
In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of loafing, and further propose a new training scheme as well as three improved strategies for boosting residual networks beyond their performance limits.
Learning Manifold Dimensions with Conditional Variational Autoencoders
Although the variational autoencoder (VAE) and its conditional extension (CVAE) are capable of state-of-the-art results across multiple domains, their precise behavior is still not fully understood, particularly in the context of data (like images) that lie on or near a low-dimensional manifold.
LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation
Layout-to-image generation refers to the task of synthesizing photo-realistic images based on semantic layouts.
$β$-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Search
To address the robustness problem, we first benchmark different NAS methods under a wide range of proxy data, proxy channels, proxy layers and proxy epochs, since the robustness of NAS under different kinds of proxies has not been explored before.
Crossing the Gap: Domain Generalization for Image Captioning
In this paper, we introduce a new setting called Domain Generalization for Image Captioning (DGIC), where the data from the target domain is unseen in the learning process.
Ponder: Point Cloud Pre-training via Neural Rendering
We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering.
MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency
Besides, such scenes with progressive masking ratios can also serve to self-distill their intrinsic spatial consistency, requiring to learn the consistent representations from unmasked areas.
OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection
In contrast to the original hard depth labels, such soft pseudo labels with quality scores allow the network to learn a reasonable depth range, boosting training stability and thus improving final performance.
Frozen CLIP Model is An Efficient Point Cloud Backbone
This paper introduces Efficient Point Cloud Learning (EPCL), an effective and efficient point cloud learner for directly training high-quality point cloud models with a frozen CLIP model.
GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds
In contrast to previous 3D MAE frameworks, which either design a complex decoder to infer masked information from maintained regions or adopt sophisticated masking strategies, we instead propose a much simpler paradigm.
Reconstructing Hand-Held Objects from Monocular Video
The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker.
3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness.
LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
Data augmentations are important in training high-performance 3D object detectors for point clouds.
Self-supervised Amodal Video Object Segmentation
The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned.
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications.
Bridging the Gap to Real-World Object-Centric Learning
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm
Inspired by prompting approaches from NLP, we creatively reinterpret point cloud generation and refinement as the prompting and predicting stages, respectively.
PointInst3D: Segmenting 3D Instances by Points
The current state-of-the-art methods in 3D instance segmentation typically involve a clustering step, despite the tendency towards heuristics, greedy algorithms, and a lack of robustness to the changes in data statistics.
GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction
Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems.
Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning
Goal-oriented Reinforcement Learning (GoRL) is a promising approach for scaling up RL techniques on sparse reward environments requiring long horizon planning.
ARCH++: Animation-Ready Clothed Human Reconstruction Revisited
We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary clothing styles.
Ranked #1 on
3D Object Reconstruction From A Single Image
on RenderPeople
(using extra training data)
3D Object Reconstruction From A Single Image
Image-to-Image Translation
Progressive Coordinate Transforms for Monocular 3D Object Detection
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.
Dynamic Convolution for 3D Point Cloud Instance Segmentation
The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
Learning Hierarchical Graph Neural Networks for Image Clustering
Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
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.
ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting
Previous methods can be roughly categorized into two groups: character-based and segmentation-based, which often require character-level annotations and/or complex post-processing due to the unstructured output.
Ranked #7 on
Text Spotting
on Inverse-Text
Explore with Dynamic Map: Graph Structured Reinforcement Learning
In reinforcement learning, a map with states and transitions built based on historical trajectories is often helpful in exploration and exploitation.
DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
Previous top-performing approaches for point cloud instance segmentation involve a bottom-up strategy, which often includes inefficient operations or complex pipelines, such as grouping over-segmented components, introducing additional steps for refining, or designing complicated loss functions.
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
We propose Geo-PIFu, a method to recover a 3D mesh from a monocular color image of a clothed person.
FCOS: A simple and strong anchor-free object detector
In computer vision, object detection is one of most important tasks, which underpins a few instance-level recognition tasks and many downstream applications.
Improving Semantic Segmentation via Self-Training
In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.
ResNeSt: Split-Attention Networks
It is well known that featuremap attention and multi-path representation are important for visual recognition.
Ranked #8 on
Instance Segmentation
on COCO test-dev
(APM metric)
ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network
Our contributions are three-fold: 1) For the first time, we adaptively fit arbitrarily-shaped text by a parameterized Bezier curve.
Ranked #9 on
Text Spotting
on Inverse-Text
Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
3D point cloud semantic and instance segmentation is crucial and fundamental for 3D scene understanding.
Ranked #24 on
3D Instance Segmentation
on ScanNet(v2)
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints.
Ranked #32 on
Skeleton Based Action Recognition
on NTU RGB+D
Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection
More importantly, based on OBD, we provide a detailed analysis of the impact of a collection of refinements, which may inspire others to build state-of-the-art text detectors.
Ranked #3 on
Scene Text Detection
on ICDAR 2017 MLT
SAM: Squeeze-and-Mimic Networks for Conditional Visual Driving Policy Learning
To learn this representation, we train a squeeze network to drive using annotations for the side task as input.
Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs.
Ranked #34 on
Node Classification
on Cora
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes.
FCOS: Fully Convolutional One-Stage Object Detection
By eliminating the predefined set of anchor boxes, FCOS completely avoids the complicated computation related to anchor boxes such as calculating overlapping during training.
Ranked #5 on
Pedestrian Detection
on TJU-Ped-campus
Knowledge Adaptation for Efficient Semantic Segmentation
To tackle this dilemma, we propose a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride.
Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
In this work, we propose a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
Ranked #46 on
Semantic Segmentation
on PASCAL Context
Bag of Freebies for Training Object Detection Neural Networks
Training heuristics greatly improve various image classification model accuracies~\cite{he2018bag}.
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
We present a method to infer 3D pose and shape of vehicles from a single image.
GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
In this paper, we propose GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild.
GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling.
Bag of Tricks for Image Classification with Convolutional Neural Networks
Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.
Ranked #44 on
Domain Generalization
on VizWiz-Classification
FashionNet: Personalized Outfit Recommendation with Deep Neural Network
Our system, dubbed FashionNet, consists of two components, a feature network for feature extraction and a matching network for compatibility computation.
An end-to-end TextSpotter with Explicit Alignment and Attention
This allows the two tasks to work collaboratively by shar- ing convolutional features, which is critical to identify challenging text instances.
Single Shot Text Detector with Regional Attention
Our text detector achieves an F-measure of 77% on the ICDAR 2015 bench- mark, advancing the state-of-the-art results in [18, 28].
Ranked #4 on
Scene Text Detection
on COCO-Text
Detecting Text in Natural Image with Connectionist Text Proposal Network
We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image.
Accurate Text Localization in Natural Image with Cascaded Convolutional Text Network
We propose a novel Cascaded Convolutional Text Network (CCTN) that joints two customized convolutional networks for coarse-to-fine text localization.
Text-attentional convolutional neural network for scene text detection
Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images.
Text-Attentional Convolutional Neural Networks for Scene Text Detection
The rich supervision information enables the Text-CNN with a strong capability for discriminating ambiguous texts, and also increases its robustness against complicated background components.
