Search Results for author:
Found 30 papers, 7 papers with code
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.
A Closer Look at Self-Supervised Lightweight Vision Transformers
We also point out some defects of such pre-training, e. g., failing to benefit from large-scale pre-training data and showing inferior performance on data-insufficient downstream tasks.
A Survey of Label-Efficient Deep Learning for 3D Point Clouds
We address three critical questions in this emerging research field: i) the importance and urgency of label-efficient learning in point cloud processing, ii) the subfields it encompasses, and iii) the progress achieved in this area.
VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning
Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning.
Masked AutoDecoder is Effective Multi-Task Vision Generalist
Inspired by the success of general-purpose models in NLP, recent studies attempt to unify different vision tasks in the same sequence format and employ autoregressive Transformers for sequence prediction.
Infrared and Visible Image Fusion via Interactive Compensatory Attention Adversarial Learning
The existing generative adversarial fusion methods generally concatenate source images and extract local features through convolution operation, without considering their global characteristics, which tends to produce an unbalanced result and is biased towards the infrared image or visible image.
Handling The Non-Smooth Challenge in Tensor SVD: A Multi-Objective Tensor Recovery Framework
We develop a new optimization algorithm named the Alternating Proximal Multiplier Method (APMM) to iteratively solve the proposed tensor completion model.
Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations
We apply our method to two of the typical actor-critic reinforcement learning algorithms, DDPG and ACER, and demonstrate with experiments that our method not only outperforms the RL algorithms without pretraining process, but also is more simulation efficient.
Multiple Object Tracking: A Literature Review
We inspect the recent advances in various aspects and propose some interesting directions for future research.
Constructive neural network learning
In this paper, we aim at developing scalable neural network-type learning systems.
Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors
In this context, the state-of-the-art algorithms RASL'' and "TILT'' can be viewed as two special cases of our work, and yet each only performs part of the function of our method."
Local Subspace Collaborative Tracking
To address this, this paper presents a local subspace collaborative tracking method for robust visual tracking, where multiple linear and nonlinear subspaces are learned to better model the nonlinear relationship of object appearances.
Pretrain Soft Q-Learning with Imperfect Demonstrations
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms.
Self-Weighted Robust LDA for Multiclass Classification with Edge Classes
In this regard, a novel self-weighted robust LDA with l21-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.
Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network
In this paper, we propose a cross-modal self-attention (CMSA) module to utilize fine details of individual words and the input image or video, which effectively captures the long-range dependencies between linguistic and visual features.
Ranked #5 on
Referring Expression Segmentation
on J-HMDB
(Precision@0.9 metric)
DA-DETR: Domain Adaptive Detection Transformer with Information Fusion
DA-DETR introduces a novel CNN-Transformer Blender (CTBlender) that fuses the CNN features and Transformer features ingeniously for effective feature alignment and knowledge transfer across domains.
Semantics-Guided Contrastive Network for Zero-Shot Object detection
To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection.
Ranked #4 on
Zero-Shot Object Detection
on MS-COCO
Contrastive Learning
Generalized Zero-Shot Object Detection
+3
DcnnGrasp: Towards Accurate Grasp Pattern Recognition with Adaptive Regularizer Learning
The task of grasp pattern recognition aims to derive the applicable grasp types of an object according to the visual information.
UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration
Domain adaptive panoptic segmentation aims to mitigate data annotation challenge by leveraging off-the-shelf annotated data in one or multiple related source domains.
Ranked #2 on
Domain Adaptation
on Panoptic SYNTHIA-to-Cityscapes
VMRF: View Matching Neural Radiance Fields
With the feature transport plan as the guidance, a novel pose calibration technique is designed which rectifies the initially randomized camera poses by predicting relative pose transformations between the pair of rendered and real images.
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution
In addition, stochastic noises fed to the generator are employed for unconditional detail generation, which tends to produce unfaithful details that compromise the fidelity of the generated SR image.
Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors.
Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning
HCD consists of a hierarchical dehazing network (HDN) and a novel hierarchical contrastive loss (HCL).
Audio-Driven Talking Face Generation with Diverse yet Realistic Facial Animations
To accommodate fair variation of plausible facial animations for the same audio, we design a transformer-based probabilistic mapping network that can model the variational facial animation distribution conditioned upon the input audio and autoregressively convert the audio signals into a facial animation sequence.
A Novel Tensor Factorization-Based Method with Robustness to Inaccurate Rank Estimation
This study aims to solve the over-reliance on the rank estimation strategy in the standard tensor factorization-based tensor recovery and the problem of a large computational cost in the standard t-SVD-based tensor recovery.
WaveNeRF: Wavelet-based Generalizable Neural Radiance Fields
Neural Radiance Field (NeRF) has shown impressive performance in novel view synthesis via implicit scene representation.
Pose-Free Neural Radiance Fields via Implicit Pose Regularization
However, as the pose estimator is trained with only rendered images, the pose estimation is usually biased or inaccurate for real images due to the domain gap between real images and rendered images, leading to poor robustness for the pose estimation of real images and further local minima in joint optimization.
Adversarial Attacks on Video Object Segmentation with Hard Region Discovery
Particularly, the gradients from the segmentation model are exploited to discover the easily confused region, in which it is difficult to identify the pixel-wise objects from the background in a frame.
Conditional Tuning Network for Few-Shot Adaptation of Segmentation Anything Model
CAT-SAM freezes the entire SAM and adapts its mask decoder and image encoder simultaneously with a small number of learnable parameters.
Weakly Supervised Monocular 3D Detection with a Single-View Image
We propose SKD-WM3D, a weakly supervised monocular 3D detection framework that exploits depth information to achieve M3D with a single-view image exclusively without any 3D annotations or other training data.
